Skip to content
Back to search

academic-research-skills

MarketplaceWorks with Claude CodeGitHub

Academic Research Skills — contract-audited research, writing, peer review, and pipeline orchestration for Claude Code.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 15 Nov 2026. Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Imbad0202/academic-research-skills with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Imbad0202/academic-research-skills'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/imbad0202-academic-research-skills/badge.svg)](/listings/imbad0202-academic-research-skills)

HTML

<a href="/listings/imbad0202-academic-research-skills"><img src="/api/listings/imbad0202-academic-research-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Prerequisites**

- [Claude Code](https://docs.claude.com/en/docs/claude-code/setup) (latest; plugin packaging requires recent versions) - `ANTHROPIC_API_KEY` exported, or set on first `claude` run - *Optional:* Pandoc for DOCX, tectonic + Source Han Serif TC for APA 7.0 PDF (Markdown output works without either) - *Optional (real Python):* needed only for the write-scope guard and a few opt-in commands; the core skills are prompt-driven. Details, including the Windows notes on Git Bash and the Microsoft Store Python stub, are in [docs/SETUP.md § Python (optional)](docs/SETUP.md#python-optional).

> **Which controls are active in *your* install channel?** Availability varies by install channel. See the per-channel map: [docs/CONTROL_AVAILABILITY.md](docs/CONTROL_AVAILABILITY.md).

**Plugin install (v3.7.0+, recommended):**

/plugin marketplace add Imbad0202/academic-research-skills
/plugin install academic-research-skills

**Verify it works:** run `/ars-plan` and describe a paper you're working on — ARS will start a Socratic dialogue to map out chapter structure. For a single-shot test instead, try `/ars-lit-review "your topic"`.

**👉 [docs/SETUP.md](docs/SETUP.md)** — full guide: install Claude Code, set up API keys, optional Pandoc/tectonic for DOCX/PDF, cross-model verification (`ARS_CROSS_MODEL`), and six installation methods (Plugin for Claude Code / claude.ai / Claude Desktop, project skills, global skills, claude.ai Project, repo-cloned, Claude Science import).

**👉 [docs/DATA_FLOWS.md](docs/DATA_FLOWS.md)** — what leaves your machine (bibliographic resolvers, optional consent-gated cross-model calls, the plugin update check), what is cached locally, for how long, and how to turn each path off.

**👉 [docs/RISK_REGISTER.md](docs/RISK_REGISTER.md)** — the standing risks the suite knows about, which existing controls address each one, the evidence status behind those controls, and what remains open.

**Using Claude Science?** The five skills import directly: **Skills → Import from GitHub**, paste `https://github.com/Imbad0202/academic-research-skills`, **Preview**, then **Import** (requires v3.14.0+ of this repo — the importer reads the explicit skill paths in the marketplace manifest). Imports are point-in-time snapshots: re-import after ARS updates. Imported skills carry the ARS methodology (research / writing / review protocols); Claude Code-specific machinery — slash commands, hooks, subagent orchestration — does not transfer. See [docs/SETUP.md](docs/SETUP.md) Method 5 for details.

**Using Pi?** Install the in-tree, community-maintained wrapper with `pi install git:github.com/Imbad0202/academic-research-skills`. It keeps the original ARS content authoritative and documents Pi-specific orchestration and hook limitations. See [`pi/README.md`](pi/README.md).

**Using Codex CLI?** Install the sibling distribution instead: [`Imbad0202/academic-research-skills-codex`](https://github.com/Imbad0202/academic-research-skills-codex) — same workflow content, Codex-native packaging as a single `$academic-research-suite` skill with `ars-*` aliases.

**Third-party platforms and integrations** that wrap or host ARS are listed in [THIRD_PARTY.md](THIRD_PARTY.md) — community-submitted and not reviewed or endorsed by the maintainer.

