review-pr

Review a GitHub pull request from its link, read the PR description, inspect the code locally only when useful, and judge whether the change is safe to run from a security and runtime-safety perspective. Use only after the user pastes a PR URL. Handle one PR at a time, make a clear merge/close/supersede recommendation, and keep all GitHub review and merge actions with the user.

Quality

86%

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

81%Weight 40%Scale 1-5

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

A thorough, actionable, well-sequenced review workflow with concrete commands, repo-specific hotspots, and a clear output format. The main weakness is repetition of the recommendation framing and some generic threat-model exposition that could be tightened.

Suggestions

Consolidate the merge/close/supersede recommendation guidance into one section; the Overview, 6.5, and "After The Review" each re-derive it — define it once and reference it.

Trim the generic threat-model questions in section 6 (e.g. "Does this add or widen code execution paths?") toward the repo-specific high-scrutiny signals already listed, since Claude already applies threat-modeling.

Consider extracting the "Electrobun Hotspots" list and the high-risk-file checklist into a reference file so the core workflow stays leaner.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and repo-specific, but the merge/close/supersede recommendation is restated across Overview, section 6.5, and "After The Review", and the "Judge safe-to-run risk" questions repeat generic threat-model concepts Claude already knows.	3 / 5
Actionability	Provides copy-paste-ready git and build commands (`git fetch origin pull/<pr-number>/head:pr-<pr-number>`, `bun build:dev`, `bun dev`), concrete repo hotspot paths, and an exact verdict/output template covering the common review cases.	5 / 5
Workflow Clarity	A clearly numbered 0→6.5 sequence with explicit validation gates (security screen before execution, re-diff/re-test before merge, stop-and-ask for interactive tests) and checklists for high-risk files and threat signals.	5 / 5
Progressive Disclosure	Single well-organized file with clear section headers and no nested or buried references; the skill exceeds 50 lines so the simple-skill exception does not apply, but the structure is good and content is appropriately placed.	4 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

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, concrete description that clearly states capabilities, trigger conditions, and scope. Third-person imperative voice is used throughout with no first/second-person slippage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "read the PR description", "inspect the code locally only when useful", "judge whether the change is safe to run", "make a clear merge/close/supersede recommendation" — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (review/inspect/judge safe-to-run) and when ("Use only after the user pastes a PR URL") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Uses natural terms a user would say ("GitHub pull request", "PR URL", "PR", "merge/close/supersede") with good coverage, but misses a few common synonyms like "code review" or "diff" that users also say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — security and runtime-safety review of a GitHub PR by pasted URL — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 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: blackboardsh/electrobun
Path: .skills/review-pr/SKILL.md
Commit: 08cd730

Reviewed: 3 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.