Skip to content
Back to search

look-before-you-build

MarketplaceWorks with Claude CodeGitHub

Risk-scaled meta-research skill for Claude Code: decide how much thinking a task deserves before building it.

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/gxxxr-111--look-before-you-build/badge.svg)](/listings/gxxxr-111--look-before-you-build)

HTML

<a href="/listings/gxxxr-111--look-before-you-build"><img src="/api/listings/gxxxr-111--look-before-you-build/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.

As a plugin (recommended):

/plugin marketplace add gxxxr-111/look-before-you-build
/plugin install look-before-you-build@look-before-you-build

Or copy the skill folder by hand:

git clone https://github.com/gxxxr-111/look-before-you-build
cp -R look-before-you-build/skills/preflight ~/.claude/skills/preflight

Make it actually trigger

Claude rarely picks this skill up on its own for build requests (see below). Add one line to `~/.claude/CLAUDE.md` or a project's `CLAUDE.md`:

Before starting a new project or feature, an integration with an external site/API, a scraper or automation, or a stack/architecture choice — or after the same bug survives three fix attempts — use the preflight skill.

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 · 17 lines
  1. {
  2. "name": "look-before-you-build",
  3. "owner": {
  4. "name": "gxxxr-111"
  5. },
  6. "metadata": {
  7. "description": "Risk-scaled meta-research skill for Claude Code: think about what to build before building it.",
  8. "version": "0.1.0"
  9. },
  10. "plugins": [
  11. {
  12. "name": "look-before-you-build",
  13. "source": "./",
  14. "description": "Risk-scaled meta-research before building: tiering, prior art, cheap environment scouting, a one-page brief, and mid-build step-back triggers."
  15. }
  16. ]
  17. }
README.md · README · 96 lines
  1. # look-before-you-build
  2. **English** | [简体中文](README.zh-CN.md)
  3. > **Status: v0.1, experimental.** Small eval suite, weak auto-triggering. See [What we know so far](#what-we-know-so-far).
  4. A Claude Code skill (`preflight`) that does the **meta-research** coding agents usually skip: deciding how much thinking a task deserves *before* writing code, then doing just that much.
  5. ## The problem
  6. Ask an agent to "build a game AI" and it piles up heuristics. Ask it to "write a scraper for subtitles" and it writes a scraper, without checking whether an official caption endpoint or a mature tool already exists. The costly mistakes are rarely bad code. They are:
  7. - **misclassifying the problem**: patching a search problem with hand-tuned rules instead of using minimax/MCTS;
  8. - **missing prior art**: an official API, a standard library, or an existing skill/MCP server;
  9. - **expensive access paths**: launching browser automation before looking at the docs, a sitemap, or structured data;
  10. - **architecture that's hard to undo**: data formats, schemas, public interfaces;
  11. - **losing the human**: a non-engineer can't follow, veto, or own the key decisions.
  12. Code review catches problems *after* code exists. This skill covers the step before, deciding what to build and how, which is where most rework comes from.
  13. ## What it does
  14. 1. **Tier the task** (0 / 1 / 2) by reversibility, blast radius, external dependencies, and uncertainty. Tier 0 just gets done, with no ceremony.
  15. 2. **Research at the depth the tier calls for.** A six-dimension checklist covers problem framing, prior art, access path, architecture, tooling, and human control. For tier 2, three parallel subagents handle problem classification, prior art, and cheap environment scouting.
  16. 3. **Write a one-page brief in plain language**, with runnable verification and every key decision (what was chosen, what was rejected, and the cost of changing it later).
  17. 4. **Ask first or build first.** Decisions the user can't cheaply undo (third-party ToS, accounts, money, schemas, data migrations, real forks in direction) wait for sign-off. Reversible ones get built and verified, then presented *with* the brief. The test: *if the user disagrees after seeing the result, how much do they lose?*
  18. 5. **Step back mid-build** after three failed fix rounds, two rejections, growing special cases, or a broken premise.
  19. 6. **Retro.** Each task ends by asking: *what question, asked up front, would have saved the most rework?* Answers go into the project's `PREFLIGHT.md` or your personal lessons file.
  20. Inspired in part by Anthropic's write-up on [how the Claude Code team does code review](https://claude.dev/blog/solving-code-review-at-anthropic/): effort scaled to risk, runnable verification, capped rounds, and incidents fed back into the process. This project is not affiliated with Anthropic.
  21. ## Install
  22. As a plugin (recommended):
  23. ```
  24. /plugin marketplace add gxxxr-111/look-before-you-build
  25. /plugin install look-before-you-build@look-before-you-build
  26. ```
  27. Or copy the skill folder by hand:
  28. ```bash
  29. git clone https://github.com/gxxxr-111/look-before-you-build
  30. cp -R look-before-you-build/skills/preflight ~/.claude/skills/preflight
  31. ```
  32. ### Make it actually trigger
  33. Claude rarely picks this skill up on its own for build requests (see below). Add one line to `~/.claude/CLAUDE.md` or a project's `CLAUDE.md`:
  34. ```markdown
  35. Before starting a new project or feature, an integration with an external site/API, a scraper or automation, or a stack/architecture choice — or after the same bug survives three fix attempts — use the preflight skill.
  36. ```
  37. ## Where your lessons live
  38. | File | Holds | Survives updates |
  39. |---|---|---|
  40. | `skills/preflight/references/lessons.md` | Starter lessons shipped with the skill | Replaced on update |
  41. | `~/.claude/preflight/lessons.md` | Your own cross-project lessons | Yes |
  42. | `<project>/PREFLIGHT.md` | Project-specific pitfalls and checks | Yes |
  43. ## What we know so far
  44. Evaluated with Anthropic's skill-creator workflow, one run per configuration, so treat these as early signals and not as proof.
  45. | Case | With skill | Without skill | Notes |
  46. |---|---|---|---|
  47. | `rename-function-tier0` (trivial rename) | 3/3 | 3/3 | No ceremony in either; confirms tier 0 stays lightweight |
  48. | `gomoku-stuck-reframe` (5 failed weight tweaks) | 5/5 | 5/5 | Both reframed to search. Not discriminating yet |
  49. | `transcript-tool-tier2` (Bilibili transcripts at scale) | 6/6 | 3/6 | With the skill it built on an existing tool, wrote offline tests, and stopped before the login/ToS decision |
  50. **Auto-triggering is weak.** On 20 queries (10 that should trigger, 10 near-misses), precision was 100% but recall was 0–17%, and five rounds of rewriting the description didn't beat the original on held-out queries. Use the `CLAUDE.md` line above.
  51. Details: [`evals/RESULTS.md`](evals/RESULTS.md). Harder, more discriminating cases are very welcome.
  52. ## Run the evals
  53. ```bash
  54. claude plugin eval .
  55. ```
  56. Each run starts real agent sessions and costs real tokens (one full suite ran several hundred thousand). Run single cases while you iterate.
  57. ## Contributing
  58. Issues and PRs are welcome, especially:
  59. - eval cases where agents without the skill go wrong in a costly way;
  60. - lessons that answer "what question would have saved the most rework?" and apply across projects.
  61. This is a side project, so replies may be slow.
  62. ## License
  63. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

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