**Governance:** who decides, what cross-model review does and does not provide, and the project's end-of-life posture are stated in [GOVERNANCE.md](GOVERNANCE.md); security reporting and triage in [SECURITY.md](SECURITY.md).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 24 lines
  1. {
  2. "name": "academic-research-skills",
  3. "owner": {
  4. "name": "Cheng-I Wu",
  5. "url": "https://github.com/Imbad0202"
  6. },
  7. "description": "Academic Research Skills — contract-audited research, writing, peer review, and pipeline orchestration for Claude Code.",
  8. "plugins": [
  9. {
  10. "name": "academic-research-skills",
  11. "source": "./",
  12. "description": "5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.",
  13. "version": "3.24.3",
  14. "license": "CC-BY-NC-4.0",
  15. "skills": [
  16. "./academic-paper",
  17. "./academic-paper-reviewer",
  18. "./academic-pipeline",
  19. "./deep-research",
  20. "./sr-screener"
  21. ]
  22. }
  23. ]
  24. }
README.md · README · 405 lines
  1. # Academic Research Skills for Claude Code
  2. [![Version](https://img.shields.io/badge/version-v3.24.3-blue)](https://github.com/Imbad0202/academic-research-skills/releases/tag/v3.24.3)
  3. [![DOI](https://img.shields.io/badge/DOI-10.5281%2Fzenodo.20696614-blue)](https://doi.org/10.5281/zenodo.20696614)
  4. [![License: CC BY-NC 4.0](https://img.shields.io/badge/license-CC%20BY--NC%204.0-lightgrey)](https://creativecommons.org/licenses/by-nc/4.0/)
  5. [![Sponsor](https://img.shields.io/badge/sponsor-Buy%20Me%20a%20Coffee-orange?logo=buy-me-a-coffee)](https://buymeacoffee.com/crucify020v)
  6. [简体中文版](README.zh-CN.md) | [繁體中文版](README.zh-TW.md) | [日本語版](README.ja-JP.md) | [한국어](README.ko-KR.md) | [Español](README.es-ES.md) | [Português](README.pt-BR.md)
  7. A comprehensive suite of Claude Code skills for academic research, covering the full pipeline from research to publication.
  8. **Install in 30 seconds** (Claude Code CLI / VS Code / JetBrains, v3.7.0+):
  9. ```text
  10. /plugin marketplace add Imbad0202/academic-research-skills
  11. /plugin install academic-research-skills
  12. ```
  13. Then try `/ars-plan` to walk through your paper structure via Socratic dialogue, or jump to [Quick install](#quick-install) for prerequisites and the traditional symlink flow.
  14. On claude.ai or Claude Desktop (paid plans), add the same repository under **Customize → Plugins → Add → Add marketplace → Add from a repository**, then install `academic-research-skills`. Hooks and plugin agents do not run in plain chat there; see [SETUP Method 0](docs/SETUP.md#install-from-claudeai-or-claude-desktop-account-marketplace).
  15. > **AI is your copilot, not the pilot.** It can draft text, including a whole paper in full mode, but the decisions stay yours, and the pipeline stops for your confirmation at every stage. It handles the grunt work (hunting down references, formatting citations, verifying data, checking logical consistency) so you can focus on the parts that actually require your brain: defining the question, choosing the method, interpreting what the data means, and deciding what comes after "I argue that." You remain the author, and you answer for every claim you submit.
  16. >
  17. > Unlike a humanizer, this tool doesn't help you hide the fact that you used AI. It helps you write better. Style Calibration learns your voice from past work. Writing Quality Check catches the patterns that make prose feel machine-generated. The goal is quality, not cheating.
  18. ### Why human-in-the-loop, not full automation?
  19. Lu et al. (2026, *Nature* 651:914-919) built **The AI Scientist** — the first fully autonomous AI research system to publish a paper through blind peer review at a top-tier ML venue (ICLR 2025 workshop, score 6.33/10 vs workshop average 4.87). Their Limitations section enumerates the failure modes that any fully-autonomous AI research pipeline inherits: implementation bugs, hallucinated results, shortcut reliance, bug-as-insight reframing, methodology fabrication, frame-lock, citation hallucinations.
  20. ARS is built on the premise that **a human researcher augmented by AI avoids these failure modes better than either alone**. Stage 2.5 and Stage 4.5 integrity gates run a 7-mode blocking checklist (see [`academic-pipeline/references/ai_research_failure_modes.md`](academic-pipeline/references/ai_research_failure_modes.md)); the reviewer offers an opt-in calibration mode that measures its own FNR/FPR against a user-supplied gold set.
  21. [**Zhao et al.**](https://arxiv.org/abs/2605.07723) (2026-05) audited 111M references across 2.5M papers on arXiv, bioRxiv, SSRN, and PMC. Their conservative estimate is 146,932 hallucinated citations for 2025 alone, with an observed mid-2024 inflection; for the bioRxiv-to-PMC pairing they report 85.3% preprint-to-published persistence. The paper describes "real citations deployed to support claims the cited references do not actually make" as an open challenge. ARS v3.7.1 added trust-chain frontmatter for source provenance; v3.7.3 added locator infrastructure (three-layer citation anchors) for future claim-level audits and surfaces advisory risk signals at cite time (ARS labels the claim-faithfulness gap internally as "L3"; this is ARS terminology, not the paper's). v3.7.x is motivated by Zhao et al.'s corpus-scale findings; corpus-scale evaluation of ARS itself remains future work.
  22. v3.8 closes the second half of the L3 gap. v3.7.3 made every citation carry a locator anchor; v3.8 adds an opt-in audit pass (`ARS_CLAIM_AUDIT=1`) that fetches the cited source against each anchor and judges whether the claim is actually supported. Five new HIGH-WARN classes (claim-not-supported, negative-constraint-violation, fabricated-reference, anchorless, constraint-violation-uncited) gate-refuse output through the formatter terminal hard gate. A calibration runner ships with a 25-tuple synthetic gold set and FNR<0.15 + FPR<0.10 acceptance thresholds. Its shipped test drives the runner with a stub judge that returns the gold labels, so it checks the tooling, not a live judge; no live-judge calibration result is recorded yet, and the ramp-on plan waits for one (v3.8 spec §5).
  23. [**Ren et al.**](https://arxiv.org/abs/2607.13104) (2026, *Self-Improvements in Modern Agentic Systems: A Survey*) supplies a third, survey-level anchor. Its scientific-discovery synthesis (§7.4) concludes that discovery agents cannot easily verify novelty, correctness, or reproducibility on their own and may exploit weak proxies instead, must manage evidence across heterogeneous tools and literature, and raise governance issues — "scientific writing can also amplify misinformation when the evidence is weak." Its generation-loop chapters (§5.1–§5.2) list human auditing and retained human anchors among the practical safeguards for self-generated evaluation loops, and its historical chapter (§2.2) records the oldest form of the same lesson: the practical success of Lenat's EURISKO depended heavily on the user serving as the external evaluation signal, pruning unproductive heuristic drift — a limitation the survey notes persists in modern agentic systems. ARS cites the survey as design rationale for its human-in-the-loop stance, not as empirical proof that human-in-the-loop pipelines outperform autonomous ones; the survey's actionable deltas for ARS are tracked in #539–#541 and #547–#550.
