commit
The /commit slash command analyzes staged git changes using `git diff --cached` and generates a Semantic Commit message following Conventional Commits standards. It determines the appropriate commit type (feat, fix, docs, refactor, chore), creates a concise subject line under 50 characters, and writes a structured body detailing added, modified, and deleted resources to `.git/COMMIT_EDITMSG`. Use this command when ready to commit staged changes and needing an automatically formatted commit message.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/guanyang/open-agent-hub/HEAD/commands/commit.md -o ~/.claude/commands/commit.mdcommit.md
# Slash Command: /commit ## Core Objective Analyze staged git modifications and generate/write a high-quality Semantic Commit message. ## Steps for the Agent 1. **Analyze Staged Changes**: Run `git diff --cached` to inspect what changes have been staged. 2. **Determine Conventional Commit Type**: - `feat`: New features (e.g., new skill, agent, command, utility). - `fix`: Bug fixes. - `docs`: Documentation updates. - `refactor`: Code restructurings. - `chore`: Maintenance, dependencies, config updates. 3. **Format Subject & Body**: - Write a concise summary line (subject) under 50 characters. - Formulate a structured commit message body detailing Added, Modified, and Deleted resources. 4. **Action**: Write the generated message directly to `.git/COMMIT_EDITMSG`. 5. **Output**: Output the commit message for the user to review, and tell them they can run `git commit -F .git/COMMIT_EDITMSG` to finalize the commit.
Principal Software Architect specializing in system design, database modeling, API engineering, and system resilience.
Principal Diagnostics Engineer specializing in root cause analysis, error troubleshooting, and hotfixes.
Principal Clean Code Specialist specializing in code simplification, performance tuning, and refactoring loops.
Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.
Senior QA Automation Engineer specializing in unit, integration, and E2E test suite creation.
Run when user calls /review. Analyzes local changes and runs a comprehensive code review using the agent-reviewer prompt.
Run when user calls /test-tdd. Scans modified files, locates their corresponding unit/integration test suites, and runs them.
This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.