check-pr

Check a single PR's CI status, review comments, and requested changes. Fix actionable failures and address feedback. "check PR 1234", "what's the status of my PR", "address review comments on #500".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

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

The content is lean and highly actionable with executable gh/git/GraphQL commands and a clear branching workflow, but it omits post-action verification loops and keeps everything inline in one long file rather than splitting detail into references.

Suggestions

Add an explicit verification step after fixing/pushing in section 4 (e.g., re-run `gh pr checks` and only report success once CI passes) to close the feedback loop for the destructive push action.

Confirm each comment reply succeeds and verify thread resolution state in section 5 before declaring the review addressed.

Move the lengthy GraphQL review-thread queries (or the per-state gathering recipes) into a references/ file referenced from the main body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what a PR, CI check, or `gh` is, and the few prose notes (e.g., 'A review with an empty body may still have line-level comments') are non-obvious gotchas that earn their tokens rather than padding.	3 / 3
Actionability	Provides fully executable, copy-paste-ready `gh`, `git`, and GraphQL commands with only the necessary fill-in placeholders (`<branch>`, `<thread-id>`), meeting the anchor for complete executable guidance rather than pseudocode.	3 / 3
Workflow Clarity	The six numbered sections give a clear branching sequence (merged / closed / failing / changes requested), but after pushing fixes or resolving threads there is no explicit verification or feedback loop, which caps destructive/outward-facing batch operations at 2 rather than 3.	2 / 3
Progressive Disclosure	Sections are clearly organized, but the skill is a single monolithic file over the 50-line simple-skill threshold with no content split into reference files, and the verbose inline GraphQL blocks are candidates for externalization.	2 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is tight and complete: it names concrete actions, supplies natural trigger phrases, and occupies a distinct niche. It avoids fluff and uses third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'check CI status, review comments, and requested changes' plus 'Fix actionable failures and address feedback' — matching the anchor that rewards several specific actions rather than vague language.	3 / 3
Completeness	Explicitly states what the skill does and provides equivalent explicit trigger guidance via the quoted user phrases, satisfying both the 'what' and 'when' requirements rather than leaving 'when' implied.	3 / 3
Trigger Term Quality	Embeds natural phrases a user would actually say — "check PR 1234", "what's the status of my PR", "address review comments on #500" — giving strong coverage of real trigger terms.	3 / 3
Distinctiveness Conflict Risk	Targets a clear, narrow niche (single-PR CI/review triage) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: docker/docs
Commit: 67d0999

Reviewed: about 10 hours 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.