  24. [**Gartenberg et al.**](https://doi.org/10.1287/orsc.2026.ed.v37.n3) (2026, *Organization Science* 37(3):795-812, "More versus better") supplies a fourth anchor, and the first from the journal side. The *Organization Science* AI Task Force scored every first submission (6,957) and every text-format review (10,389) the journal received between January 2021 and February 2026 with a commercial AI-writing classifier and standard readability indices. Manuscripts scored as heavily AI-written read worse on those indices and were desk-rejected more often; reviews scored as more AI-written leaned toward theory and away from data; and the editors conclude that current AI tools, amplified by publish-or-perish incentives, "appear to be pushing the system toward an equilibrium of more rather than better research." Their §5 contrasts "cognitive surrender" (Shaw & Nave, 2026, as cited there) with human-first use and asks authors to disclose how a manuscript was produced. The evidence is observational, aggregate, and from one journal, and the classifier is a proprietary instrument. ARS cites the editorial as design rationale for recording volume as a non-goal (see `POSITIONING.md`) and for the Collaboration Depth Observer and the claim-strength ladder, not as evidence about ARS output; the actionable deltas are tracked in #829–#833.
  25. [**Wang, Li et al.**](https://arxiv.org/abs/2609.07713) (2026-09, *The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing*, a survey of 230 sources) supplies a fifth anchor, and the first that treats research production and peer review as one coupled system. Its evaluative-authority ladder (§4.1) runs from author-facing feedback through reviewer assistance and official AI reviews to scoring and decision support, with the survey's point that capability at one rung does not justify use at the next; ARS's simulated panel sits on the lowest rung by design (see `POSITIONING.md`). Two of its findings shape the reviewer roadmap. First, as the survey summarizes Dycke & Gurevych (2026, §4.5), 391 edits that break a paper's scientific support relations produced no statistically significant difference in the tested automated reviewers' aspects, sentiment, or scores compared with 540 soundness-neutral controls, while presentation-only rewrites with the science held fixed moved AI-review scores (§5.2); the survey's §9.2 conclusion is that a static evaluation can overstate an AI reviewer's reliability once authors can observe and adapt to it. ARS tracks the corresponding Round-1 paired controls in #871 and the author-identity-cue controls (§7.2) in #872; both are measurements, not new mechanisms. Second, its §9.1 cites Brodeur et al. (2026, *PNAS* 123(22):e2524747123), a randomized study in which 288 researchers in 103 teams reproduced published quantitative social-science results under three conditions: human-only, AI-assisted (ChatGPT as a collaborative tool), and AI-led (ChatGPT with minimal human oversight). Human-only and AI-assisted teams reproduced 94% and 91%, AI-led teams 37%, and the AI-assisted teams detected fewer major coding errors than the human-only teams. In that study, then, AI assistance did not verify better than humans alone and AI-led verification did much worse; ARS reads this as a reason to keep verification human-led at every checkpoint, not as evidence that its own checkpoints or integrity gates are effective. The survey is a synthesis rather than an experiment, its structured search stops at 2026-07-01 and the later targeted update did not rerun every query (§10), its deployment evidence is concentrated in a small number of AI/CS conferences, OpenReview-based settings, and selected journals, and its "arms race" framing is a lens, not a finding; ARS cites it as design rationale, not as evidence about ARS output.
  26. [**King & Worthington**](https://gking.harvard.edu/peerless) (2026-10, *AI Article Reviews Dominate Human Peer Reviews at Their Best: Evidence and Policy Choices*) supplies a sixth anchor, and the first that compares AI and human reviews of the same manuscripts head to head. On 124 manuscripts and 134 paid expert reviews from a pre-submission review service whose authors rated those reviews highly, Claude Opus 4.8 wrote one review per manuscript in each of two conditions, at maximum reasoning effort. A GPT-5.5 judge preferred the AI review in every decided pair, each pair judged in both presentation orders, and three former journal editors preferred it in 26 of 30 blinded judgements. In a replication that used both model families as reviewers and judges, the AI review was preferred in 404 of 416 comparisons (97.1%) by the Opus judge and in 392 of 416 (94.2%) by the GPT judge. Two results bear on ARS's reviewer. In the additional-sources area (alternative data, theory, or literature), the AI review won 62% of decided pairs without web retrieval (n=85) and 100% with it (n=99), and ARS's domain reviewer recommends literature without retrieving or verifying it (#1001). The AI reviews were also not error-free: in the no-tools condition, 5.5% of AI claim assessments were judged contradicted by the manuscript, against 15.9% for the human reviews, and 37.1% of AI reviews had at least one such claim; ARS does not check its panel's claims against the manuscript (#1002). The paper's policy section describes authors iterating with a published AI review prompt and answering it in a letter, close to the use ARS is designed for, and warns that authors who revise for a published prompt may end up optimizing for it, leaving biases unrelated to the quality of the science. Its limits frame how ARS reads it: one review service, one judge model in the main analysis, editors who judged from the reviews alone, no measure of whether revised papers improved, and results that, in the authors' words, "do not speak to" how editors should make publication decisions. That last boundary matches where `POSITIONING.md` places ARS's panel. This paper and the Dycke & Gurevych result above address different questions: review preference and factual grounding here, sensitivity to changes in a manuscript's soundness there, so neither result answers the other. ARS cites the paper as design rationale, not as evidence about ARS output.
  27. v3.3 was inspired by [**PaperOrchestra**](https://arxiv.org/abs/2604.05018) (Song, Song, Pfister & Yoon, 2026, Google): Semantic Scholar API verification, anti-leakage protocol, VLM figure verification, and revision-trajectory tracking. ARS now implements that last idea through categorical, evidence-anchored criterion trajectories rather than score deltas.
  28. ---
  29. ## Architecture & pipeline
  30. **👉 [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md)** — the full pipeline view: flow diagram, stage-by-stage matrix, data-access flow, skill dependency graph, quality gates, and mode list.
  31. The architecture doc supersedes the sprawling pipeline description that used to live here. Everything about *what runs in which stage* now lives in one place.
  32. ## Quick install
  33. **Prerequisites**
  34. - [Claude Code](https://docs.claude.com/en/docs/claude-code/setup) (latest; plugin packaging requires recent versions)
  35. - `ANTHROPIC_API_KEY` exported, or set on first `claude` run
  36. - *Optional:* Pandoc for DOCX, tectonic + Source Han Serif TC for APA 7.0 PDF (Markdown output works without either)
  37. - *Optional (real Python):* needed only for the write-scope guard and a few opt-in commands; the core skills are prompt-driven. Details, including the Windows notes on Git Bash and the Microsoft Store Python stub, are in [docs/SETUP.md § Python (optional)](docs/SETUP.md#python-optional).
  38. > **Which controls are active in *your* install channel?** Availability varies by install channel. See the per-channel map: [docs/CONTROL_AVAILABILITY.md](docs/CONTROL_AVAILABILITY.md).
  39. **Plugin install (v3.7.0+, recommended):**
  40. ```text
  41. /plugin marketplace add Imbad0202/academic-research-skills
  42. /plugin install academic-research-skills
  43. ```
  44. **Verify it works:** run `/ars-plan` and describe a paper you're working on — ARS will start a Socratic dialogue to map out chapter structure. For a single-shot test instead, try `/ars-lit-review "your topic"`.
  45. **👉 [docs/SETUP.md](docs/SETUP.md)** — full guide: install Claude Code, set up API keys, optional Pandoc/tectonic for DOCX/PDF, cross-model verification (`ARS_CROSS_MODEL`), and six installation methods (Plugin for Claude Code / claude.ai / Claude Desktop, project skills, global skills, claude.ai Project, repo-cloned, Claude Science import).
  46. **👉 [docs/DATA_FLOWS.md](docs/DATA_FLOWS.md)** — what leaves your machine (bibliographic resolvers, optional consent-gated cross-model calls, the plugin update check), what is cached locally, for how long, and how to turn each path off.
  47. **👉 [docs/RISK_REGISTER.md](docs/RISK_REGISTER.md)** — the standing risks the suite knows about, which existing controls address each one, the evidence status behind those controls, and what remains open.
  48. **Using Claude Science?** The five skills import directly: **Skills → Import from GitHub**, paste `https://github.com/Imbad0202/academic-research-skills`, **Preview**, then **Import** (requires v3.14.0+ of this repo — the importer reads the explicit skill paths in the marketplace manifest). Imports are point-in-time snapshots: re-import after ARS updates. Imported skills carry the ARS methodology (research / writing / review protocols); Claude Code-specific machinery — slash commands, hooks, subagent orchestration — does not transfer. See [docs/SETUP.md](docs/SETUP.md) Method 5 for details.
  49. **Using Pi?** Install the in-tree, community-maintained wrapper with `pi install git:github.com/Imbad0202/academic-research-skills`. It keeps the original ARS content authoritative and documents Pi-specific orchestration and hook limitations. See [`pi/README.md`](pi/README.md).
  50. **Using Codex CLI?** Install the sibling distribution instead: [`Imbad0202/academic-research-skills-codex`](https://github.com/Imbad0202/academic-research-skills-codex) — same workflow content, Codex-native packaging as a single `$academic-research-suite` skill with `ars-*` aliases.
  51. **Third-party platforms and integrations** that wrap or host ARS are listed in [THIRD_PARTY.md](THIRD_PARTY.md) — community-submitted and not reviewed or endorsed by the maintainer.
  52. **Governance:** who decides, what cross-model review does and does not provide, and the project's end-of-life posture are stated in [GOVERNANCE.md](GOVERNANCE.md); security reporting and triage in [SECURITY.md](SECURITY.md).
  53. ## Performance & cost
  54. **👉 [docs/PERFORMANCE.md](docs/PERFORMANCE.md)** — per-mode token budgets, full-pipeline estimate (about US$3–7 for a 15k-word paper at 2026-09 list prices, before cache discounts), and recommended Claude Code settings (Auto mode; Agent Team optional).
  55. ## Guides & articles
  56. - [Academic Writing Shouldn't Be a Solo Act](https://open.substack.com/pub/edwardwu223235/p/academic-writing-shouldnt-be-a-solo?r=4dczl&utm_medium=ios) — full pipeline walkthrough (English)
  57. - [學術寫作不該是一個人的事:一套開源 AI 協作工具如何改變研究者的工作流](https://open.substack.com/pub/edwardwu223235/p/ai?r=4dczl&utm_medium=ios) — 完整使用指南(繁體中文)
  58. ---
  59. ## Features at a glance
  60. - **Deep Research** — 13-agent research team with Socratic guided mode, PRISMA systematic review, intent detection, dialogue health monitoring, optional cross-model DA, Semantic Scholar API verification.
  61. - **Academic Paper** — 12-agent paper writing with Style Calibration, Writing Quality Check, LaTeX hardening, visualization, revision coaching, citation conversion, anti-leakage protocol, and VLM figure verification.
  62. - **Academic Paper Reviewer** — 7-agent multi-perspective peer review with criterion-bound, evidence-anchored narrative judgements (Journal-Fit Reviewer + 3 dynamic reviewers + Devil's Advocate), concession threshold protocol, attack intensity preservation, optional cross-model DA critique / calibration, R&R traceability matrix, read-only constraint. Current live reviews remain `NOT_CALIBRATED`; full calibration produces a bounded candidate profile, while live-profile application is not yet wired.
  63. - **Academic Pipeline** — 10-stage pipeline orchestrator with adaptive checkpoints, claim verification, Material Passport, optional `repro_lock`, optional cross-model integrity verification, mid-conversation reinforcement, and narrative criterion-by-criterion regression checks (the typed trajectory carrier is deferred).
  64. - **SR-Screener** — protocol-driven study screening for systematic, scoping and rapid reviews: two blinded AI reviewers plus a third-reviewer adjudicator, ordered exclusion codes, no silent defaults, resumable batch runs, QC (seed studies, near-miss rechecks, kappa and PABAK), PRISMA 2020 counts, EndNote/Zotero RIS groups, and a `literature_corpus[]` handoff to `academic-paper`. AI decisions are decision support; the review team verifies them.
  65. - **Data Access Level Metadata** (v3.3.2+) — every skill declares `data_access_level` (`raw` / `redacted` / `verified_only`); enforced by `scripts/check_data_access_level.py`. Pattern adapted from Anthropic's automated-w2s-researcher (2026). See [`shared/ground_truth_isolation_pattern.md`](shared/ground_truth_isolation_pattern.md).
  66. - **Task Type Annotation** (v3.3.2+) — every skill declares `task_type` (`open-ended` or `outcome-gradable`). All current ARS skills are `open-ended`.
  67. - **Benchmark Report Schema** (v3.3.5+) — JSON Schema + lint for honest benchmark comparisons. See [`shared/benchmark_report_pattern.md`](shared/benchmark_report_pattern.md).
  68. - **Artifact Reproducibility Lockfile** (v3.3.5+) — optional `repro_lock` sub-block on Material Passport. **Configuration documentation, not replay guarantee** — LLM outputs are not byte-reproducible. See [`shared/artifact_reproducibility_pattern.md`](shared/artifact_reproducibility_pattern.md).
  69. - **Model Tiering** (#517, v3.16+) — optional `ARS_MODEL_TIERING` switch with two directions: `economy` (execution-type agents dispatch one tier below the session model, floor Opus-class) and `quality-boost` (judgment-type agents at integrity gates and final review step up to the frontier tier). Default unset = byte-equivalent to pre-#517 behavior. See [`shared/model_tiering.md`](shared/model_tiering.md).
  70. - **Canonical Cross-Model Handoff Envelope** (#527, v3.17+) — the owner→dispatcher→owner blind-checkpoint transport path (#523) now has a machine-stable `[CROSS-MODEL-HANDOFF v1]` envelope with a normative Python grammar (`scripts/cross_model_handoff.py`) instead of prose-only enforcement, pinning agreement/divergence/malformed-result routing across all three checkpoint owners. See [`shared/cross_model_verification.md`](shared/cross_model_verification.md) §"Cross-model handoff envelope".
  71. - **Experiment Provenance Intake** (#260) — optional `experiment_provenance[]` on the Material Passport records experiments the scholar ran **externally** (ARS never runs experiments), and manuscript claims join to them via `claim_intent_manifest.planned_experiment_ids[]`. The integrity gate (Stage 2.5/4.5) audits each experiment-backed claim against declared provenance — `ALIGNED` / `OVERSTATED` / `NOT_SUPPORTED_BY_PROVENANCE` / `PROVENANCE_INSUFFICIENT` — **without judging whether the experiment itself was correct**. A fail-closed `experiment_intake_declaration` makes "did you run experiments?" an explicit decision the scholar answers after Stage 1, or on entry when a run starts later (even literature-only runs declare `no_experiments_declared`). See [`shared/handoff_schemas.md`](shared/handoff_schemas.md) §"Experiment Provenance Intake (#260)".
  72. **Integrity and verification boundary:** ARS checks the manuscript and the reported process—including citation existence, claim–source alignment, reported methodology, declared experiment–result alignment, figure/table fidelity, and reporting/process/package conformance. Some checks are sampled or LLM-mediated. ARS does **not** establish that procedures were actually performed, raw data are authentic, or results reproduce; a consistently reported fabrication can pass these checks. See [POSITIONING.md § Integrity checks and the empirical-work boundary](POSITIONING.md#integrity-checks-and-the-empirical-work-boundary).
  73. ---
  74. ## Showcase: real pipeline output
  75. See the complete artifacts from a real pipeline run, including peer review reports, integrity verification reports, and the final paper:
  76. > **A March 2026 record, not current performance.** This run (2026-03-07 to 03-08) used academic-pipeline v2.3, before ARS v3.3 added the Semantic Scholar check and v3.11 added the deterministic four-index citation gate. Its numbers describe that version; the current gates have not been measured on this paper. The byline names Claude (Anthropic) as author because the researcher asked for that during the experiment. The paper is not an Anthropic publication, and ARS's positioning is that the tool does not replace the researcher and does not claim authorship ([POSITIONING.md](POSITIONING.md#what-this-is-not)).
  77. **[Browse all pipeline artifacts →](examples/showcase/)**
  78. | Artifact | Description |
  79. |---|---|
  80. | [Final Paper (EN)](examples/showcase/full_paper_apa7.pdf) | APA 7.0 formatted, LaTeX-compiled |
  81. | [Final Paper (ZH)](examples/showcase/full_paper_zh_apa7.pdf) | Chinese version, APA 7.0 |
  82. | [Integrity Report — Pre-Review](examples/showcase/integrity_report_stage2.5.pdf) | Stage 2.5: flagged 15 problem references (8 with bibliographic errors, 6–8 likely fabricated) + 3 statistical errors |
  83. | [Integrity Report — Final](examples/showcase/integrity_report_stage4.5.pdf) | Stage 4.5: zero regressions confirmed |
  84. | [Peer Review Round 1](examples/showcase/stage3_review_report.pdf) | Journal-Fit Reviewer + 3 Reviewers + Devil's Advocate |
  85. | [Re-Review](examples/showcase/stage3prime_rereview_report.pdf) | Verification after revisions |
  86. | [Peer Review Round 2](examples/showcase/stage3_review_report_r2.pdf) | Follow-up review |
  87. | [Response to Reviewers](examples/showcase/response_to_reviewers_r2.pdf) | Point-by-point author response |
  88. | [Post-Publication Audit Report](examples/showcase/post_publication_audit_2026-03-09.pdf) | Full-reference audit run separately with Claude Code + WebSearch: 21 of the 68 final references still had problems after 3 rounds of integrity checks |
  89. ---
  90. ## Companion: Experiment Agent
  91. If your research involves running experiments (code or human studies) before writing, the [Experiment Agent](https://github.com/Imbad0202/experiment-agent) skill fills the gap between ARS Stage 1 (RESEARCH) and Stage 2 (WRITE).
  92. ```
  93. ARS Stage 1 RESEARCH → RQ Brief + Methodology Blueprint
  94. ↓
  95. experiment-agent → run/manage experiments → validate results
  96. ↓
  97. ARS Stage 2 WRITE → write paper with verified experiment results
  98. ```
  99. **What it does**: executes code experiments (Python, R, etc.) with real-time monitoring, manages human study protocols with IRB ethics checklist, interprets statistics with 11-type fallacy detection, and verifies reproducibility.
  100. **How to use together**: pause the ARS pipeline after Stage 1, run experiments in a separate experiment-agent session, then bring the results (with Material Passport) back to ARS Stage 2. ARS requires zero modification. See the [experiment-agent README](https://github.com/Imbad0202/experiment-agent) for setup instructions.
  101. **Stage 1 intake declaration (#260, #925)**: at the checkpoint after Stage 1, or on entry when a run starts after Stage 1, ARS asks you whether the paper reports experiments or data analyses you ran yourself, and records your answer, in your words, in a fail-closed `experiment_intake_declaration` on the Material Passport. ARS does not infer the answer from the manuscript. If you ran experiments externally, the scholar enters one `experiment_provenance[]` entry per experiment (`experiment_id`, nested `repro_lock`, `planned_vs_executed[]`, `negative_results[]`, `known_limitations[]`) and the declaration is set to `experiments_declared`; if not, it is set to `no_experiments_declared`. The declaration is **required on every post-#260 passport** — a run that touches no experiments still declares `no_experiments_declared`, so the integrity gate can never be silently bypassed by a forgotten provenance block. The `experiment_id`s are frozen at this intake point, which closes before the first Stage 2 writer is dispatched (or before the first integrity gate when no Stage 2 lies ahead), so you can pause after Stage 1, run the experiments, and record them when you return; the writers later reference them via `planned_experiment_ids[]`.
