Skills making-commits
📦

making-commits

Content revision r1 Safe

Create Clear Git Commits

Large changes often produce messy commit history that slows review. This skill guides Claude, Codex, and Claude Code to make small commits with quality checks.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "making-commits" from https://skillstore.io/skills/crossbill-highlights-making-commits.md and its manifest at https://skillstore.io/api/skills/crossbill-highlights-making-commits/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/crossbill-highlights-making-commits.md Signed manifest GET /api/skills/crossbill-highlights-making-commits/manifest Signed lockfile GET /api/skills/crossbill-highlights-making-commits/lockfile

Test it

Using "making-commits". I changed the API client, updated tests, and reformatted unrelated files.

Expected outcome:

Suggested split: one commit for API client behavior, one commit for related tests, and one separate formatting commit if needed.

Using "making-commits". I finished a large feature and want a clean pull request history.

Expected outcome:

  • Start with dependency or setup changes.
  • Commit the core feature implementation separately.
  • Add tests in a focused follow-up commit.
  • Run linting and formatting before the final commit.

Security Audit

Safe
v10 • 7/6/2026 Open versioned report

No static findings were reported for this prompt-only skill. Manual review found no prompt injection, credential handling, executable code, network access, or filesystem operations in SKILL.md.

1
Files scanned
9
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/crossbill-highlights-making-commits/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/crossbill-highlights-making-commits/security.svg)](https://skillstore.io/skills/crossbill-highlights-making-commits?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/crossbill-highlights-making-commits?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/crossbill-highlights-making-commits/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/crossbill-highlights-making-commits.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

Crossbill-Highlights. (2026). making-commits security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/crossbill-highlights-making-commits/audits/10

BibTeX citation

@techreport{crossbill-highlights-crossbill-highlights-making-commits-2026, author = {Crossbill-Highlights}, title = {making-commits security audit report (audit version 10)}, institution = {Skillstore}, year = {2026}, number = {10}, url = {https://skillstore.io/skills/crossbill-highlights-making-commits/audits/10}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "making-commits security audit report (audit version 10)" version: "unspecified" type: report authors: - name: "Crossbill-Highlights" date-released: "2026-07-06" url: "https://skillstore.io/skills/crossbill-highlights-making-commits/audits/10" identifiers: - type: other value: "skillstore:crossbill-highlights-making-commits:audit:10" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
85
Content
70
Community
91
Spec Compliance

What You Can Build

Prepare Reviewable Feature Work

Split a larger feature into focused commits before opening a pull request.

Clean Up Agent-Generated Changes

Guide an AI coding agent to group generated edits into logical commit steps.

Maintain Project Commit Hygiene

Remind contributors to run formatting and linting before recording project changes.

Try These Prompts

Plan Small Commits 
Review my current changes and suggest a small, focused commit plan. Keep each commit limited to one concern.
Group Related Changes 
Group these edits into logical commits for review. Identify any change that should be separated before committing.
Check Commit Readiness 
Before I commit, verify that the change groups are focused and list the linting or formatting checks I should run.
Structure a Large Task History 
Create a commit sequence for this larger task. Separate setup, implementation, tests, and cleanup into reviewable steps.

Best Practices

  • Keep each commit focused on one concern or feature.
  • Split large changes into logical review steps.
  • Run linting and formatting before creating commits.

Avoid

  • Combining unrelated fixes, features, and formatting in one commit.
  • Committing large tasks without a clear review sequence.
  • Skipping formatting or linting before recording changes.

Frequently Asked Questions

Does this skill run Git commands?
No. It provides guidance only and does not execute commands.
Can it write commit messages?
It can help plan commits, but the source does not define a message format.
Does it work with Claude Code?
Yes. The report marks it compatible with Claude, Codex, and Claude Code.
What problem does it solve?
It helps keep commit history focused, readable, and easier to review.
Should I still run tests?
Yes. The skill mentions linting and formatting, but it does not replace tests.
Is this a security-sensitive skill?
No evidence found. It is a prompt-only skill with no executable code or external access.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/Crossbill-Highlights/crossbill-web/tree/main/.claude/skills/making-commits

Ref

b959ebfd1043a07c0c4378ab94ca4342cb0259f5

Maintenance freshness

7/20/2026

Usage

8 downloads · 173 views

File structure

📄 SKILL.md

More from Crossbill-Highlights

View all

Related Skills

View all