Agent skill

PR Etiquette

by overmind-core in overmind-core/overmind

How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here…

AGPL-3.0Auto-check passedDevelopment

Install PR Etiquette

skills CLI
$ npx skills add overmind-core/overmind --skill pr-etiquette -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install overmind-core/overmind pr-etiquette --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pr-etiquette .claude/skills/pr-etiquette && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pr-etiquette
GitHub stars
597
Token cost
~1.5k tokens
SKILL.md length
731 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
AGPL-3.0

At a glance

How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here…

  • Works in 3 steps: MCP → Cross-vertical blast radius → Docs
  • Editing a PR title
  • SKILL.md covers Before you push — what CI will…, Completeness — the surfaces a…, Creating and Editing title/body — gh pr…, plus 1 more section
  • Calls make, gh and uv

What it does

PR Etiquette is an agent skill from overmind-core/overmind. How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here, and body conventions. Use when opening a PR, editing a PR title or body, or pushing branch work for review.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests. It works with Model Context Protocol. The repository describes itself as: The platform for continuously improving AI agents. The licence is AGPL-3.0.

When your agent uses it

  • Editing a PR title
  • Pushing branch work for review

Example prompts

  • “/pr-etiquette”

Requirements

  • Python 3
  • Docker

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. MCP
  2. Cross-vertical blast radius
  3. Docs

What it can do on your machine

Read from SKILL.md and the folder at commit 3dec73c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • make
    • gh
    • uv
    • bun
    • git
    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, uv and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

PR Etiquette loads about 1.5k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 731 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from overmind-core/overmind at commit 3dec73c, republished under its AGPL-3.0 licence (© overmind-core). 731 words, ~1,546 tokens.

Download SKILL.mdSave it as .claude/skills/pr-etiquette/SKILL.md (or your agent's skills folder).
name
pr-etiquette
description
How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here, and body conventions. Use when opening a PR, editing a PR title or body, or pushing branch work for review.

Pull requests on overmind-core/overmind

Before you push — what CI will run

.github/workflows/ci.yml runs four jobs on every non-draft PR. Run the equivalents locally rather than discovering them in CI:

CI jobWhat it runsLocal equivalent
lintuv run ruff check . and uv run ruff format --check .make lint-backend
frontendbun run check, bun run typecheck, bun run check:all, bun run test — in parallel, all must passsame four, from frontend/
testuv run pytest tests/ -n auto --dist worksteal -qmake test
migrationsmakemigrations --check on the merge commit plus scripts/check_migrations.py; only when overbae/models/ or overbae/migrations/ changedmake check-migrations

pre-commit run --files <changed files> before committing substantial work. Note that mdformat reflows markdown, so commit its output rather than fighting it.

SDK changes: bump the bundled release

Any change under overmind/, including bundled skills or documentation, triggers the SDK version gate. Bump overmind/pyproject.toml above the version on the PR's base branch, match overmind/overmind/__init__.py, and regenerate overmind/uv.lock with uv lock --project overmind. Verify the versions agree before pushing. The root uv.lock pins the platform's installed SDK dependency; do not change it to an unpublished local release. The merge publishes the bumped version to PyPI (sdk-publish.yml runs on every push to main that touches overmind/).

Migrations: rebase before you push

make test runs --nomigrations, so a stale branch passes locally and forks the migration graph on main. Main moves fast; a branch that touched a model is usually behind by the time it is ready. Before pushing a model change:

  1. git fetch origin && git rebase origin/main.
  2. If main gained migrations, delete yours and regenerate it: makemigrations picks the next number and depends on main's newest leaf.
  3. make check-migrations — the exact CI check, against origin/main.

Never resolve a fork with makemigrations --merge. A _merge_ file or a reused number fails the migrations job; renumber instead.

Completeness — the surfaces a PR must carry with it

CI cannot catch these. Every one of them has shipped half-done before, so walk the list before opening the PR and say in the body which ones applied.

1. MCP

MCP is the agent API, with the same completeness bar as the Console. Walk the mcp skill: classify the change (MCP-ready / CLI-guided / frontend-only / out of scope), then tools, resources, prompts, contracts, and tests in overbae/services/mcp/ and tests/test_mcp_*.py. Update the user-facing Overmind skill (overmind/skills/overmind/) when the public catalog, prompts, or resources change. A Console-only vertical change that an agent should be able to progress is not complete. The mcp skill itself lives in .agents/skills/mcp/ and must not be copied into overmind/skills/.

Show full SKILL.md (306 more words)Show less
2. Cross-vertical blast radius

Ask what else reads what you changed, and check each one that does:

  • Celery routing in CELERY_TASK_ROUTES, make worker, and docker-compose — tests/test_celery_topology.py enforces the three agreeing
  • manage.py seed_demo — new tables and states must seed, and must stay terminal (seed-demo-data skill)
  • the generated OpenAPI client (api-endpoints skill)
  • AGENTS.md and any skill whose statements the change makes untrue
3. Docs

User-visible behaviour changes ship with a docs change in the sibling repo overmind-core/docs (Mintlify, checked out at ../docs): the relevant .mdx page, plus docs.json if the navigation moves. Open that PR alongside this one and link the two. A platform PR that changes what a user sees is not complete while the docs still describe the old behaviour.

Creating

gh pr create --body-file <file> works normally. Write the body to a temp file in the scratchpad, never inline via --body (quoting breaks on long bodies). Fill in .github/PULL_REQUEST_TEMPLATE.md — the Verification section takes the commands you actually ran, not the ones you would run.

Editing title/body — gh pr edit is BROKEN

gh pr edit <n> --title/--body-file aborts on this repo with a Projects-classic GraphQL deprecation error (repository.pullRequest.projectCards) and exits looking like it worked. The PR is left unchanged.

Use REST instead:

bash
python3 -c "import json;print(json.dumps({'title':'<title>','body':open('pr.md').read()}))" > pr.json
gh api -X PATCH repos/overmind-core/overmind/pulls/<n> --input pr.json --jq .title

Always re-read the PR afterwards (gh pr view <n>) to confirm the edit landed.

Conventions

  • Never push directly to main; land work via a PR from a feature branch. A hook blocks the push.
  • Verify the actual current branch with git status -sb before pushing — the session-start banner can be stale.
  • Commit messages: short subject + at most one body line. No co-author trailers.
  • For fix-sweep PRs, a before/after table in the body is the house style (see PR #458/#460 for the shape).
  • If the change makes AGENTS.md or a skill wrong, fix it in the same PR. There is one copy of each rule.

© overmind-core, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/pr-etiquette of overmind-core/overmind.

Open the folder on GitHubat commit 3dec73c

Compare with similar skills

PR Etiquette next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

PR Etiquette compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PR Etiquette this skillovermind-core/overmind597—~1.5kAutomated safety check: PassAGPL-3.0
Plane Release Notes Generatormakeplane/plane61k—~2.5kAutomated safety check: PassAGPL-3.0
Review PRPrefectHQ/fastmcp28k—~3.1kAutomated safety check: PassApache-2.0
ObservalObserval/Observal4.2k—~2.2kAutomated safety check: PassApache-2.0
Rocketmq Rust PR Submittermxsm/rocketmq-rust1.5k—~1.4kAutomated safety check: PassApache-2.0
PR Bot Reviewspgplex/pgconsole155—~2.1kAutomated safety check: PassApache-2.0

Similar skills

  • Builds categorized release notes for a Plane release pull request from its commits and writes them into the PR description, for both the plane-cloud and plane-ee repos.

    61k GitHub stars~2.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Review PR

    PrefectHQ/fastmcp

    Assess a FastMCP pull request for justified behavior, compatibility, and correctness, then follow CI and review feedback to a revision-specific verdict.

