Menu
Commit Staged Changes
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Version Bump
Generate a changeset file describing the current PR's changes. Use when asked to "create a changeset", "add a changeset", "/changeset", or after implementing a feature/fix that needs a changelog entry. Produces a randomly named `.changeset/*.md` file with affected packages, bump type, and an 80-character-max user-facing summary.
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
Find deepening opportunities in a codebase, informed by the architecture docs in apps/docs/content/docs/developer-docs/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.
Based on SOC occupation classification
| name | commit |
| description | Commit Staged Changes |
| disable-model-invocation | true |
Generate a conventional commit message and commit staged changes, respecting the project's commitlint configuration.
Branch: Commit on the current branch. Do not create or switch to a feature branch unless the user asks (see git-conventions — Current branch (agents)).
Run the single git command from git-conventions to gather all context:
echo "=== BRANCH ===" && git rev-parse --abbrev-ref HEAD && echo "=== STAGED FILES ===" && git diff --staged --stat && echo "=== STAGED CHANGES ===" && git diff --staged
From the gathered information:
Show the generated commit message in a code block:
type(scope): description
Optional body text
Closes #123
Explain the ticket number, type, and scope chosen.
Then execute the commit:
For commits with body:
git commit -m "type(scope): description" -m "Body paragraph" -m "Closes #GITHUB_ISSUE"
For commits without body:
git commit -m "type(scope): description"
After committing, show the commit hash and confirm success.
If the commit fails (e.g., commitlint validation fails):
<type>(<scope>): <subject>Closes #123 is optional but recommended for feat/fix commitsUser: "commit", "commit staged changes", or /commit
Response: