cp
Commit all current changes, push to a feature branch, and create a PR. Use when the user asks to commit, push, save progress, or ship changes.
Best use case
cp is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Commit all current changes, push to a feature branch, and create a PR. Use when the user asks to commit, push, save progress, or ship changes.
Teams using cp should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/cp/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How cp Compares
| Feature / Agent | cp | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Commit all current changes, push to a feature branch, and create a PR. Use when the user asks to commit, push, save progress, or ship changes.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# commit-and-push (PR workflow) Commit all current changes, push to a feature branch, and open a pull request. All pre-push checks must pass before pushing. ## Instructions 1. **Run pre-push checks with auto-fix** (quiet mode suppresses output on success): ```sh tools/pre-push --fix -q ``` If this fails, fix the issues and re-run until it passes. Do NOT skip this step — it is the project's only gate against broken code. 2. **Check for changes**: ```sh git status git diff --stat git log --oneline -5 ``` 3. **Stage all changes** (including any fixes from step 1): ```sh git add -A ``` 4. **Write a commit message** following the project convention: - Prefix with `synq: ` (lowercase) - Concise summary line describing the "why" - Add detail in the body for non-trivial changes 5. **Commit using a HEREDOC**: ```sh git commit -m "$(cat <<'EOF' synq: <summary> <optional body> EOF )" ``` 6. **Create a feature branch if on main**: If currently on `main`, create and switch to a descriptive branch: ```sh git checkout -b <branch-name> ``` Branch naming: use lowercase kebab-case describing the change (e.g., `add-cte-column-validation`, `fix-fmt-trailing-comma`). No prefixes needed. 7. **Push the branch**: ```sh git push -u origin HEAD ``` 8. **Create a PR** using `gh pr create`: ```sh gh pr create --title "<title>" --body "$(cat <<'EOF' ## Motivation <Why this change is needed — what problem exists, what's missing, what broke> ## Changes <What this PR does to address the motivation> EOF )" ``` - Keep the title under 70 characters, prefixed with `synq: ` - Motivation section: explain the problem/need driving this change - Changes section: describe what you're doing about it 9. **Report the PR URL** to the user.
Related Skills
validate
Validate SQL and report diagnostics using syntaqlite. Use when the user wants to check SQL for errors, lint SQL files, or verify correctness against a schema.
parse
Parse SQL and inspect the AST using syntaqlite. Use when the user wants to see the parse tree, debug SQL syntax, or understand how a query is structured.
format
Format SQL files using the syntaqlite formatter. Use when the user wants to format, reformat, or pretty-print SQL code.
run-tests
Run tests to verify correctness after code changes. Use when the user asks to run tests, verify changes, or check that things still work. Runs Rust unit tests and integration tests.
run-codegen
Regenerate all generated code from .synq definitions and SQLite grammar. Use when .synq files, grammar actions, or dialect definitions have been modified and generated C/Rust code needs updating.
release
Bump version, commit, tag, and create a draft GitHub Release. Use when the user
debug-formatter
Debug a SQL formatter bug. Use when the user reports incorrect formatting output — wrong whitespace, misplaced comments, blank lines, etc.
cpfast
Quickly commit and push current changes to a feature branch and create a PR, skipping pre-push checks. WARNING: if CI starts failing, use /cp instead.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
skill-comply
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines