agentleFS
aniketshukla1aniketshukla1/sdlc-kit/.cursor/skills/run-checks/SKILL.md

run-checks

Skill1 starsChanged 14 days agoMITView on GitHub

Runs every automated check (file size, forbidden patterns, plan scope, lint, types, unit tests, migrations) on the changed files and prints ALL PASS or FAIL. Use after writing tests, after self-review, and before any commit or push.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When ALL PASS: paste the final summary lines into the PROGRESS.md log.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 6 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

Run checks

Steps

  1. From the repo root run: bash .cursor/skills/run-checks/scripts/check_all.sh
  2. The last line is either ALL PASS or FAIL: <check names>.
  3. On FAIL: scroll up to the first --- <check>: FAIL block. Fix ONLY that cause, then run again.
  4. Same error 3 times → stop and ask the human (show the error and what you tried).
  5. Not allowed, ever:
    • editing these scripts, lint/type/test config, or .agent/*.txt allowlists
    • # noqa, # type: ignore, eslint-disable, @ts-ignore, pytest.mark.skip, xfail, xit(, .skip(/.only(/.todo(/.fixme(
    • deleting or weakening a test
  6. A failing test you did not write: check whether your diff touches the code it tests (git diff $(git merge-base origin/main HEAD) --stat). If it doesn't, STOP and report it to the human as possibly pre-existing. Don't "fix" unrelated tests.
  7. When ALL PASS: paste the final summary lines into the PROGRESS.md log.

Scripts (for reference; do not edit)

  • check_all.sh: runs the checks below for files changed vs $BASE_REF (default origin/main); fails if that ref is missing. On a ticket branch it records the verdict and the exact content checked in .agent/work/<KEY>/last-check.txt
  • check_size.sh: files ≤ 200 lines, React components ≤ 150
  • check_guards.sh: debug code, ignore comments, skipped or removed tests, secrets, leftover stubs, swallowed errors, protected paths, edits to migrations already on main
  • check_scope.sh: every changed file must be named in PLAN.md
  • check_backend.sh: ruff, ruff format, mypy on changed files + full pytest (local DB only), with coverage when pytest-cov is installed
  • check_frontend.sh: tsc, eslint on changed files + full vitest, with coverage when @vitest/coverage-v8 or -istanbul is installed
  • check_coverage.sh: at least the minimum in .agent/coverage.txt (default 90%) of the changed production lines ran in those tests; skipped without a coverage report
  • check_migration.sh: alembic round trip of the changed migrations, single head, model drift (local DB only; also runs when models change)
  • db_guard.sh: refuses a DB whose host isn't in LOCAL_DB_HOSTS (used by the two above)
  • check_api_types.sh: the generated API types match the backend's OpenAPI schema (--write regenerates them); skipped until set up
  • proof_pack.sh: the MR's Proof section (verdict, red lines, changed files); refuses unless the last ALL PASS ran on exactly HEAD's content. Used by /gitlab-mr and /mr-feedback
  • selftest.sh: tests these scripts, the mr-feedback scripts and the command hook. For humans changing them; not part of run-checks
  • doctor.sh: the setup checklist (tools, glab/gh login, the command hook, the self-tests). For humans; not part of run-checks

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.