pull-request

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.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable, concise, and workflow-clear with strong validation checkpoints and a feedback loop. Its one weakness is progressive disclosure: a long single-file skill with no reference bundles to offload detail.

Suggestions

Move the long Scope Discipline and PR Description Standard sections into a reference file (e.g. references/pr-scope.md) and link to it one level deep, keeping SKILL.md as a tighter overview.

Consider extracting the Codex Review Loop gate-state block and classification taxonomy into a separate reference so the main flow stays scannable.

Add a short 'See also' navigation pointing to the pr-description and pr-review-loop skills with one-line descriptions of when to reach for each.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it gives commands and rules without explaining what a PR or CI is — and does not pad with concepts Claude knows, fitting the level-3 anchor better than the level-2 'could be tightened' case.	3 / 3
Actionability	Concrete, copy-paste-ready guidance throughout: 'source .venv/bin/activate', 'gh pr view', 'just fast-check', 'just package-check', plus a fully specified gate-state block, matching the level-3 executable anchor rather than the pseudocode level-2.	3 / 3
Workflow Clarity	A numbered Flow with explicit validation gates ('run focused tests', the required gate before ready), a review loop with feedback/retry steps, and a final explicit Codex-gate checkpoint block satisfy the level-3 clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	The skill is a ~125-line monolithic single file with no bundle files or one-level-deep file references (the pr-description/pr-review-loop mentions are skill names, not linked reference files), so while sections are well-organized it fits the level-2 'content that should be separate is inline' anchor rather than the level-3 split-with-navigation anchor.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, explicit trigger clause, and concrete enumerated actions covering the whole PR lifecycle. No vague fluff or over-claims; nothing significant to improve.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'open, update, describe, push to, monitor, review, address comments on, declare ready, or merge a PR' — matching the anchor for several specific concrete actions, not a level-2 single-action domain.	3 / 3
Completeness	It clearly answers both what ('Drive GitHub pull request work end to end... Covers...') and when ('Use when Codex is asked to...'), with an explicit trigger clause, satisfying the level-3 anchor and avoiding the level-2 cap for a missing 'Use when' clause.	3 / 3
Trigger Term Quality	The 'Use when...' clause enumerates natural verbs a user would say ('open, update, review, merge a PR') plus domain terms ('branch hygiene', 'CI checks', 'review-loop'), giving good coverage rather than just a single keyword like level 2.	3 / 3
Distinctiveness Conflict Risk	The PR lifecycle is a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the level-3 anchor rather than the generic level-2 overlap case.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: basicmachines-co/basic-memory
Path: .agents/skills/pull-request/SKILL.md
Commit: cb95e59

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.