agentleFS
Sign inStart free
evergonlabsevergonlabs/aiframework/.claude/skills/aiframework-review/SKILL.md

aiframework-review

Skill0 starsChanged 7 months agoMITView on GitHub

aiframework pre-landing code review with project-specific checks. Checks all invariants, runs specialist reviews based on changed files.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Verify LLM output is never trusted as safe.

    line 24
  2. Distinctive:

    Look for: unsanitized AI output in HTML, eval of AI-generated code, AI output in SQL.

    line 25
  3. Distinctive:

    Verify no API keys, passwords, tokens, or credentials are committed.

    line 28
  4. Distinctive:

    Look for: hardcoded secrets, .env files committed, credentials in config, tokens in URLs.

    line 29
  5. Very specific:

    Check tools/review-specialists/ for domain-specific review checklists.

    line 35
  6. Distinctive:

    If vault/ exists, check for related decisions:

    line 46
  7. Very specific:

    Read vault/memory/decisions/ for ADRs related to changed files

    line 47
  8. Very specific:

    Run vault/.vault/scripts/vault-tools.sh lint to verify vault integrity

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

/aiframework-review — Code Review

Step 1: CRITICAL Pass

For each changed file (git diff --name-only HEAD~1 HEAD), check:

1.1 INV-1: LLM Trust Boundary

Verify LLM output is never trusted as safe. Look for: unsanitized AI output in HTML, eval of AI-generated code, AI output in SQL.

1.2 INV-2: No Secrets in Source Code

Verify no API keys, passwords, tokens, or credentials are committed. Look for: hardcoded secrets, .env files committed, credentials in config, tokens in URLs.

Step 2: Specialist Army (if applicable)

Launch parallel specialists based on what files changed. Check tools/review-specialists/ for domain-specific review checklists.

Step 3: Report

Output a table:

CheckStatusDetails
...PASS/FAIL/WARN...

Step 4: Vault Check

If vault/ exists, check for related decisions:

  • Read vault/memory/decisions/ for ADRs related to changed files
  • Run vault/.vault/scripts/vault-tools.sh lint to verify vault integrity

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.

Check your setup, free