oprogramadorreal/skills/commit-message
skills/commit-message/SKILL.md
Suggests conventional commit messages by analyzing staged, unstaged, and untracked git changes — read-only, never commits. Use when a commit message suggestion is needed without actually committing.
$ install --global
skillsauthnpx skillsauth add oprogramadorreal/optimus-claude skills/commit-messageInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 16, 2026, 5:41 AM160.3s3 files scanned
SKILL.md
- description:
- Suggests conventional commit messages by analyzing staged, unstaged, and untracked git changes — read-only, never commits. Use when a commit message suggestion is needed without actually committing.
- disable-model-invocation:
- true
Commit Message Suggester
Generate a conventional commit message by analyzing all local git changes (staged, unstaged, and untracked) without performing any commit.
Workflow
1. Gather Change Context
Read $CLAUDE_PLUGIN_ROOT/skills/commit/references/gather-changes.md and follow the procedure (multi-repo detection + git commands).
2. Analyze Changes and Generate Conventional Commit Message
Read $CLAUDE_PLUGIN_ROOT/skills/commit-message/references/conventional-commit-format.md and follow its instructions to analyze the gathered changes and generate a conventional commit message.
3. Present the Message
Output the suggested commit message in a copyable code block. Do NOT run git commit. If the changes naturally split into multiple commits, present each message separately with instructions on which files to stage for each.
In a multi-repo workspace, present each repo's commit message under a heading with the repo directory name (e.g., ## isa-server). If a repo's changes span multiple concerns, suggest separate commits within that repo's section. If only one repo has changes, still label it with the repo name for clarity.
Important
- Never commit, stage, or modify any files
- This skill is read-only — it only analyzes and suggests
- When changes are too broad for a single commit, recommend splitting
Recommend the next step based on readiness:
- If the user wants to commit now →
/optimus:committo commit (and optionally push) - If the feature is ready →
/optimus:prto create a pull request
Tell the user the closing tip per $CLAUDE_PLUGIN_ROOT/references/skill-handoff.md "Closing tip wording" — use Variant A with <continuation-skill(s)> = `/optimus:commit` or `/optimus:pr` and <non-continuation-examples> = /optimus:code-review, /optimus:unit-test, etc.
Related Skills
oprogramadorreal/skills/spec-init
development
VerifiedTrustedCommunity
Use when starting a new project or product and you want a docs-first plan before writing code — scaffolds an empty, product-neutral spec-driven-development cascade (product vision, MVP PRD, target tech-stack) for a human to fill, then hands off to brainstorm. Emits skeletons only; it never authors product content and never overwrites existing docs.
57SKILL.mdUpdated Jun 4, 2026
oprogramadorreal/skills/handoff
tools
VerifiedTrustedCommunity
Compacts the current conversation into a single self-contained handoff document under docs/handoffs/ so a fresh agent — a new session, a different AI tool, or another developer on a different machine — can resume the work by reading only that file. References committed artifacts (PRDs, plans, ADRs, issues, commits) by path or URL and inlines anything not yet pushed. Redacts secrets and PII. Re-running on an existing handoff lets you enhance the shared doc or overwrite it. Use when pausing work that someone else or a future session will pick up, or when a long conversation needs a durable summary.
57SKILL.mdUpdated May 26, 2026
oprogramadorreal/skills/unit-test
development
VerifiedTrustedCommunity
Improves unit test coverage on demand — discovers testing gaps and generates tests that follow project conventions. Requires /optimus:init to have set up test infrastructure first. Conservative — only adds new test files, never refactors existing source code. Supports `deep` mode for iterative in-conversation test generation and `deep harness` mode for an automated multi-cycle unit-test + testability-refactor loop with fresh context per phase. Use when test coverage is low, after adding new code that lacks tests, or when you want an automated coverage-improvement harness.
57SKILL.mdUpdated Apr 15, 2026
oprogramadorreal/skills/tdd
development
VerifiedTrustedCommunity
Guides test-driven development — decompose a feature or bug fix into behaviors, then cycle through Red (failing test) → Green (minimal implementation) → Refactor for each one. Requires /optimus:init and working test infrastructure. Use when starting a new feature or bug fix with test-first discipline.
57SKILL.mdUpdated Apr 15, 2026