Skip to content
Back to search

agent-research-skills

Skills for Claude Code — deep-research: systematic academic literature review

Safety scan

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

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/lingzhi227-agent-research-skills/badge.svg)](/listings/lingzhi227-agent-research-skills)

HTML

<a href="/listings/lingzhi227-agent-research-skills"><img src="/api/listings/lingzhi227-agent-research-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

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

One-line install

npx skills add lingzhi227/agent-research-skills -g -a claude-code

> Use the `-g` (global) flag. Scripts use `~/.claude/skills/` paths that require global installation.

Post-install setup

git clone https://github.com/lingzhi227/agent-research-skills.git /tmp/agent-research-skills
/tmp/agent-research-skills/install.sh
rm -rf /tmp/agent-research-skills

This installs slash commands, checks Python dependencies, and verifies script syntax.

Optional dependencies

| Package | Required by | Install | |---------|------------|---------| | Python 3 | All scripts | `brew install python3` | | PyMuPDF | `self-review`, `deep-research` (PDF parsing) | `pip install PyMuPDF` | | numpy + scipy | `data-analysis` (statistical tests) | `pip install numpy scipy` |

Optional configuration

1. **Semantic Scholar API key** (higher rate limits for literature search): - Get one at https://www.semanticscholar.org/product/api#api-key - Save in `~/keys.md`: `S2_API_Key: your-key-here`

2. **Output directory**: Deep research outputs go to `~/deep-research-output/` by default.

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.

