Stage, commit, and push changes to the current branch. Use when asked to commit, push, or create a commit for the current task.
Scanned 9/8/2026
Install to Claude Code
npx -y skills add bg-szy/TOP-SKILLS --skill commit --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Commit?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/bg-szy-commit)More formats (shields.io, HTML) on the badges page.
---
name: commit
description: Stage, commit, and push changes to the current branch. Use when asked to commit, push, or create a commit for the current task.
---
# Commit and Push Skill
1. Stage only files related to the current task
2. Run `git commit --no-verify` if pre-commit hooks fail on unrelated issues
3. Push to the current branch
4. Report the commit hash and branch name
NOTE: This repo uses Azure DevOps. For PRs use `az repos pr create`.
NOTE: The `commit-msg` hook strips `Co-Authored-By` trailers so commits appear as sole-author.
---
## Gotchas
- **`git commit --no-verify` bypasses pre-commit hook** — logged in reflog but easy to forget. A CI check that fails on no-verify trailers prevents drift.
- **`commit-msg` hook transforms the message AFTER the editor closes** — verify the final state with `git show -s --format=%B`, not the editor draft.
- **Azure DevOps strips `Co-Authored-By` server-side** — local commits show co-author; PR display doesn't. Test what shows in the PR UI before assuming attribution worked.
- **`git commit` on a detached HEAD creates an orphan** — `git checkout main` loses it unless you branch first. Reflog recovers but only for 30 days.
- **Trailing whitespace in commit messages**: some hooks normalize, some preserve. Format-checks comparing raw vs normalized fail confusingly.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling