New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pull Request

by basicmachines-co in basicmachines-co/basic-memory

Drive GitHub pull request work end to end. An agent skill from basicmachines-co/basic-memory.

AGPL-3.0Auto-check passedDevelopment

Install Pull Request

skills CLI
$ npx skills add basicmachines-co/basic-memory --skill pull-request -a claude-code

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

GitHub CLI
$ gh skill install basicmachines-co/basic-memory pull-request --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/basicmachines-co/basic-memory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pull-request .claude/skills/pull-request && 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
pull-request
GitHub stars
4.1k
Token cost
~1.7k tokens
SKILL.md length
916 words
Files
1
Skills in repo
49
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Drive GitHub pull request work end to end. An agent skill from basicmachines-co/basic-memory.

  • Works in 6 steps: Inspect the live artifact first. → Keep branch scope clean. → Implement and validate. → …
  • Codex is asked to open
  • SKILL.md covers Runtime Setup, Flow, Scope Discipline and PR Description Standard, plus 2 more sections
  • Calls python, gh and just

What it does

Pull Request is an agent skill from basicmachines-co/basic-memory. Drive GitHub pull request work end to end. Use when Codex is asked to open, update, describe, push to, monitor, review, address comments on, declare ready, or merge a PR. Covers branch hygiene, PR descriptions with why/what/testing/risk, CI checks, Codex review-loop monitoring, comment handling, and the final merge gate.

Its SKILL.md is about 1.7k 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 GitHub and Python. The repository describes itself as: AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN. The licence is AGPL-3.0.

When your agent uses it

  • Codex is asked to open
  • Address comments on

Example prompts

  • “/pull-request”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Inspect the live artifact first.
  2. Keep branch scope clean.
  3. Implement and validate.
  4. Write or update the PR description.
  5. Open or update the PR.
  6. Enter the review loop immediately.

What it can do on your machine

Read from SKILL.md and the folder at commit cb7407f. 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:

    • python
    • gh
    • just
    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use gh and uv, 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

Pull Request loads about 1.7k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 916 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 basicmachines-co/basic-memory at commit cb7407f, republished under its AGPL-3.0 licence (© basicmachines-co). 916 words, ~1,696 tokens.

Download SKILL.mdSave it as .claude/skills/pull-request/SKILL.md (or your agent's skills folder).
name
pull-request
description
Drive GitHub pull request work end to end. Use when Codex is asked to open, update, describe, push to, monitor, review, address comments on, declare ready, or merge a PR. Covers branch hygiene, PR descriptions with why/what/testing/risk, CI checks, Codex review-loop monitoring, comment handling, and the final merge gate.

Pull Request

Use this skill for the whole PR lifecycle, not only the moment of opening or merging.

Runtime Setup

For Basic Memory Python tooling, use the project environment first:

bash
source .venv/bin/activate

After activation, run Python scripts as python .... For one-off commands where activation is awkward, prefer ./.venv/bin/python ... or the repo's uv run ... patterns. Do not fall back to system python, python3, or global packages just because a command is missing.

Flow

  1. Inspect the live artifact first.

    • Use gh pr view, gh issue view, linked review comments, CI status, and current branch state before deciding what to change.
    • If the user links a specific PR discussion, inspect that exact discussion before broad edits.

  2. Keep branch scope clean.

    • Base product-fix PRs on the intended remote base.
    • Avoid mixing workflow/skill/doc commits into unrelated product branches.
    • In basic-memory, prefer local branches in the main workspace unless the user asks for a worktree.

  3. Implement and validate.

    • Read files fully before editing.
    • Make the smallest behaviorally complete change.
    • Run focused tests for the changed surface.
    • Run the repo's required gate, such as just fast-check for source changes or just package-check for agent/package changes, before calling the branch ready.

  4. Write or update the PR description.

    • A PR without a useful description is not done.
    • Use the existing pr-description skill when available.
    • Make the body explain the change to a reviewer who did not watch the chat.

  5. Open or update the PR.

    • Include linked issues, review comments, or specs.
    • Include exact validation commands and outcomes.
    • Mark draft only when the PR is intentionally not ready for review.

  6. Enter the review loop immediately.

    • Use pr-review-loop after opening, pushing, updating the PR body in a meaningful way, or when the user asks whether the PR is ready.
    • Do not treat PR creation as the end of the task when the user expects review follow-through.

Scope Discipline

Codex feedback is adversarial input, not authority to redefine the pull request. Before changing code for a review finding:

  1. Restate the PR's Why, acceptance criteria, and behavior being protected.
  2. Trace or reproduce the concrete failure against the current head.
  3. Classify the finding:
    • In-scope blocker: any regression introduced by the branch, or a direct violation of the stated behavior, acceptance criteria, security boundary, data integrity, or a required check. Fix it in the current PR.
    • Sidequest / gold-plating: speculative hardening, a broader concurrency model, unrelated cleanup, a new abstraction, or an improvement that is not required for the stated outcome. Push back with evidence and keep it out of the branch.
    • Fast follow: a real and material concern that deserves work but is separable from the current outcome. Keep the current PR focused and track it independently.

Narrow PR wording never makes a branch-introduced regression a fast follow. Treat every regression caused by the current branch as an in-scope blocker, even when the Why or acceptance criteria omitted the affected behavior.

Do not accept a P1, P2, or other severity label at face value. Severity must follow from a reproducible impact and the product contract. In particular, do not add locks, leases, retries, migrations, or generalized frameworks merely to close every theoretical interleaving when the documented behavior permits eventual consistency.

For out-of-scope feedback, reply on the review thread with the scope boundary and supporting evidence. If the concern is independently critical or otherwise worth scheduling, open a fast-follow issue when the user has already authorized issue creation; otherwise provide the proposed issue title/body and ask. Link the PR and review comment, state the concrete impact, and give the follow-up its own acceptance criteria. Do not mix the follow-up implementation into the current product branch.

Show full SKILL.md (310 more words)Show less

PR Description Standard

Every PR body should include these ideas, using headings that fit the repo's style:

  • Why: the problem, reviewer comment, issue, incident, user need, or spec requirement that makes the change necessary now.
  • What Changed: the concrete behavior or files changed, in reviewer-friendly language.
  • Implementation Details: important design choices, constraints, tradeoffs, data-flow changes, or why a simpler-looking alternative was avoided.
  • Testing: exact commands run and whether they passed. If something relevant was not tested, say so.
  • Risks / Follow-ups: remaining uncertainty, rollout concerns, known deferred work, or why there are none.

Avoid PR bodies that only restate commit messages. Prefer a short but complete explanation over a long changelog.

Codex Review Loop

Apply pr-review-loop as part of normal PR work:

  • After opening a ready PR, check Codex state and CI.
  • If Codex shows eyes, keep monitoring; eyes is pending, not approval.
  • If Codex leaves feedback, classify its scope immediately while tests continue when possible.
  • If the feedback is correct and in scope, patch, run focused validation, push, and restart the loop on the new head.
  • If the feedback is wrong, speculative, gold-plating, or out of scope, push back with evidence, resolve the thread after replying, and keep the loop moving.
  • If a separate concern is critical, create or propose a fast-follow issue instead of expanding the current PR.
  • The loop completes only when required checks pass and Codex has approved the latest head with a thumbs-up, unless the user explicitly overrides the gate.

Do not merge, declare merge-ready, or move on as though finished until the loop state is explicit:

text
Codex gate: approved | waiting | blocking | overridden
Head: <sha>
Tests: passing | pending | failing
Evidence: <thumbs-up reaction, blocking comment URL, reply URL, or explicit user override>

Merge Discipline

Before merging:

  • Confirm latest head SHA.
  • Confirm required checks are passing on that head.
  • Confirm no current-head Codex comments remain unaddressed.
  • Confirm Codex thumbs-up or explicit user override.
  • Ask or wait for the user's merge instruction unless they already gave it.

Never merge from green CI alone.

© basicmachines-co, 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/pull-request of basicmachines-co/basic-memory.

Open the folder on GitHubat commit cb7407f

Compare with similar skills

Pull Request 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.

Pull Request compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pull Request this skillbasicmachines-co/basic-memory4.1k—~1.7kAutomated safety check: PassAGPL-3.0
Create Cuda Python Pull RequestNVIDIA/cuda-python3.4k—~1.1kAutomated safety check: PassApache-2.0
Ghbubbuild/bub1.7k—~798Automated safety check: PassApache-2.0
GitHub Fork and PR Submissionjxxghp/MoviePilot12k—~1.1kAutomated safety check: NotesGPL-3.0
Beava PR Reviewbeava-dev/beava138—~2.1kAutomated safety check: PassApache-2.0
Changelog Draft Generatorwarpdotdev/warp65k1 repos~3.1kAutomated safety check: PassAGPL-3.0

Similar skills

  • Create Cuda Python Pull Request

    NVIDIA/cuda-python

    Official

    Create a CUDA Python pull request from an approved personal or organization-owned fork, including the GitHub CLI GraphQL fallback for renamed organization-owned forks.

    3.4k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed

  • Gh

    bubbuild/bub

    GitHub CLI skill for interacting with GitHub via the gh command line tool.

    1.7k GitHub stars~798 tokensUpdated today
    DevelopmentAuto-check passed

  • GitHub Fork and PR Submission

    jxxghp/MoviePilot

    Submits code changes as a GitHub pull request through an isolated Git clone, reusing or creating your fork and pushing only after you confirm the real diff.

    12k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check: notes

  • Beava PR Review

    beava-dev/beava

    Reviews a beava PR diff for real bugs, beava-specific architectural invariants, and AI-generated "slop" patterns (hollow code, phantom imports, inflated comments, disconnected pipelines).

    138 GitHub stars~2.1k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed

  • Changelog Draft Generator

    warpdotdev/warp

    Builds a reviewable changelog draft from the PRs merged between two release cuts, with contributor attribution and Markdown and JSON outputs.

    65k GitHub starsUsed in 1 repo~3.1k tokens
    DevelopmentAuto-check passed

  • GitHub PR Description

    lucasvieirasilva/nx-plugins

    Generates a GitHub Pull Request description for this repository from the commits on the current branch, filling in .github/PULLREQUESTTEMPLATE.md (Current Behavior / Expected Behavior / Related…

    153 GitHub stars~1.4k tokensUpdated 9 days ago
    DevelopmentAuto-check passed

More from basicmachines-co/basic-memory

All 49 skills in this repo

  • cmux Settings Editor

    basicmachines-co/basic-memory

    Views, sets, unsets and validates cmux settings in ~/.config/cmux/cmux.json with a helper script that checks keys against the schema.

    4.1k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

  • cmux Window and Pane Control

    basicmachines-co/basic-memory

    End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash). Use when automation needs…

    4.1k GitHub starsUsed in 2 repos~842 tokens
    Auto-check passed

  • Cmux Markdown Viewer Panel

    basicmachines-co/basic-memory

    Opens markdown files in a formatted cmux panel beside the terminal that re-renders on every change, handy for plans and task lists.

    4.1k GitHub starsUsed in 2 repos~527 tokens
    Auto-check passed

  • cmux Workspace Scoping

    basicmachines-co/basic-memory

    Keeps agent actions scoped to the cmux workspace and terminal that invoked it, and lays out pane and surface commands that avoid disrupting the user's own focus.

    4.1k GitHub starsUsed in 2 repos~1.7k tokens
    Auto-check passed

  • Basic Memory Repo Images

    basicmachines-co/basic-memory

    Produces PR, changelog and two-week retro images for the Basic Memory repository from evidence in PR bodies, saved to fixed paths under docs/assets/infographics.

    4.1k GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Logfire Instrumentation

    basicmachines-co/basic-memory

    Adds Pydantic Logfire tracing, logging and metrics to Python, JavaScript or TypeScript and Rust projects, with the correct setup order and library extras.

    4.1k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Pull Request

What does Pull Request do?

Drive GitHub pull request work end to end. An agent skill from basicmachines-co/basic-memory. Pull Request is an agent skill from basicmachines-co/basic-memory. Drive GitHub pull request work end to end.

When should I use Pull Request?

Pull Request fits situations like: Codex is asked to open; address comments on.

How do I install Pull Request in Claude Code?

Run `npx skills add basicmachines-co/basic-memory --skill pull-request -a claude-code`. Or copy the skill folder (.agents/skills/pull-request in basicmachines-co/basic-memory) into .claude/skills/pull-request in your project. Claude Code loads it when a task matches its description.

How do I install Pull Request in Codex?

Run `npx skills add basicmachines-co/basic-memory --skill pull-request -a codex`. Or copy the skill folder (.agents/skills/pull-request in basicmachines-co/basic-memory) into .agents/skills/pull-request in your project. Codex loads it when a task matches its description.

Can I use Pull Request 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 basicmachines-co/basic-memory --skill pull-request -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pull-request, .gemini/skills/pull-request, .github/skills/pull-request and .opencode/skills/pull-request in your project.

What does Pull Request need to run?

Going by SKILL.md and its folder, Pull Request needs the command-line tools its instructions call (python, gh, just and uv). Our summary lists: Python 3.

Does Pull Request access the network?

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

Is Pull Request 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 Pull Request use?

Pull Request 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 Pull Request use?

About 1.7k tokens (SKILL.md is roughly 6.8k 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 Pull Request?

Skills that share tags, products or a category with Pull Request: Create Cuda Python Pull Request (NVIDIA/cuda-python, 3.4k stars), Gh (bubbuild/bub, 1.7k stars), GitHub Fork and PR Submission (jxxghp/MoviePilot, 12k stars) and Beava PR Review (beava-dev/beava, 138 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pull Request?

basicmachines-co (a GitHub organization) maintains it in basicmachines-co/basic-memory, which has 4,115 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 7, 2026.

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