ask-commit-assistance

Ask Commit Assistance

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "ask-commit-assistance" with this command: npx skills add navanithans/agent-skill-kit/navanithans-agent-skill-kit-ask-commit-assistance

Ask Commit Assistance

This skill assists in the "pre-commit" phase: scanning for secrets, reviewing new code, and staging files.

<critical_constraints> ❌ NEVER AUTO-COMMIT: Execution of git commit is strictly forbidden for the agent. ❌ NO git add . → stage specific files only. ❌ NO committing secrets/debug code without explicit user confirmation. ✅ MUST scan for API keys, tokens, passwords before staging. ✅ MUST use Conventional Commits format for suggested messages. ✅ MUST offer detailed and short message options. ✅ USER FINALIZATION: Always provide the final git commit command for the user to execute manually. </critical_constraints>

<safety_scan> Check for:

  • Secrets: API keys, tokens, passwords

  • Debug: print(), console.log(), dd()

  • Markers: TODO, FIXME, HACK → Warn user before staging if found. No automated cleanup unless requested. </safety_scan>

<commit_format> Types: feat, fix, docs, style, refactor, test, chore Format: type(scope): description

Option 1 (detailed): subject + body explaining why/what Option 2 (short): just subject line </commit_format>

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

ask-shadcn-architect

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

ask-nextjs-architect

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

ask-skill-creator

No summary provided by upstream source.

Repository SourceNeeds Review