create-pr
Commit the current branch, push it, and open a pull request.
Skill by pabloleonalcaide
Chalk Labs
Need help deploying create-pr?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/pabloleonalcaide-create-pr
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/create-pr
What's inside
- Skill name
create-pr- Description
- Commit the current branch, push it, and open a pull request. Use at the delivery step of a development task, once the work is done and verified. Triggered by "open a PR", "ship this", "create the pull request", or as the delivery step of /develop.
- License
- MIT
- Instructions
- 30 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# create-pr Ship the finished work as a pull request. The branch already exists (created in `develop` phase D). Keep the PR small and readable; the full detail lives in the tracker task. ## Steps 1. **Confirm the branch and diff.** `git status` + `git diff <base>...HEAD`. Never open a PR from the main branch. 2. **Commit** any pending work in atomic commits with clear messages (follow `.context/styling.md` if present). Never silence `git commit` output: a failing pre-commit hook aborts the commit and its error is the only signal. After each commit, check the exit code and that `git log -1 --oneline` shows it; if a hook reformatted files, re-stage and commit again before pushing. 3. **Push** the branch: `git push -u origin HEAD`. 4. **Open the PR** with the tracker's CLI — `gh pr create` for GitHub, `glab mr create` for GitLab (see `docs/agents/issue-tracker.md`): - **Title**: what the change does, imperative mood. - **Body**: what / why + a link to the tracker task. Keep it short — detail lives in the task. If that task has subtasks, link the subtask this change implements, never the parent; ask if it's ambiguous. - **Reviewers / labels / CI**: apply whatever your repo documents in `.context/`. This skill hardcodes none. 5. **Report** the PR URL. 6. **Remove the worktree the PR came from.** If the PR was opened from a linked worktree (not the main one), the branch now lives on origin; bring it back later if more work is needed. Leave the worktree and remove it in one command, so the shell never sits in a deleted directory: ```bash wt="$(git rev-parse --show-toplevel)"; main="$(git worktree list --porcelain | head -1 | cut -d' ' -f2-)" [ "$wt" != "$main" ] && cd "$main" && ~/.claude/skills/disk-cleanup/scripts/worktree-cleanup.sh --remove "$wt" ``` It refuses, changing nothing, if there are uncommitted changes or the branch tip is not on origin — then report why and keep it. Large `node_modules` make this slow: run it in the background. ## Notes - This is the **generic** delivery skill. Anything repo-specific — required reviewers, CI gates, a PR template, protected-branch rules, a branch-naming convention — belongs in your repo's `.context/`, not here. - **Non-analysis branches only.** An `analysis` task produces a report, not a PR.
From pabloleonalcaide/development-skills, MIT.
More from pabloleonalcaide/development-skills
- 0.592score
develop
pabloleonalcaide
Orchestrates any non-trivial development or analysis task end-to-end — discovery, alignment, blueprint, registration, implementation and delivery.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
disk-cleanup
pabloleonalcaide
Reclaim local disk space safely on a development machine — leftover git worktrees, Docker leftovers from integration tests (Testcontainers containers, orphan…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
api-design
pabloleonalcaide
Design stable public interfaces — HTTP endpoints, event payloads, module boundaries, SDK-style ports — and make retried operations safe with idempotency keys.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
deprecation
pabloleonalcaide
Retire code, endpoints, fields, flags and dependencies safely, and migrate data without downtime using expand/contract.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
observability
pabloleonalcaide
Instrument code so production behavior is visible and diagnosable — structured logs with correlation ids, metrics, traces, symptom-based alerts and minimal…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
security-hardening
pabloleonalcaide
Threat-model a change and harden it before it ships — trust boundaries, authn/authz, input validation, secrets, SSRF, destructive operations, rate limits and…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
setup
pabloleonalcaide
Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub by default, or…
SkillAFreshness: A★ 1Claude Code +9 - 0.567score
diagnose
pabloleonalcaide
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
receiving-code-review
pabloleonalcaide
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires…
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
grilling
pabloleonalcaide
Grill the user relentlessly about a plan or design until shared understanding — interview one decision at a time, no code until confirmed.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
tdd
pabloleonalcaide
Test-driven development with red-green-refactor loop.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
write-a-skill
pabloleonalcaide
Create new agent skills with proper structure, progressive disclosure, and bundled resources.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from pabloleonalcaide
- 0.592score
disk-cleanup
pabloleonalcaide
Reclaim local disk space safely on a development machine — leftover git worktrees, Docker leftovers from integration tests (Testcontainers containers, orphan…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
develop
pabloleonalcaide
Orchestrates any non-trivial development or analysis task end-to-end — discovery, alignment, blueprint, registration, implementation and delivery.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
observability
pabloleonalcaide
Instrument code so production behavior is visible and diagnosable — structured logs with correlation ids, metrics, traces, symptom-based alerts and minimal…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
deprecation
pabloleonalcaide
Retire code, endpoints, fields, flags and dependencies safely, and migrate data without downtime using expand/contract.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
api-design
pabloleonalcaide
Design stable public interfaces — HTTP endpoints, event payloads, module boundaries, SDK-style ports — and make retried operations safe with idempotency keys.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
security-hardening
pabloleonalcaide
Threat-model a change and harden it before it ships — trust boundaries, authn/authz, input validation, secrets, SSRF, destructive operations, rate limits and…
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get create-pr running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
create-pr skill. Agent Mart. https://agentmart.dev/skills/pabloleonalcaide-create-pr (last updated 2026-10-24)