agentsclimarketplace

Self review checklist

Skill theinterneti/TTA.dev/.claude/skills/self-review-checklist

AI devops for vibe coders

Install
npx -y skills add theinterneti/TTA.dev --skill self-review-checklist

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 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.

What its author says it does

Copied from the file, not written here

Use this skill before submitting code for review or merging a pull request. Covers a pre-merge checklist of common mistakes to catch.

SKILL.md

1.7 KB, 394 tokens by cl100k_base, as published. Nobody here has run it

Self-Review Checklist (TTA.dev)

Run through this checklist before marking any task or PR as complete.

Code Quality

  • All new functions have type annotations (str | None, not Optional[str])
  • All public functions have Google-style docstrings
  • No manual retry/timeout/cache loops — use primitives
  • State passed via WorkflowContext, not globals
  • Import order: stdlib → third-party → local

Testing

  • 100% coverage on new code
  • Tests follow AAA pattern (Arrange-Act-Assert)
  • Uses MockPrimitive for mocking (not real implementations)
  • Uses @pytest.mark.asyncio on async tests
  • Tests cover success, failure, and edge cases
  • No external dependencies in tests (databases, APIs, filesystem)

Security

  • No secrets or credentials in code
  • No new eval(), exec(), or subprocess.shell=True
  • URL validation uses urlparse(), not substring checks

Quality Gate

  • uv run ruff format --check . — zero violations
  • uv run ruff check . — zero violations
  • uvx pyright platform/ — zero errors
  • uv run pytest -v — all tests pass

Documentation

  • README updated if public API changed
  • Code examples are copy-paste runnable
  • Changed files have updated docstrings

Deep Reference

Gives 0 of the 12 instructions most code review skills give in 394 tokens

Counted across 610 of the 674 authors here whose files we hold, read 2026-08-06

  • push back with technical reasoning if wrongin 60 of 610, across 24 files
  • ask for clarification on unclear itemsin 51 of 610, across 16 files
  • fix critical issues immediatelyin 45 of 610, across 29 files
  • implement one item at a timein 45 of 610, across 11 files
  • group findings by severityin 44 of 610, across 43 files
  • verify feedback against the codebasein 42 of 610, across 8 files
  • dispatch a code reviewer subagentin 39 of 610, across 23 files
  • fix important issues before proceedingin 37 of 610, across 22 files
  • test each fix individuallyin 35 of 610, across 7 files
  • reply in github comment threadsin 33 of 610, across 5 files
  • check for security vulnerabilitiesin 31 of 610, across 27 files
  • factualize corrections without over-explainingin 30 of 610, across 2 files

Said here and by no other author read

  • Run this checklist before marking PR complete
  • Add type annotations to all new functions
  • Add Google-style docstrings to public functions
  • Pass state via WorkflowContext
  • Verify 100 percent coverage on new code
  • Keep external dependencies out of tests

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.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.