Release check
Use right before opening a pull request or shipping a change. A final gate covering tests, formatting, secrets, tenant-safety, and post-deploy steps.From its SKILL.md
npx -y skills add yousefkadah/laravel-ai-kit --skill release-checkAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 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
1.2 KB, 272 tokens by cl100k_base, as published. Nobody here has run it
Release check
Run this gate before proposing a PR. Do not push unless the human asked.
Gate
- Tests for the change pass — command + output captured.
- Formatter/linter clean (
vendor/bin/pint --dirty, and frontend build if UI changed). - No secrets in the diff — grep for keys, tokens,
.envlines, credentials. - Multi-tenant: every new query is scoped; no cross-tenant leak.
- No side-effectful behavior runs without an explicit trigger/approval.
- Diff is tight; no unrelated changes.
-
.ai/or a skill updated if this change altered a rule or workflow.
PR
- Branch off «
main» with afeat/…orfix/…name (never commit to main directly). - Fill in the PR template completely, with test evidence.
Post-deploy reminders
- «Restart queue workers after view/lang/template changes (
php artisan horizon:terminate).» - «Rebuild frontend (
npm run build) if assets changed.» - «Any migration ordering / backfill caveats.»
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most quality gates skills give in 272 tokens
Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07
- Read the output and check the exit codein 54 of 1195, across 14 files
- Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
- Identify the verification command proving the claimin 51 of 1195, across 12 files
- Run the full verification commandin 50 of 1195, across 11 files
- Verify output confirms the claimin 49 of 1195, across 12 files
- Check version control diff after agent delegationin 46 of 1195, across 6 files
- State claim with evidencein 44 of 1195, across 4 files
- Run the test suitein 33 of 1195, across 26 files
- Keep state in memory by defaultin 27 of 1195, across 6 files
- Make prototype runnable with one commandin 26 of 1195, across 5 files
- Produce a verification reportin 25 of 1195, across 14 files
- Detect the package manager from lockfilesin 24 of 1195, across 5 files
Said here and by no other author read
- Run tests and capture output
- Verify every new query is tenant-scoped
- Keep the diff tight without unrelated changes
- Update documentation if workflow changed
- Name branches with feat or fix prefixes
- Fill the pull request template completely with evidence
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.