  102. **Teaching-side companion**: [Teaching Skills](https://github.com/YujxZJCN/teaching-skills) applies the ARS architecture (skill ensembles, shared contracts, staged gates, a Course Passport) to the teaching side of academic life — course design → lessons → assessment → delivery → reflection; its `sotl` mode hands classroom-inquiry projects off to ARS deep-research / academic-paper for the publication phase.
  103. ---
  104. ## Usage
  105. ### Quick Start
  106. ```
  107. # Start a full research pipeline
  108. You: "I want to write a research paper on AI's impact on higher education QA"
  109. # Start with Socratic guidance
  110. You: "Guide my research on AI in educational evaluation"
  111. # Write a paper with guided planning
  112. You: "Guide me through writing a paper on demographic decline"
  113. # Review an existing paper
  114. You: "Review this paper" (then provide the paper)
  115. # Check pipeline status
  116. You: "status"
  117. ```
  118. ### Individual Skills
  119. #### Deep Research (8 modes)
  120. ```
  121. "Research the impact of AI on higher education" → full mode
  122. "Give me a quick brief on X" → quick mode
  123. "Do a systematic review on X with PRISMA" → systematic-review mode
  124. "Guide my research on X" → socratic mode (guided)
  125. "Fact-check these claims" → fact-check mode
  126. "Do a literature review on X" → lit-review mode
  127. "Compare these papers in WHY/HOW/WHAT format" → three-way-scan mode
  128. "Review this paper's research quality" → review mode
  129. ```
  130. #### Academic Paper (11 modes)
  131. ```
  132. "Write a paper on X" → full mode
  133. "Guide me through writing a paper" → plan mode (guided)
  134. "Build a paper outline" → outline-only mode
  135. "I have a draft, here are reviewer comments" → revision mode
  136. "Parse these reviewer comments into a roadmap" → revision-coach mode
  137. "Write an abstract for this paper" → abstract-only mode
  138. "Turn this into a literature review paper" → lit-review mode
  139. "Convert to LaTeX" / "Convert citations to IEEE" → format-convert mode
  140. "Check citations" → citation-check mode
  141. "Generate an AI disclosure statement for NeurIPS" → disclosure mode
  142. "Audit my rebuttal draft against the reviews" → rebuttal-audit mode
  143. ```
  144. #### Academic Paper Reviewer (6 modes)
  145. ```
  146. "Review this paper" → full mode (Journal-Fit Reviewer + R1/R2/R3 + Devil's Advocate)
  147. "Quick assessment of this paper" → quick mode
  148. "Guide me to improve this paper" → guided mode
  149. "Check the methodology" → methodology-focus mode
  150. "Verify the revisions" → re-review mode
  151. "Calibrate this reviewer against my gold set" → calibration mode
  152. ```
  153. #### Academic Pipeline (Orchestrator)
  154. ```
  155. "I want to write a complete research paper" → full pipeline from Stage 1
  156. "I already have a paper, review it" → mid-entry at Stage 2.5 (integrity first)
  157. "I received reviewer comments" → mid-entry at Stage 4
  158. ```
  159. > Pipeline ends with **Stage 6: Process Summary** — auto-generates a paper creation process record with 6-dimension Collaboration Quality Evaluation (1–100 scoring).
  160. #### SR-Screener (8 modes)
  161. ```
  162. "Turn my proposal into a screening protocol" → protocol mode
  163. "Is this abstract eligible for my review?" → quick mode (single-reviewer triage)
  164. "Pilot the screening with my seed studies" → pilot mode
  165. "Screen these database exports" → ta-screen mode
  166. "Screen the full texts of the advanced records" → ft-screen mode
  167. "Adjudicate the conflicts in my Rayyan export" → adjudicate mode
  168. "Double-check my exclusions" → audit mode
  169. "Give me the PRISMA numbers for the screening" → report mode
  170. ```
  171. ### Supported Languages
  172. - **Traditional Chinese** (繁體中文) — default when user writes in Chinese
  173. - **English** — default when user writes in English
  174. - Bilingual abstracts (Chinese + English) for academic papers
  175. > **Using a different language?** Socratic mode (deep-research) and Plan mode (academic-paper) use **intent-based activation** — they detect the meaning of your request, not specific keywords. This means they work in **any language** without modification.
  176. >
  177. > However, the general `Trigger Keywords` section (which determines whether the skill is activated at all) still lists English and Traditional Chinese keywords. If you find the skill isn't activating reliably in your language, you can add your language's keywords to the `### Trigger Keywords` section in each `SKILL.md` file to improve matching confidence.
  178. ### Supported Citation Formats
  179. - APA 7.0 (default, including Chinese citation rules)
  180. - Chicago (Notes & Author-Date)
  181. - MLA
  182. - IEEE
  183. - Vancouver
  184. ### Supported Paper Structures
  185. - IMRaD (empirical research)
  186. - Thematic Literature Review
  187. - Theoretical Analysis
  188. - Case Study
  189. - Policy Brief
  190. - Conference Paper
  191. ---
  192. ## Skill Details
  193. Per-agent responsibilities and per-stage artifacts now live in [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md). Version numbers are anchored here so release metadata stays in one place.
  194. ### Deep Research (v2.12.1)
  195. 13-agent research team. Modes: full, quick, review, lit-review, three-way-scan, fact-check, socratic, systematic-review. Full agent roster and artifacts: see ARCHITECTURE.md §3.
  196. ### Academic Paper (v3.3.1)
  197. 12-agent paper writing pipeline. Modes: full, plan, outline-only, revision, revision-coach, abstract-only, lit-review, format-convert, citation-check, disclosure, rebuttal-audit. Output: MD + DOCX (via Pandoc when available) + LaTeX (APA 7.0 `apa7` class / IEEE / Chicago) → PDF via tectonic. Full agent roster and per-phase responsibilities: see ARCHITECTURE.md §3.
  198. ### Academic Paper Reviewer (v1.11.1)
  199. 7-agent multi-perspective review with **criterion-bound narrative judgements**. Modes: full, re-review, quick, methodology-focus, guided, calibration. Current live reviews and Schema 6 packages remain `NOT_CALIBRATED`; full calibration can produce a bounded candidate profile, but application to a live review is not wired. No numerical total is mapped to Accept, Minor Revision, Major Revision, or Reject. First-round review panel vs. contract-governed re-review dispatch boundary: see ARCHITECTURE.md §3 Stage 3 / Stage 3'.
  200. ### Academic Pipeline (v3.24.3)
