commit
$
npx mdskill add microsoft/vscode/commitCommit staged or unstaged code changes using an AI-generated message matching repo style.
- Handles user requests to save work or create a new code snapshot.
- Interacts with the local Git version control system to manage changes.
- Analyzes recent commit history to adopt established message formatting.
- Provides confirmation and executes the final commit operation upon user consent.
SKILL.md
.github/skills/commitView on GitHub ↗
--- name: commit description: Commit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style. Use when the user asks to 'commit', 'commit changes', 'create a commit', 'save my work', or 'check in code'. --- <!-- Customize this skill and select save to override its behavior. Delete that copy to restore the built-in behavior. --> # Commit Changes Help the user commit code changes with a well-crafted commit message derived from the diff, following the conventions already established in the repository. ## Guidelines - **Never amend existing commits** without asking. - **Never force-push or push** without explicit user approval. - **Never skip pre-commit hooks** (do not use `--no-verify`). - **Never skip signing commits** (do not use `--no-gpg-sign`). - **Never revert, reset, or discard user changes** unless the user explicitly asked for that. - Check for obvious secrets or generated artifacts that should not be committed. If something looks risky - ask the user. - When in doubt about staging, convention, or message content — ask the user. ## Workflow ### 1. Discover the repository's commit convention Run the following to sample recent commits and the user's own commits: ``` # Recent repo commits (for overall style) git log --oneline -20 # User's recent commits (for personal style) git log --oneline --author="$(git config user.name)" -10 ``` Analyse the output to determine the commit message convention used in the repository (e.g. Conventional Commits, Gitmoji, ticket-prefixed, free-form). All generated messages **must** follow the detected convention. ### 2. Check repository status ``` git status --short ``` - If there are **no changes** (working tree clean, nothing staged), inform the user and stop. - If there are **staged changes**, proceed with those and do not stage any unstaged changes. - If there are **only unstaged changes**, stage everything (`git add -A`), and proceed with those. ### 3. Generate the commit message Obtain the full diff of what will be committed: ```bash git diff --cached --stat git diff --cached ``` Using the diff and the commit convention detected in step 1, draft a commit message with: - A **subject line** (≤ 72 characters) that summarises the change, following the repository's convention. - An optional **body** that explains *why* the change was made, only when the diff is non-trivial. - Reference issue/ticket numbers when they appear in branch names or related context. - Focus on the intent of the change, not a file-by-file inventory. ### 4. Commit Construct the `git commit` command with the generated message. Execute the commit: ``` git commit -m "<subject>" -m "<body>" ``` ### 5. Confirm After the commit: - Run `git status --short` to confirm the commit completed. - Run `git log --oneline -1` to show the new commit. - If pre-commit hooks changed files or blocked the commit, summarize exactly what happened. - If hooks rewrote files after the commit attempt, do not amend automatically. Tell the user what changed and ask whether they want you to stage and commit those follow-up edits.
More from microsoft/vscode
- accessibilityPrimary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements, keyboard navigation, and ARIA labels/roles.
- act-on-feedbackAct on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.
- add-policyUse when adding, modifying, or reviewing VS Code configuration policies. Covers the full policy lifecycle from registration to export to platform-specific artifacts. Run on ANY change that adds a `policy:` field to a configuration property.
- agent-customization**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized workflows; packaging domain knowledge; fixing YAML frontmatter syntax. DO NOT USE FOR: general coding questions (use default agent); runtime debugging or error diagnosis; MCP server configuration (use MCP docs directly); VS Code extension development. INVOKES: file system tools (read/write customization files), ask-questions tool (interview user for requirements), subagents for codebase exploration. FOR SINGLE OPERATIONS: For quick YAML frontmatter fixes or creating a single file from a known pattern, edit the file directly — no skill needed.
- anthropic-sdk-upgrader"Use this agent when the user needs to upgrade Anthropic SDK packages. This includes: upgrading @anthropic-ai/sdk or @anthropic-ai/claude-agent-sdk to newer versions, migrating between SDK versions, resolving SDK-related dependency conflicts, updating SDK types and interfaces, or asking about SDK upgrade procedures. Examples: 'Upgrade the Anthropic SDK to the latest version', 'Help me migrate to the latest claude-agent-sdk', 'What's the process for upgrading Anthropic packages?'"
- author-contributionsIdentify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.
- auto-perf-optimizeRun agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
- azure-pipelinesUse when validating Azure DevOps pipeline changes for the VS Code build. Covers queueing builds, checking build status, viewing logs, and iterating on pipeline YAML changes without waiting for full CI runs.
- chat-customizations-editorUse when working on the Chat Customizations editor — the management UI for agents, skills, instructions, hooks, prompts, MCP servers, and plugins.
- chat-perfRun chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.