Fallow
Skill produtoramaxvision/maxvision-utilities/.claude/skills/fallow
Use when auditing TypeScript/JavaScript code quality in this repo — dead code, copy-paste duplication, complexity hotspots, circular dependencies, architecture boundary violations, or gating a PR. Triggers on "fallow", "codebase audit", "dead code", "find duplication", "complexity hotspots", "PR gate", "tech debt scan". Deterministic (no AI), Rust engine, sub-second. Run after editing TS/TSX.From its SKILL.md
npx -y skills add produtoramaxvision/maxvision-utilities --skill fallowAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.5 KB, 294 tokens by cl100k_base, as published. Nobody here has run it
fallow — deterministic codebase intelligence (TS/JS)
Static analysis of this pnpm monorepo (no AI): dead code, duplication, complexity, dependency hygiene, architecture cycles. Run via pnpm exec fallow or the fallow MCP server (registered in .mcp.json).
Commands
pnpm exec fallow audit --format json --quiet— PR gate: verdictpass/warn/failover changed filespnpm exec fallow health --score— repo health score 0–100pnpm exec fallow dead-code --format json --quiet— unused-code + dependency-hygiene candidatespnpm exec fallow dupes— copy-paste and structural duplicationpnpm exec fallow fix --dry-run— preview safe unused-code auto-fixes
Rules
- Apply only the
auto_fixableactions from theactions[]array; review the rest. - PR gate passes only on verdict
pass. - Suppress narrowly:
// fallow-ignore-next-line <rule>plus a one-line reason. NEVER raise a global threshold to hide a hotspot. - Config lives in
.fallowrc.jsonc(workspaces:media-forge,credit-core). The MCP server and this skill load when the Claude Code session reopens in this repo.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most refactoring skills give in 294 tokens
Counted across 521 of the 525 authors here whose files we hold, read 2026-08-07
- Run tests after each changein 52 of 521
- Run the full test suite after each stepin 32 of 521
- Preserve external behaviorin 27 of 521, across 24 files
- Remove dead codein 26 of 521
- Write tests before refactoringin 26 of 521, across 25 files
- Make small incremental changesin 19 of 521, across 16 files
- Break the implementation into tiny commitsin 18 of 521, across 5 files
- Ask the user about alternative optionsin 17 of 521, across 4 files
- Create a GitHub issue with the planin 17 of 521, across 4 files
- Explore the repository to verify assertionsin 17 of 521, across 4 files
- Interview the user about the refactorin 16 of 521, across 3 files
- Check the codebase for test coveragein 16 of 521, across 3 files
Said here and by no other author read
- run the audit command for PR gating
- apply only auto-fixable actions
- review non-auto-fixable actions
- require pass verdict for PR gate
- suppress findings narrowly with inline comments
- include a one-line reason for suppressions
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.