agentleFS
roborracleroborracle/agent-workflow-kit/skills/git-protocol/SKILL.md

git-protocol

Skill0 starsChanged 3 months agoMITView on GitHub

Audit git workflow compliance including branch architecture, commit standards, issue linkage, and production readiness (check git compliance, audit branches, git hygiene).

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Verify main and prod branches exist

    line 39
  2. Very specific:

    Check each of the last 20 commits against conventional format: type(scope): description

    line 44
  3. Distinctive:

    Check for orphaned issues (no linked commits)

    line 50

≈ “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

Git Protocol Enforcement

Audit scope: $ARGUMENTS (blank = full audit)

Pre-fetched State

All Branches

!git branch -a 2>/dev/null || echo "Not a git repository"

Current Branch

!git branch --show-current 2>/dev/null

Last 20 Commits

!git log --oneline -20 2>/dev/null

Open Issues

!gh issue list --state open --limit 20 --json number,title,labels 2>/dev/null | jq -r '.[] | "#\(.number): \(.title)"' 2>/dev/null || echo "No GitHub CLI or repo"

Tracked .env Files

!git ls-files 2>/dev/null | grep -E "\.env" || echo "None tracked"


Your Task

Using the pre-fetched data above, run a comprehensive audit:

Phase 1: Branch Architecture

  • Verify main and prod branches exist
  • Validate all branch names follow feature/* or hotfix/* convention
  • Flag non-standard names

Phase 2: Commit Standards

  • Check each of the last 20 commits against conventional format: type(scope): description
  • Valid types: feat, fix, docs, style, refactor, perf, test, chore, build, ci, revert
  • Flag commits without issue references (#N)

Phase 3: Issue Linkage

  • Identify commits without issue references
  • Check for orphaned issues (no linked commits)

Phase 4: Production Readiness

Scan for violations:

grep -rn --include="*.ts" --include="*.tsx" --include="*.js" --include="*.jsx" --include="*.py" --include="*.go" --include="*.rs" \
  -E "console\.(log|debug|info|warn|error)|debugger" src/ 2>/dev/null || echo "None found"
grep -rn --include="*.ts" --include="*.tsx" --include="*.js" --include="*.jsx" --include="*.py" --include="*.go" --include="*.rs" \
  -E "(TODO|FIXME|HACK|XXX):" src/ 2>/dev/null || echo "None found"
# Not violations on their own: list colocated tests so you can confirm the build excludes them
find src/ \( -name "*.test.*" -o -name "*.spec.*" \) 2>/dev/null

Phase 5: Branch Hygiene

  • Stale branches (14+ days no activity)
  • Merged branches that can be deleted
  • Branches without upstream tracking

Generate Compliance Report

AreaCheckStatus
BranchesCore branches existOK/FAIL
BranchesNaming conventionX violations
CommitsConventional formatX/20 compliant
CommitsIssue referencesX/20 linked
IssuesOpen countX
ProdDebug statementsX found
ProdTODO commentsX found
HygieneStale branchesX
HygieneMerged (deletable)X

Overall compliance: X%

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.