commit
Create atomic git commits with a secrets/artifact safety check, green tests, and explicit human approval per commit.
Skill by smlfg
Chalk Labs
Need help deploying commit?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/smlfg-commit
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/commit
What's inside
- Skill name
commit- Description
- Create atomic git commits with a secrets/artifact safety check, green tests, and explicit human approval per commit. Use when the user asks to commit current changes.
- License
- MIT
- Instructions
- 52 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Commit ## Setup 1. `git status`. If the tree is clean, say so and stop. 2. `git diff --stat` to understand the scope of changes. ## Safety check (before staging anything) Scan changed files for `.env`, `*credentials*`, `*secret*`, `*.db`, `*.pyc`, `__pycache__/`, `.venv/`. - Warn the user and refuse to stage these files. - If `.gitignore` is missing entries for found artifacts, suggest adding them first. ## Plan atomic commits Group changed files by logical change. One logical change = one commit. Ask the user whether the grouping looks right before proceeding. ## For each atomic commit 1. Stage only the files for this change. Never `git add -A` blindly. 2. Run the tests (`pytest`, `npm test`, or whatever the project uses). If red: **stop**, show the failure, do not proceed until fixed. 3. Draft a message: `type(scope): description`, max 72 chars, types `feat|fix|refactor|docs|test|chore`, in English, explaining *why* rather than *what*. 4. Show the user the staged files and the proposed message. 5. Wait for explicit approval. "Looks good" counts; silence does not. ## After approval Commit with the approved message, then continue with the next atomic commit. When all are done, show `git log --oneline -5`. ## Hard rules - Never push without explicit approval. - Never commit on red tests. - Never `git add -A` / `git add .` without reviewing what is included. - The user decides when to commit. Never commit preemptively. ## Example ```text Proposed commit 1/2 staged: src/parser.py, tests/test_parser.py message: fix(parser): accept trailing commas so exported configs round-trip tests: 48 passed Approve? (yes / edit / skip) ``` ## Use case You finished a messy afternoon session touching a parser, docs and a stray `.env`. Run `/commit`: the agent refuses the `.env`, proposes two commits (fix + docs), runs tests before each, and only commits after you say yes.
From smlfg/HAI-skills-registry, MIT.
More from smlfg/HAI-skills-registry
- 0.570score
pdf-to-md
smlfg
Convert PDFs (lecture slides, scripts, books) into clean Markdown/text an agent can read and search, with automatic fallback to Tesseract OCR for scanned PDFs.
SkillAFreshness: AClaude Code +9 - 0.570score
archify-swarm
smlfg
Map a repository's architecture with several cheap/free models in parallel, verify every claimed file:line deterministically against the committed code, and…
SkillAFreshness: AClaude Code +9 - 0.565score
agentic-gate-verification
smlfg
Decide whether agentic work may proceed, be marked done, merge, or spawn more work.
SkillAFreshness: AClaude Code +9 - 0.565score
cross-model-review
smlfg
Get independent second, third and fourth opinions from different model families on a problem or solution, then synthesise convergence (validated) versus…
SkillAFreshness: AClaude Code +9 - 0.565score
experiment-to-project
smlfg
Turn an AI/agent experiment with several failed or half-working attempts into an evaluated, measurable project.
SkillAFreshness: AClaude Code +9 - 0.565score
github-community-checklist
smlfg
Audit a GitHub repo's community health files (description, README, license, code of conduct, contributing, security policy, issue/PR templates).
SkillAFreshness: AClaude Code +9 - 0.565score
skilleval
smlfg
Run the same task through several models or agents and score the artifacts against a pre-agreed, machine-checkable quality axis.
SkillAFreshness: AClaude Code +9 - 0.565score
subprocess-cli-pitfalls
smlfg
Diagnose Linux CLI commands that run in milliseconds in a terminal but hang or crawl when called via Python subprocess (or any non-TTY caller like cron or an…
SkillAFreshness: AClaude Code +9 - 0.565score
coursepack
smlfg
Push an entire course folder into Google NotebookLM and generate prioritised study media (audio, video, study guide) per topic and per exercise sheet, driven…
SkillAFreshness: AClaude Code +9 - 0.565score
podcast
smlfg
Produce an audio podcast from source material (doc, text, link, topic) via Google NotebookLM's MCP server.
SkillAFreshness: AClaude Code +9 - 0.565score
spoiler-free-shorts
smlfg
Add a short (60–90 s) NotebookLM video to each task of an existing interactive learning page, using a parallel example so the short never solves the task…
SkillAFreshness: AClaude Code +9 - 0.565score
visual-explainer
smlfg
Generate self-contained HTML explainers with SVG diagrams and interactive step-by-step animations for algorithms, data structures, systems or concepts.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 15, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/smlfg/HAI-skills-registry
- Website
- human-agent-interface.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from smlfg
- 0.606score
HAI-MCP
smlfg
Model-agnostic MCP control plane for HAI: bounded missions, owner-gated actions, drift checks.
ConnectorAFreshness: ALocal★ 1↓ 47/wkClaude Code +5 - 0.570score
archify-swarm
smlfg
Map a repository's architecture with several cheap/free models in parallel, verify every claimed file:line deterministically against the committed code, and…
SkillAFreshness: AClaude Code +9 - 0.570score
pdf-to-md
smlfg
Convert PDFs (lecture slides, scripts, books) into clean Markdown/text an agent can read and search, with automatic fallback to Tesseract OCR for scanned PDFs.
SkillAFreshness: AClaude Code +9 - 0.565score
automation-handover
smlfg
Hand a verified automation over to its users with a short explanation, a visible demo through the real UI, a demonstrated stop path, and one small user action…
SkillAFreshness: AClaude Code +9 - 0.565score
cross-model-review
smlfg
Get independent second, third and fourth opinions from different model families on a problem or solution, then synthesise convergence (validated) versus…
SkillAFreshness: AClaude Code +9 - 0.565score
agentic-gate-verification
smlfg
Decide whether agentic work may proceed, be marked done, merge, or spawn more work.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get commit running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
commit skill. Agent Mart. https://agentmart.dev/skills/smlfg-commit (last updated 2026-10-24)