  201. 10-stage orchestrator with integrity verification, two-stage review, Socratic coaching, and collaboration evaluation. Pipeline rules (protocol the agents follow, not runtime guarantees): every stage requires user confirmation checkpoint; integrity verification (Stage 2.5 + 4.5) is MANDATORY with no unrecorded bypass (every override requires user reasoning recorded for Stage 6); R&R Traceability Matrix (Schema 11) maps each reviewer concern to the author's revision claim and records whether the re-review verified it. v3.4 added the Compliance Agent (PRISMA-trAIce + RAISE) at Stage 2.5 / 4.5. v3.5 adds the **Collaboration Depth Observer** (`collaboration_depth_agent`, advisory only — never blocks) at every FULL/SLIM checkpoint and at pipeline completion. MANDATORY integrity gates (2.5 / 4.5) explicitly skip the observer so compliance checks are not diluted. Based on Wang & Zhang (2026), IJETHE 23:11. Stage-by-stage matrix with agents, artifacts, and gates: see ARCHITECTURE.md §3.
  202. ### SR-Screener (v1.0.0)
  203. 4-agent study screening between `deep-research` (question, protocol, search) and `academic-paper` (writing the review). Modes: protocol, quick, pilot, ta-screen, ft-screen, adjudicate, audit, report. Two blinded reviewer subagents (Read and Grep only) screen every record against the user-confirmed protocol, a third reviewer adjudicates advance-vs-exclude conflicts, and standard-library Python scripts parse RIS / PubMed .nbib / Web of Science / CSV exports, de-duplicate, batch, merge, and build the screening log, RIS groups, PRISMA 2020 counts, a methods draft with `[TO COMPLETE]` slots, and a `literature_corpus[]` file. Rules the agents follow (not runtime guarantees): no record is screened before the user confirms the protocol, no failed call becomes a default "exclude", and the review team verifies the decisions before the numbers are reported. See [`sr-screener/SKILL.md`](sr-screener/SKILL.md).
  204. ---
  205. ## v3.0 Optimizations: What We Discovered About AI's Structural Limits
  206. ### What happened
  207. While using ARS to write a reflection article about AI in higher education, I ran into three structural problems that no amount of prompt engineering could fix:
  208. 1. **Frame-lock**: I asked the AI to run a devil's advocate debate against its own thesis. It did — four rounds, each more refined than the last. But every round stayed inside the frame I'd set. The DA attacked arguments, never premises. It never asked "are we even discussing the right question?" This is the same pattern that caused the 31% citation error rate in v2.7's stress test: the verifying AI and the generating AI share the same cognitive frame.
  209. 2. **Sycophancy under pushback**: Every time I challenged the DA's attacks, it conceded too quickly. It retracted findings faster than it launched them. The model's training rewards conversational harmony — so "the user pushed back" was treated as evidence that the attack was wrong, when often it just meant the user was persistent.
  210. 3. **Intent misdetection**: The Socratic Mentor kept trying to converge and produce deliverables ("Want me to write this up?") when I was still exploring. It couldn't distinguish "the user wants a deep philosophical discussion" from "the user wants an RQ brief." Both look like engagement, but they need opposite AI behaviors.
  211. ### What we changed (v3.0)
  212. **Devil's Advocate — Concession Threshold Protocol** (`deep-research` + `academic-paper-reviewer`)
  213. - DA must now score every rebuttal on a 1-5 scale before responding
  214. - Concession only allowed at score ≥4 (rebuttal directly addresses core attack with evidence)
  215. - Score ≤3: hold position and restate the original attack
  216. - Anti-sycophancy rules: no consecutive concessions, concession rate tracking, frame-lock detection after each checkpoint
  217. **Socratic Mentor — Intent Detection Layer** (`deep-research`)
  218. - Classifies user intent as exploratory vs. goal-oriented at dialogue start and every 3 turns
  219. - Exploratory mode: disables auto-convergence, raises max rounds to 60, prohibits "want me to summarize?" prompts
  220. - Goal-oriented mode: standard convergence behavior
  221. - Anti-premature-closure rules: in exploratory mode, the user decides when to stop
  222. **Socratic Mentor — Dialogue Health Indicator** (`deep-research`)
  223. - Silent self-assessment every 5 turns on three dimensions: persistent agreement, conflict avoidance, premature convergence
  224. - Auto-injects challenging questions when agreement pattern detected
  225. - Invisible to user (to prevent gaming), but log available for post-session review
  226. ### Why this matters
  227. These optimizations don't solve AI's structural limits — they make the limits visible and manageable. The DA will still eventually concede if pushed hard enough. The Socratic Mentor will still have some convergence bias. But now there are explicit checkpoints that slow down the sycophancy, force the DA to justify concessions, and prevent the Mentor from wrapping up before the user is ready.
  228. The deeper lesson: AI literacy isn't about learning to use AI as a tool, following ethics rules, or fearing AI risks. It's about engaging AI deeply enough to discover its structural limits yourself — and your own thinking limits in the process.
  229. ---
  230. ## License
  231. This work is licensed under [CC-BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/).
  232. **You are free to:**
  233. - Share — copy and redistribute the material
  234. - Adapt — remix, transform, and build upon the material
  235. **Under the following terms:**
  236. - **Attribution** — You must give appropriate credit
  237. - **NonCommercial** — You may not use the material for commercial purposes
  238. **Attribution format:**
  239. ```
  240. Based on Academic Research Skills by Cheng-I Wu
  241. https://github.com/Imbad0202/academic-research-skills
  242. ```
  243. ---
  244. ## Contributors
  245. **Cheng-I Wu** (吳政宜) — Author and maintainer
  246. **[aspi6246](https://github.com/aspi6246)** — Contributor. The v3.1 optimization was inspired by patterns from [Claude-Code-Skills-for-Academics](https://github.com/aspi6246/Claude-Code-Skills-for-Academics): read-only constraint pattern, anti-pattern codification as first-class design, cognitive framework approach (teaching "how to think" not just procedures), and lean skill size philosophy.
  247. **[mchesbro1](https://github.com/mchesbro1)** — Contributor. Originally proposed and drafted the IS Basket of 8 journals for `academic-paper-reviewer/references/top_journals_by_field.md` ([Issue #5](https://github.com/Imbad0202/academic-research-skills/issues/5)).
  248. **[cloudenochcsis](https://github.com/cloudenochcsis)** — Contributor. Extended the IS section from the *Basket of 8* to the full *Senior Scholars' Basket of 11* — adding *Decision Support Systems*, *Information & Management*, and *Information and Organization* ([Issue #7](https://github.com/Imbad0202/academic-research-skills/issues/7), [PR #8](https://github.com/Imbad0202/academic-research-skills/pull/8)). Sourced from the [AIS Senior Scholars' List of Premier Journals](https://aisnet.org/research/seniorscholarsbasket/).
  249. **[eltociear](https://github.com/eltociear)** (Ikko Eltociear Ashimine) — Contributor. Translated the Japanese README ([`README.ja-JP.md`](README.ja-JP.md)) ([PR #161](https://github.com/Imbad0202/academic-research-skills/pull/161)).
  250. **[xpfo-go](https://github.com/xpfo-go)** (xpfo) — Contributor. Translated the Simplified Chinese README ([`README.zh-CN.md`](README.zh-CN.md)) ([PR #181](https://github.com/Imbad0202/academic-research-skills/pull/181)).
  251. **[devCharlotte](https://github.com/devCharlotte)** — Contributor. Translated the Korean README ([`README.ko-KR.md`](README.ko-KR.md)) ([PR #469](https://github.com/Imbad0202/academic-research-skills/pull/469)).
  252. **[Yaobin29](https://github.com/Yaobin29)** — Contributor. Proposed reviewer-response tooling in [PR #433](https://github.com/Imbad0202/academic-research-skills/pull/433); the `deep-research three-way-scan` mode and the `academic-paper rebuttal-audit` mode (rescued from the PR's `audit` concept) were integrated from that contribution in v3.12.1.
  253. **[ktao732084-arch](https://github.com/ktao732084-arch)** — Contributor. Expanded the `academic-paper` disclosure system with nine medical-publishing policy targets, target-specific required-fact intake, and fail-closed standalone rendering ([Issue #596](https://github.com/Imbad0202/academic-research-skills/issues/596), [PR #599](https://github.com/Imbad0202/academic-research-skills/pull/599)); expanded the EQUATOR clinical-reporting reference with condensed CARE, STARD and TRIPOD+AI guidance plus a fail-closed study-design routing sequence ([Issue #594](https://github.com/Imbad0202/academic-research-skills/issues/594), [PR #601](https://github.com/Imbad0202/academic-research-skills/pull/601)); and designed and contributed the standalone Chinese-literature resolver, API protocol, and synthetic transport-fixture suite ([Issue #595](https://github.com/Imbad0202/academic-research-skills/issues/595), [PR #600](https://github.com/Imbad0202/academic-research-skills/pull/600)).
  254. **[didacrios](https://github.com/didacrios)** — Contributor. Translated the Spanish README ([`README.es-ES.md`](README.es-ES.md)).
  255. **[laqueiroz](https://github.com/laqueiroz)** (Laís Queiróz) — Contributor. Translated the Brazilian Portuguese README ([`README.pt-BR.md`](README.pt-BR.md)).
  256. ---
  257. ## Changelog
  258. Only the three most recent releases are summarized here. The full release history, including the one-paragraph summaries that used to live on this page, is in [CHANGELOG.md](CHANGELOG.md).
  259. ### v3.24.3 (2026-11-14) — An author letter in the user's language, a field analyst that names no unconfirmed journal, and Phase 1 checks that count Chinese and Japanese text
  260. > **Reviewer, citation, and adapter repairs and one new reviewer output; no new skill or mode, and the prompt-level changes are unmeasured:** A `full` review now also writes the author a letter in the user's language beside the Editorial Decision Package. `scripts/check_author_letter.py` fails a quotation in the supported quotation marks that it cannot find in the manuscript, a machine line or internal id in the letter, and an item map that does not list each roadmap row once (#1078). The field analyst lists what it read before the Reviewer Configuration Cards (#1075), and the cards give checks with manuscript locations rather than conclusions (#1076); it no longer recommends journals or other venues and names a target only when the author has confirmed one (#1080). The Phase 1 checks count a Han or kana letter as 1 point and a word as 2, so a short Chinese or Japanese trigger is measured, and the manuscript-leak check finds a 24-point Chinese or Japanese passage copied from the manuscript unless the passage also occurs in a metadata-envelope value or the contract (#1077). Korean keeps the whitespace count. For text with no Han or kana letter after NFKC, both checks now run NFKC first, and the trigger count no longer counts a lone mark such as `—` as a word. The leak check has synthetic tests only; no rate on real reviews is measured. The reviewer claim check applies NFC before it matches a quotation (#1074). `citation_compliance_agent` edits the paper draft only in `full` mode, where its Corrected Draft now goes to Phase 6, and returns proposals in `revision` mode (#1068); its Phase Boundary block names both of its outputs (#1067), and standalone citation-check returns a report and rewrites the user's text only on request (#1062). The Zotero and Obsidian adapters send an item or note that fails the schema or a type check to the rejection log, instead of writing it to the passport or stopping the run; a Zotero `date` or `issued` that holds a number, such as `"date": 2024`, is now rejected, and all three adapters, `folder_scan.py` included, now need `jsonschema`. No real Zotero export or Obsidian vault was run (#1055, #1056, #1058, #1059). Claude Fable 5.2 is a supported session model; it has a system-card audit and a routing smoke test, but no full pipeline run or reviewer calibration (#1063).
  261. ### v3.24.2 (2026-11-06) — An honest null for experiment locks, repro_lock alignment, and a corrected sr-screener methods sentence
  262. > **Repairs and docs; no new skill or mode, and the prompt-level changes are unmeasured:** An `experiment_provenance[]` entry can now say it has no honest lock values, with `repro_lock: null` and a `repro_lock_reason` (#1049). A survey or an analysis with no LLM could pass before only with placeholder values. Earlier ARS releases reject this form, so a passport that uses it needs this release. `check_repro_lock.py` now fails a required value that breaks its field's type or value rule, such as a null model id; `cross_model.secondary_model_id` may still be null. `planned_vs_executed[].value` accepts only a number or a string, so some passports that passed before now fail (#1050). The `sr-screener` methods text no longer says the reviewers could read only the record file: the tool list removes web and write access, and reading only the given file is an instruction (#1039). SETUP records two checks in which an uploaded skill dispatched a built-in sub-agent in a conversation after a retry; multi-agent stages stay untested (#1040).
  263. ### v3.24.1 (2026-11-02) — Plugin installs from a claude.ai account marketplace, reviewer card confirmation, and a Brazilian Portuguese README
  264. > **Install repairs for claude.ai and Claude Desktop; no new skill or mode:** ARS now installs from a claude.ai account marketplace. Before this release, that install loaded none of the five core skills (#1035), and claude.ai left out the four plugin agents because their names had underscores (#1037). On Claude Desktop, a skill and `/ars-lit-review` ran in plain chat, a project session dispatched the `synthesis-agent` plugin agent, and the SessionStart announce appeared in folder work. The write-scope guard, the tools allowlist, and a full pipeline run are untested on claude.ai and Claude Desktop. The reviewer now waits for the user to confirm the Reviewer Configuration Cards (#1030), and the README has a Brazilian Portuguese translation (#1032).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.