README.md · README · 183 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # agent-research-skills
  2. 31 skills for [Claude Code](https://claude.ai/code) covering the full academic research paper lifecycle — from literature search to slide generation — plus GitHub repository analysis for research topics.
  3. Extracted from 17 GitHub repos studying LLM-agent-driven research automation. See [SKILLS_DESIGN.md](/Users/lingzhi/Code/research-engine/SKILLS_DESIGN.md) for the original design specifications.
  4. ## Installation
  5. ### One-line install
  6. ```bash
  7. npx skills add lingzhi227/agent-research-skills -g -a claude-code
  8. ```
  9. > Use the `-g` (global) flag. Scripts use `~/.claude/skills/` paths that require global installation.
  10. ### Post-install setup
  11. ```bash
  12. git clone https://github.com/lingzhi227/agent-research-skills.git /tmp/agent-research-skills
  13. /tmp/agent-research-skills/install.sh
  14. rm -rf /tmp/agent-research-skills
  15. ```
  16. This installs slash commands, checks Python dependencies, and verifies script syntax.
  17. ### Optional dependencies
  18. | Package | Required by | Install |
  19. |---------|------------|---------|
  20. | Python 3 | All scripts | `brew install python3` |
  21. | PyMuPDF | `self-review`, `deep-research` (PDF parsing) | `pip install PyMuPDF` |
  22. | numpy + scipy | `data-analysis` (statistical tests) | `pip install numpy scipy` |
  23. ### Optional configuration
  24. 1. **Semantic Scholar API key** (higher rate limits for literature search):
  25. - Get one at https://www.semanticscholar.org/product/api#api-key
  26. - Save in `~/keys.md`: `S2_API_Key: your-key-here`
  27. 2. **Output directory**: Deep research outputs go to `~/deep-research-output/` by default.
  28. ## Available Skills (31)
  29. ### Phase 0: Research Discovery & Planning
  30. | Skill | Description | Scripts |
  31. |-------|-------------|---------|
  32. | **[github-research](skills/github-research/)** | 6-phase GitHub repo discovery, analysis, and integration planning for research topics | 13 scripts: search, clone, analyze structure/deps/impls, compare, compile report |
  33. | **[deep-research](skills/deep-research/)** | 6-phase systematic literature survey (frontier → survey → deep dive → code → synthesis → report) | 7 scripts: search APIs, PDF extraction, paper DB, BibTeX, report compilation |
  34. | **[literature-search](skills/literature-search/)** | Multi-source academic search (Semantic Scholar, arXiv, OpenAlex, CrossRef) with ranking | 4 scripts: `search_crossref.py`, `download_arxiv_source.py`, `search_openalex.py` + shared |
  35. | **[literature-review](skills/literature-review/)** | Multi-perspective dialogue simulation with expert personas for grounded literature review | Shares search scripts |
  36. | **[idea-generation](skills/idea-generation/)** | Generate and score research ideas (Interestingness/Feasibility/Novelty) with iterative refinement | 1 script: `novelty_check.py` |
  37. | **[novelty-assessment](skills/novelty-assessment/)** | Harsh-critic novelty evaluation with up to 10 rounds of literature search | Shares search scripts |
  38. | **[research-planning](skills/research-planning/)** | 4-stage research plan design with task dependency graphs | Prompt-only |
  39. ### Phase 1: Method Design
  40. | Skill | Description | Scripts |
  41. |-------|-------------|---------|
  42. | **[atomic-decomposition](skills/atomic-decomposition/)** | Decompose ideas into atomic concepts with bidirectional math ↔ code mapping | Prompt-only |
  43. | **[algorithm-design](skills/algorithm-design/)** | Algorithm pseudocode (LaTeX) + UML diagrams (Mermaid) with consistency verification | Prompt-only |
  44. | **[math-reasoning](skills/math-reasoning/)** | Derivations, proofs, formalization, statistical test selection, notation tables | Prompt-only |
  45. | **[symbolic-equation](skills/symbolic-equation/)** | LLM-guided evolutionary search for scientific equation discovery | Prompt-only |
  46. ### Phase 2: Experiment Pipeline
  47. | Skill | Description | Scripts |
  48. |-------|-------------|---------|
  49. | **[experiment-design](skills/experiment-design/)** | 4-stage progressive experiment planning (implement → tune → research → ablate) | 1 script: `design_experiments.py` |
  50. | **[experiment-code](skills/experiment-code/)** | ML training/evaluation pipeline generation with iterative improvement | Prompt-only |
  51. | **[code-debugging](skills/code-debugging/)** | Structured error analysis with categorization and 4-retry fix loop | Prompt-only |
  52. | **[data-analysis](skills/data-analysis/)** | Statistical analysis with 4-round code review and appropriate test selection | 2 scripts: `stat_summary.py`, `format_pvalue.py` |
  53. ### Phase 3: Paper Writing
  54. | Skill | Description | Scripts |
  55. |-------|-------------|---------|
  56. | **[paper-writing-section](skills/paper-writing-section/)** | Section-by-section writing with section-specific guidance and two-pass refinement | Prompt-only |
  57. | **[related-work-writing](skills/related-work-writing/)** | Related Work section with thematic organization and compare-and-contrast style | Prompt-only |
  58. | **[survey-generation](skills/survey-generation/)** | Complete survey paper via RAG-based subsection writing with citation validation | Shares search scripts |
  59. | **[paper-to-code](skills/paper-to-code/)** | Convert paper PDF to runnable code repo (Planning → Analysis → Coding pipeline) | Prompt-only |
  60. ### Phase 4: Figures, Tables & Citations
  61. | Skill | Description | Scripts |
  62. |-------|-------------|---------|
  63. | **[figure-generation](skills/figure-generation/)** | Publication-quality matplotlib figures with VLM feedback loop (10 figure types) | 1 script: `figure_template.py` |
  64. | **[table-generation](skills/table-generation/)** | JSON/CSV → LaTeX booktabs tables with bold-best, significance stars, multi-dataset | 1 script: `results_to_table.py` |
  65. | **[citation-management](skills/citation-management/)** | BibTeX harvesting, validation, deduplication, and auto-fix | 2 scripts: `harvest_citations.py`, `validate_citations.py` |
  66. | **[backward-traceability](skills/backward-traceability/)** | Every PDF number hyperlinks to the code line that produced it | 1 script: `ref_numeric_values.py` |
  67. ### Phase 5: LaTeX & Compilation
  68. | Skill | Description | Scripts |
  69. |-------|-------------|---------|
  70. | **[latex-formatting](skills/latex-formatting/)** | Conference templates (ICML/ICLR/NeurIPS/AAAI/ACL), formatting fixes, pre-submission checks | 2 scripts: `latex_checker.py`, `clean_latex.py` |
  71. | **[paper-compilation](skills/paper-compilation/)** | Full pdflatex+bibtex pipeline with auto-fix error correction loop | 2 scripts: `compile_paper.py`, `fix_latex_errors.py` |
  72. | **[excalidraw-skill](skills/excalidraw-skill/)** | Programmatic Excalidraw diagramming via MCP tools with quality verification | MCP server (7 CJS files) |
  73. ### Phase 6: Review & Polish
  74. | Skill | Description | Scripts |
  75. |-------|-------------|---------|
  76. | **[self-review](skills/self-review/)** | 3-persona automated review (NeurIPS form) with reflection and meta-review | 2 scripts: `extract_pdf_text.py`, `parse_pdf_sections.py` |
  77. | **[paper-revision](skills/paper-revision/)** | Map reviewer concerns to sections, apply targeted edits, verify improvements | Prompt-only |
  78. | **[rebuttal-writing](skills/rebuttal-writing/)** | Point-by-point rebuttal with evidence-based responses | Prompt-only |
  79. | **[slide-generation](skills/slide-generation/)** | Paper → Beamer slides (extract elements, generate skeleton, simplify) | 1 script: `extract_paper_elements.py` |
  80. | **[paper-assembly](skills/paper-assembly/)** | End-to-end pipeline orchestrator with 9-phase checkpointing | 1 script: `assembly_checker.py` |
  81. ## Usage
  82. ### Slash commands
  83. ```
  84. /research transformer architectures for long-context reasoning
  85. ```
  86. ### Natural language (skills activate automatically)
  87. ```
  88. "Analyze GitHub repos for multi-agent coordination research"
  89. "Do a literature review on protein folding with LLMs"
  90. "Write the Methods section of my paper"
  91. "Generate a comparison table from results.json"
  92. "Review my paper draft before submission"
  93. "Make slides from my paper"
  94. "Check if my idea is novel"
  95. "Design experiments for my contrastive learning method"
  96. ```
  97. ### Direct script usage
  98. ```bash
  99. # Search GitHub repos for a research topic
  100. python ~/.claude/skills/github-research/scripts/search_github.py --query "multi-agent LLM coordination" --max-results 50 --output repos.jsonl
  101. # Analyze a cloned repo's structure
  102. python ~/.claude/skills/github-research/scripts/analyze_repo_structure.py --repo-dir ./my-repo --output analysis.json
  103. # Search literature
  104. python ~/.claude/skills/literature-search/scripts/search_crossref.py --query "attention mechanism" --rows 10
  105. # Validate citations
  106. python ~/.claude/skills/citation-management/scripts/validate_citations.py --tex paper/main.tex --bib paper/references.bib
  107. # Generate experiment design
  108. python ~/.claude/skills/experiment-design/scripts/design_experiments.py --method "contrastive learning" --task classification --format markdown
  109. # Format p-values
  110. python ~/.claude/skills/data-analysis/scripts/format_pvalue.py --values "0.001 0.05 0.23" --format latex
  111. # Extract paper elements for slides
  112. python ~/.claude/skills/slide-generation/scripts/extract_paper_elements.py --tex main.tex --output slides.tex
  113. # Check paper pipeline completeness
  114. python ~/.claude/skills/paper-assembly/scripts/assembly_checker.py --dir paper/ --verbose
  115. ```
  116. ## Architecture
  117. All skills follow the same structure:
  118. ```
  119. skills/<skill-name>/
  120. ├── SKILL.md # Skill definition (prompt, workflow, rules)
  121. ├── scripts/ # Executable tools (optional)
  122. │ └── *.py # CLI scripts with argparse, docstring headers
  123. └── references/ # Reference docs (optional)
  124. └── *.md # Templates, API docs, patterns
  125. ```
  126. **Design principles:**
  127. - Scripts are stdlib-only where possible (no heavy dependencies)
  128. - Every script has `--help`, docstring header with usage examples, and argparse CLI
  129. - Skills link to each other via `## Related Skills` sections (upstream/downstream/see-also)
  130. - Prompt-only skills are fully self-contained in SKILL.md
  131. ## Requirements
  132. - [Claude Code](https://claude.ai/code)
  133. - Python 3
  134. - Optional: PyMuPDF, numpy, scipy (see installation)

Ratings and comments

Sign in to rate this skill.

Sign in

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