Slash command index

~ /Slash Commands

01 — index

Tested prompts for the jobs you repeat every day: /commit, /review, /fix-tests, /a11y. Built for frontend JS/TS projects. Each one detects your tooling, says what it may touch, and asks before anything risky. The same prompt works in Cursor, Claude Code, GitHub Copilot, Codex CLI, Antigravity, and OpenCode.

  • 22 commands
  • 6 agents
  • a safety tier on every command
  1. 01

    Pick your agent

    Choose it once in the install for bar. Your choice is remembered.

  2. 02

    Install a command

    One click opens Cursor. For other agents, one paste in your terminal.

  3. 03

    Type the slash

    Run /commit in chat. It does that one job, only when you ask.

22 commands

/commit-push-prgit

Commit, Push & PR

Commit changes, push a feature branch, and open a GitHub pull request.

/create-prgit

Create Pull Request

Push the current feature branch and open a GitHub pull request from existing commits.

/groom-github-prgit

Groom GitHub PR

Rebase, squash commits, and refresh a GitHub PR title and description to match the latest diff.

/fix-merge-conflictsgit

Resolve Merge Conflict

Three-way merge reasoning for Cursor's Resolve in Chat. Proposes each resolution before applying it.

/changelogread-only

Write Changelog

Draft release notes or a CHANGELOG entry from commits since the last tag, grouped by type. Text only.

/commitread-only

Write Commit Message

Write a Conventional Commit message from the current diff. Text only — you commit.

/pr-descriptionread-only

Write PR Description

Generate or refresh a GitHub PR title and description from the branch diff — no rebase or squash.

/yologit

YOLO Deploy

Commit and push on the current branch — fast path for personal projects.

/a11yread-only

Accessibility Audit

Audit components for accessibility — semantics, labels, keyboard, focus, ARIA — and propose fixes without applying them.

/debugread-only

Debug a Bug

Find the root cause of a bug before touching the fix — reproduce, hypothesize, test, and report. No guess-and-patch.

/fix-testsscoped edit

Fix Failing Tests

Run the project's JS/TS test suite, diagnose failures, and fix them until green.

/lintscoped edit

Fix Lint Errors

Fix JS/TS linting and formatting issues without changing behavior.

/fix-typesscoped edit

Fix Type Errors

Run the TypeScript compiler and fix type errors properly — no any, no @ts-ignore, no non-null shortcuts.

/deslopbroad edit

Remove AI Code Slop

Strip AI slop from your branch — stray comments, needless try/catch, any-casts — and match the file's style.

/reviewread-only

Review Branch

Review your branch diff like a senior teammate — bugs, security, performance, then style, each with file:line. Report only.

/write-testsbroad edit

Write Tests

Write tests for the selected code using your project's test runner and conventions. Plans the cases first.

/typescriptscoped edit

Convert to TypeScript

Convert JavaScript to TypeScript with real types, matching your tsconfig strictness.

/modernize-jsscoped edit

Modernize JavaScript

Rewrite code with modern JavaScript APIs from current Node.js LTS and baseline 2023 browsers.

/audit-depsread-only

Audit Dependencies

Run a security audit on your JS/TS dependencies and triage findings by real exposure. Suggests fixes, applies nothing.

/faviconbroad edit

Generate Favicons

Generate a complete favicon set and web manifest from one source image.

/dead-codebroad edit

Remove Dead Code

Find unused files, exports, and dependencies with Knip, then remove only what you approve.

/update-depsbroad edit

Update Dependencies

Update JS/TS dependencies within current semver ranges using the detected package manager.

Slash commands in a world of skills

Agents ship more skills every month: capabilities the model decides when to use. A slash command is the opposite. You pick the exact prompt, and it runs only when you type it.

01

You decide when

The model never guesses whether to run it. Type /commit and you get a commit message. Nothing fires in the background.

02

Same prompt, every agent

The same prompt works in Cursor, Claude Code, GitHub Copilot, Codex CLI, Antigravity, and OpenCode, whatever built-in skills each one ships.