    28k GitHub stars~3.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Observal

    Observal/Observal

    A skill your agent uses when starting any task the organization may already have an approved skill, prompt, MCP server, or Agent for: reviewing code, a commit, a diff, or a pull request; writing…

    4.2k GitHub stars~2.2k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Rocketmq Rust PR Submitter

    mxsm/rocketmq-rust

    A skill your agent uses when the user asks to prepare, submit, publish, or optimize a pull request for the rocketmq-rust project, especially when the PR title or commit message must follow the [ISSUE

    1.5k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • PR Bot Reviews

    pgplex/pgconsole

    Triage, verdict, and reply to automated PR review comments from GitHub Copilot and Greptile, then iterate until the bots have nothing left to say.

    155 GitHub stars~2.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Mariadb Operator PR Review

    mariadb-operator/mariadb-operator

    Perform a structured maintainer-style PR review for the mariadb-operator repository.

    1k GitHub stars~3.3k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from overmind-core/overmind

All 20 skills in this repo
  • API Endpoints

    overmind-core/overmind

    End-to-end workflow for adding or changing a backend API endpoint — which module the serializer and view belong in, URL registration, OpenAPI client regeneration, and typed consumption from the…

    597 GitHub stars~830 tokensUpdated yesterday
    Auto-check: notes
  • Finetuning Model Onboarding

    overmind-core/overmind

    Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in…

    597 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed
  • Frontend Design

    overmind-core/overmind

    Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts.

    597 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • MCP

    overmind-core/overmind

    End-to-end workflow for adding or changing Overmind MCP tools, resources, prompts, authentication, or result contracts — server layers, catalog registration, MCP-impact classification, and required…

    597 GitHub stars~4.3k tokensUpdated yesterday
    Auto-check passed
  • Seed Demo Data

    overmind-core/overmind

    Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows.

    597 GitHub stars~973 tokensUpdated yesterday
    Auto-check passed
  • Overmind Agent

    overmind-core/overmind

    Inspect an Overmind project's agent map, capabilities, behaviour contracts, repository provenance and evaluation coverage.

    597 GitHub stars~797 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about PR Etiquette

What does PR Etiquette do?

How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here…. PR Etiquette is an agent skill from overmind-core/overmind. How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here, and body conventions.

When should I use PR Etiquette?

PR Etiquette fits situations like: editing a PR title; pushing branch work for review.

How do I install PR Etiquette in Claude Code?

Run `npx skills add overmind-core/overmind --skill pr-etiquette -a claude-code`. Or copy the skill folder (.agents/skills/pr-etiquette in overmind-core/overmind) into .claude/skills/pr-etiquette in your project. Claude Code loads it when a task matches its description.

How do I install PR Etiquette in Codex?

Run `npx skills add overmind-core/overmind --skill pr-etiquette -a codex`. Or copy the skill folder (.agents/skills/pr-etiquette in overmind-core/overmind) into .agents/skills/pr-etiquette in your project. Codex loads it when a task matches its description.

Can I use PR Etiquette in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add overmind-core/overmind --skill pr-etiquette -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-etiquette, .gemini/skills/pr-etiquette, .github/skills/pr-etiquette and .opencode/skills/pr-etiquette in your project.

What does PR Etiquette need to run?

Going by SKILL.md and its folder, PR Etiquette needs the command-line tools its instructions call (make, gh, uv, bun, git and python3). Our summary lists: Python 3; Docker.

Does PR Etiquette access the network?

SKILL.md contains no URLs. Its commands use gh, uv and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is PR Etiquette safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does PR Etiquette use?

PR Etiquette is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does PR Etiquette use?

About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to PR Etiquette?

Skills that share tags, products or a category with PR Etiquette: Plane Release Notes Generator (makeplane/plane, 61k stars), Review PR (PrefectHQ/fastmcp, 28k stars), Observal (Observal/Observal, 4.2k stars) and Rocketmq Rust PR Submitter (mxsm/rocketmq-rust, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR Etiquette?

overmind-core (a GitHub organization) maintains it in overmind-core/overmind, which has 597 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.

Source: overmind-core/overmind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.