Skip to content
Back to skills

Commit 68

ASecurity

Commit with user prompts from this conversation. Use when user mentions committing, wants to commit changes, asks to save their work to git, or says "commit this".

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 27, 2026
toolsbashgit

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 27, 2026

npx -y skills add David-Li0406/meta-skill-evloving --skill commit-68 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Commit 68?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Commit 68
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/david-li0406-commit-68/badge)](https://www.skillsdirectory.com/skills/david-li0406-commit-68)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: commit
description: Commit with user prompts from this conversation. Use when user mentions committing, wants to commit changes, asks to save their work to git, or says "commit this".
allowed-tools: Bash, Read
---

# Commit with User Prompts

Create git commits that include the user prompts that led to the changes.

## Instructions

1. **Extract User Prompts**: Collect user messages from this conversation that led to the changes. Include them in chronological order.

2. **Analyze Changes**:
   ```bash
   git status
   git diff --staged
   ```

3. **Get Session Info**:
   ```bash
   uv run {baseDir}/ai-blame.py session-info
   ```

4. **Generate Commit Message**:
   ```
   <brief summary of changes>

   User prompts:
   - "<first user prompt>"
   - "<second user prompt>" (context if prompt is ambiguous)

   AI-Session-ID: <from session-info>
   AI Agent: <from session-info>
   Model: <from session-info>
   ```

5. **Execute Commit**:
   ```bash
   git add -A && git commit -m "$(cat <<'EOF'
   <your commit message here>
   EOF
   )"
   ```

## Rules

- Only include prompts that led to file changes (not `/commit` or meta-discussion)
- Preserve exact wording, add (context) in parentheses if prompt is ambiguous
- Summary line under 50 characters
- Each prompt on a single line, no mid-sentence wrapping

Files in this skill

  • SKILL.md1.3 KB
  • ai-blame.py28.9 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…