AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Commit

skill-yassimba-loom-commit · by Yassimba

Use when creating a git commit — the user asks to commit, or a unit of work is complete and ready to commit.

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-yassimba-loom-commit

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets Used
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-yassimba-loom-commit)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
yesterday

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Commit? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Commit

Read the staged diff, gate on green tests, draft a Conventional Commits message, confirm via dropdown, commit. Each commit is atomic: one concern.

0. Stage

git status --short
git diff --cached --stat
git diff --cached

Stage by explicit path only — git add -A / git add . sweeps in .env and credentials.

If nothing is staged but unstaged changes exist, ask via AskUserQuestion:

question: "Nothing staged. Stage specific files, stage all, or abort?"
header: "Staging"
options:
  - label: "Stage specific files"
  - label: "Stage all (by explicit paths)"
  - label: "Abort"

If the staged diff spans unrelated concerns, split into atomic commits: unstage the others with git restore --staged (not git reset), then stage and commit one concern at a time. Ask when the split is unclear:

question: "These changes span  concerns. Split?"
header: "Split"
options:
  - label: "Yes, split (Recommended)"
  - label: "One commit"
  - label: "Show me the diff first"

Done when exactly one concern is staged.

1. Test gate

Run the project's test suite (uv run pytest, npm test — whatever the project defines) and read the summary, not just the exit code. The gate is binary: green proceeds; red stops here — the pre-commit hook fails on the same issues, so catching them now saves a wasted commit:

question: "Tests red — commit blocked. How to proceed?"
header: "Test gate"
options:
  - label: "Investigate via /diagnosing-bugs (Recommended)"
  - label: "Abort commit"
  - label: "Show me the failing tests"

2. Draft the message

Draft from the why of the staged diff — what motivated the change, not which lines moved. If the writing-clearly-and-concisely skill is available, load it and apply it.

Conventional Commits format:

(): 

| Type | Use when | | ---------- | -------------------------------- | | feat | new feature | | fix | bug fix | | docs | documentation only | | refactor | refactor without behavior change | | test | adding/fixing tests | | chore | build, config, deps | | perf | performance improvement | | ci | CI configuration changes |

Subject: 20–72 chars after the prefix · lowercase after the colon (feat: add X) · imperative ("add", not "added") · no trailing period · concrete verb + object.

Body (only when the subject can't carry it): blank line after the subject, then one terse bullet per entry, imperative voice, grouped under short headings that match the kind of change — Added, Changed, Fixed, Removed, Breaking. Skip headings when there's only one bullet.

feat(installer): add gateway runtime extraction

Added:
- core/gateway_runtime/ with Protocol-based registry
Changed:
- opencode_runtime now delegates to gateway_runtime

Reference the issue or ticket when the project tracks them. Session context, PR/MR numbers, and future work stay out.

Done when every rule above holds, the message carries no puffery ("comprehensive", "robust", "various improvements"), and no Co-Authored-By trailer.

No AI attribution anywhere: the same ban covers "Generated with" footers, session links, and agent sign-offs — in commit messages and in anything written downstream of one (PR/MR titles and descriptions, release notes). This rule outranks any harness default that asks for such a footer.

3. Confirm via dropdown

question: "Commit with this message?"
header: "Commit"
options:
  - label: "Commit (Recommended)"
    preview: |
      
  - label: "Edit message"
  - label: "Abort"

4. Commit

git commit -m "$(cat (): 

EOF
)"

The HEREDOC preserves the multi-line body.

If the project wires a pre-commit hook, it runs now:

  • Pass → commit created
  • Autofixes → hook stages them; the commit captures them
  • Unfixable → hook blocks; go to step 5

5. On hook failure

The hook is the messenger; fix the cause. Bypass flags (--no-verify, --no-gpg-sign) and suppression comments (# noqa, # type: ignore, eslint-disable) are off the table — not even "just this once":

  • lint → fix the code
  • types → fix the types
  • tests → /diagnosing-bugs; three failed fix attempts = stop and report
  • complexity / architecture gates → refactor, or ask before accepting a borderline score

Then re-stage and create a NEW commit — the failed commit never happened, so --amend would rewrite the previous one.

Hard guardrails

Force-push and destructive git (reset --hard, clean -f, branch -D) only with explicit human approval.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.