03

Scoped, predictable output

Each command does one job and ends with a defined output: a commit message, a review with file:line findings, a list of what changed.

Every command says what it may touch

Each prompt has a Safety section that sets its limits. It asks before sensitive actions like committing, pushing, or overwriting files. The badge on each card shows the tier.

read-only
Reads your code and prints text. Never edits files or runs git writes.
scoped edit
Edits only the selection or paths you name. Asks first if scope is unclear.
broad edit
Plans first and asks before overwriting files or touching many of them.
git
Commits, pushes, or rewrites history. Running it is your approval.

Which git command do I need?

The git commands overlap on purpose: each fits a different moment between "I changed some files" and "it's merged". Find your situation and run that one.

I want a commit message, and I'll commit myself
/commitText only. Same idea as the sparkle button in Cursor's commit box.
Uncommitted changes on a team repo, and I want a PR
/commit-push-prBranches off the default branch if needed, commits, pushes, and opens the PR.
Already committed, no PR yet
/create-prPushes the branch and opens a PR from the existing commits.
PR is open, but the description is stale
/pr-descriptionDrafts a new title and body from the full diff. Applies only if you ask.
PR is open, and history is messy or behind the base branch
/groom-github-prRebases, squashes, and refreshes the PR after you approve the plan.
Personal project, just ship it
/yoloCommits and pushes on the current branch, even main. Not for shared repos.
A merge or rebase stopped with conflicts
/fix-merge-conflictsProposes each resolution as a diff before applying it.

Questions, answered

What is a slash command?

A Markdown file of instructions saved where your agent looks for commands or skills. Type /name in chat, or $name in Codex CLI, and the agent runs that prompt. Our install commands turn off automatic use wherever the agent supports it. Antigravity has no documented way to do that, so it can also pick up a command on its own when a task matches.

Where does the command file go?

Cursor: .cursor/commands/ in your project (the install button does this for you). Claude Code: ~/.claude/commands/, or .claude/commands/ in a project to share it with your team. OpenCode: ~/.config/opencode/commands/, or .opencode/commands/ in a project. GitHub Copilot, Codex CLI, and Antigravity load commands as skills, so each one gets a folder with a SKILL.md. GitHub Copilot: .github/skills/ in your project. Codex CLI: ~/.agents/skills/, run as $name. Antigravity: .agents/skills/ in your project.

A command I installed earlier stopped working. How do I fix it?

Codex CLI and Antigravity retired the formats we used to install, so files in ~/.codex/prompts/ and .agent/workflows/ no longer load. Install the command again from this page to get the skill version, then delete the old file. In Codex CLI, you now run it as $name instead of /prompts:name. Antigravity's /migrate-workflows documents scanning .agents/workflows/, not the older .agent/workflows/, so installing again is the reliable fix.

How do I pass arguments?

Type them after the command, like /favicon assets/logo.svg. Claude Code substitutes $1, $2, and $ARGUMENTS in the file, and OpenCode substitutes $ARGUMENTS. Other agents pass what you typed after the command along with the prompt, so commands here also ask for missing input.

Can I edit a command after installing it?

Yes. It's a plain Markdown file. Add your project's conventions, remove steps you don't need, or change the output format. Commit project-level commands so your whole team gets the same version.

Slash commands, skills, or rules: which should I use?

Use a slash command for a task you trigger on purpose: commit, review, fix tests. Use a skill for know-how the agent should apply on its own when a task calls for it, like React performance rules. Use rules (.cursor/rules, AGENTS.md, CLAUDE.md) for context that should apply to every request.

What do the safety tiers actually guarantee?

Each tier is a set of instructions the agent follows: what it may edit, and when it must stop and ask. They are not a sandbox. Keep your agent's own approval settings for terminal commands and file edits turned on, and review diffs before you commit.

Suggest a command.

Is there a prompt you paste into chat every day? Send it over, along with the job it does and what it should never touch. The good ones get a safety tier and a place in this index.

Copied to clipboard!