agentleFS
tam159tam159/next-role/.agents/skills/quality/SKILL.md

quality

Skill67 starsChanged 15 days agoMITView on GitHub

Run the repo's quality gate — pre-commit on the files you changed by default, or the full `pre-commit run --all-files` sweep when asked for a full pass, before opening a PR, or after a large refactor. Use when the user asks for quality checks, pre-commit, linting, formatting, type checking, or wants to confirm the whole repo is clean.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tasks, analyze and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • genomewalkerSkill

    tasks

    Browse and resume tasks, threads, and background jobs across sessions

    Also in 3 projects that use this

  • AnthropicSkill

    analyze

    Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.

    Also in 3 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 3 projects that use this

  • AnthropicSkill

    debug

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run validation the way AGENTS.md defines it for this repo.

    line 8
  2. Very specific:

    Don't run it after every individual edit.

    line 18
  3. Distinctive:

    When invoked explicitly, when asked for a full quality pass, before opening a PR, or after a large refactor:

    line 22
  4. Distinctive:

    Run the command from the repo root.

    line 38
  5. Distinctive:

    If hooks modify files (ruff/prettier auto-fix, EOL fixer): re-read those files before reporting — the on-disk content differs from what you …

    line 39
  6. Distinctive:

    If hooks fail with errors (type errors, lint errors that aren't auto-fixable, secrets detected): report the errors.

    line 40
  7. Very specific:

    If integration tests or visual checks need services and docker ps shows the stack is not running, remind the user to run docker compose up …

    line 54

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Quality

Run validation the way AGENTS.md defines it for this repo. Two modes — pick by scope, not habit.

Changed-file check (default after edits)

Validate everything you touched once at the end of a task — modified tracked files plus new untracked, non-ignored files — in a single run from the repo root:

pre-commit run --files $(git ls-files --modified --others --exclude-standard)

Don't run it after every individual edit; batch. If pre-commit isn't on this shell's PATH, it is a backend dev dependency: backend/.venv/bin/pre-commit run --files ....

Full sweep (/quality, "full quality pass")

When invoked explicitly, when asked for a full quality pass, before opening a PR, or after a large refactor:

pre-commit run --all-files

This executes every configured hook on every tracked file:

  • trailing-whitespace, end-of-file-fixer, check-yaml, check-added-large-files
  • gitleaks (secret scanning)
  • Backend + analytics: ruff check --fix, ruff format, and uv run ty check per project
  • Analytics dbt SQL: sqlfluff fix + sqlfluff lint
  • Frontend: eslint --fix, prettier --write, pnpm --dir frontend type-check, and scripts/check-langchain-sdk-sync.mjs (single installed copy of @langchain/langgraph-sdk)

Workflow (both modes)

  1. Run the command from the repo root.
  2. If hooks modify files (ruff/prettier auto-fix, EOL fixer): re-read those files before reporting — the on-disk content differs from what you wrote — then re-stage and re-run until the run is clean.
  3. If hooks fail with errors (type errors, lint errors that aren't auto-fixable, secrets detected): report the errors. Do not edit unrelated files to make them pass — fix only what's broken.
  4. Report the final status: green (everything passed) or red (the remaining failures).

Targeted checks

Pre-commit runs linters and type checkers, not tests. Run the relevant suite before the pre-commit step when it gives faster, more relevant feedback:

  • Backend unit tests: cd backend && uv run pytest (one file: uv run pytest tests/path/test_file.py)
  • Backend integration tests: cd backend && uv run pytest -m integration (needs the local stack)
  • Frontend tests: cd frontend && pnpm test
  • Frontend type check only: cd frontend && pnpm type-check; lint + format + type-check together: pnpm quality

Local stack

If integration tests or visual checks need services and docker ps shows the stack is not running, remind the user to run docker compose up -d. Do not start the stack yourself — they may have stopped it intentionally.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.