agentleFS
Sign inStart free
ebibibiebibibi/ebi-agent-chat-relay/.claude/skills/verify/SKILL.md

verify

Skill66 starsChanged 9 months agoMITView on GitHub

Run full verification pipeline (lint, format, test, security) before committing

188 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use instinct-export, instinct-import and 10 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.
  • TheKREATORSSkill

    instinct-export

    Export instincts from project/global scope to a file

    Also in 3 projects that use this

  • TheKREATORSSkill

    instinct-import

    Import instincts from file or URL into project/global scope

    Also in 3 projects that use this

  • AviadPSkill

    risk-assess

    Assess the risk and blast radius of a proposed code change before implementing it. Evaluates CI impact, framework-wide vs localized scope, rollback path, and identifies blindspots. Use when user says "what's the risk", "is this safe", "assess the impact", "risk assess", "blast radius", or before applying framework-wide or CI-affecting changes. Do NOT use for code quality review (use code-quality) or plan validation (use design-validator).

    Also in 3 projects that use this

  • diego-tobalinaSkill

    build-fix

    Fix build and compilation errors systematically. Run when build fails.

    Also in 6 projects that use this

  • AaravChadhaSkill

    secure

    Security review with a confidence gate - a finding exists only with a concrete exploit scenario and a high/medium/low confidence rating; everything else goes to a worth-hardening list, never inflated. Sweeps five surfaces: auth gates, secrets hygiene, injection and unsafe sinks, unsafe deserialization/crypto/transport, and LLM tool-use trust boundaries. Reports only, never fixes. Use when the user asks for a security review or to check vulnerabilities, secrets, or auth.

    Also in 3 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 10 projects that use this

  • +1 more from TheKREATORS

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 12 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 166 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run this before every commit to ensure code quality and security.

    line 8
  2. Distinctive:

    Before creating a commit

    line 12
  3. Distinctive:

    Before pushing to remote

    line 13
  4. Distinctive:

    After making significant code changes

    line 14
  5. Distinctive:

    When asked to "verify", "check", or "validate" the code

    line 15
  6. Distinctive:

    Run all steps in order. Stop on first failure.

    line 19
  7. Distinctive:

    If there are auto-fixable issues:

    line 27
  8. Distinctive:

    If formatting is needed:

    line 39
  9. Distinctive:

    All tests must pass. Review coverage for newly added code.

    line 51
  10. Distinctive:

    Before committing, check for these security concerns specific to this project:

    line 55
  11. Very specific:

    No shell=True: Search for shell=True in any subprocess call — this is forbidden

    line 57
  12. Very specific:

    No hardcoded secrets: Search for patterns like token, secret, password, api_key with string literal values

    line 58
  13. Very specific:

    Subprocess arguments: All user input passed to Claude CLI must use -- separator

    line 60
  14. Distinctive:

    Verify the public API still works:

    line 70
  15. Distinctive:

    Security failures: STOP. Do not commit. Fix the vulnerability first

    line 80
  16. Very specific:

    Import failures: Check __init__.py exports match actual module structure

    line 81

“Common” is measured: kept by at least 6 in 10 of the 166 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

Verify — Pre-Commit Quality Gate

Run this before every commit to ensure code quality and security.

When to Activate

  • Before creating a commit
  • Before pushing to remote
  • After making significant code changes
  • When asked to "verify", "check", or "validate" the code

Verification Pipeline

Run all steps in order. Stop on first failure.

Step 1: Lint

uv run ruff check claude_discord/

If there are auto-fixable issues:

uv run ruff check --fix claude_discord/

Step 2: Format

uv run ruff format --check claude_discord/

If formatting is needed:

uv run ruff format claude_discord/

Step 3: Tests

uv run pytest tests/ -v --cov=claude_discord --cov-report=term-missing

All tests must pass. Review coverage for newly added code.

Step 4: Security Audit

Before committing, check for these security concerns specific to this project:

  1. No shell=True: Search for shell=True in any subprocess call — this is forbidden
  2. No hardcoded secrets: Search for patterns like token, secret, password, api_key with string literal values
  3. Session ID validation: Any new code accepting session IDs must validate with ^[a-f0-9\-]+$
  4. Subprocess arguments: All user input passed to Claude CLI must use -- separator
  5. Environment stripping: _STRIPPED_ENV_KEYS must include any new secret env vars
# Quick security grep
uv run ruff check claude_discord/ --select S  # bandit rules via ruff

Step 5: Import Check

Verify the public API still works:

python -c "from claude_discord import ClaudeRunner, ClaudeChatCog, SkillCommandCog, SessionRepository"

Failure Protocol

  • Lint/Format failures: Fix automatically, re-run
  • Test failures: Fix the code (not the test, unless the test is wrong)
  • Security failures: STOP. Do not commit. Fix the vulnerability first
  • Import failures: Check __init__.py exports match actual module structure

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