CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-review-fix

Periodically analyze open pull requests for CI failures, code review feedback, and quality issues, then fix them in batch. Use this skill when the user asks to check PR status, triage CI failures, fix review comments, analyze open PRs, or run a scheduled PR health check across the repository.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The content is well-structured and actionable: a clear four-phase workflow with validation checkpoints and a feedback loop, plus a clean routing table to one-level-deep reference files. Minor gains are available from de-duplicating the commit format and tightening the CI verification step.

Suggestions

De-duplicate the commit message format: state it once in 'Commit conventions' and reference it from Phase 3 instead of repeating 'fix(<scope>): 🔧 <description>'.

Make the Phase 4 verification step more deterministic than 'wait 1-2 minutes' — e.g. poll 'gh pr checks <number> --watch' or re-run with a defined retry count before looping back to Phase 3.

Replace bare placeholders like '<branch>' and '<original>' in Phase 3 with a one-line note on how to capture them (e.g., from the headRefName field fetched in Phase 1) so the steps are fully copy-paste ready.

DimensionReasoningScore

Conciseness

Lean body using tables, code blocks, and bullets with no concept over-explanation; the only redundancy is the commit format appearing in both Phase 3 and the 'Commit conventions' section.

4 / 5

Actionability

Provides concrete, mostly executable commands ('gh pr list ...', 'git checkout -B <branch> github/<branch>', 'gh pr checks <number>') and a conventional-commit template; minor gaps remain in placeholder branches and scopes.

4 / 5

Workflow Clarity

Four sequenced phases with a verify→fix feedback loop (Phase 4 loops to Phase 3), a self-check checklist, and required local build/test/lint validation before push; the 'wait 1-2 minutes' verify step is somewhat loose, keeping it just below fully explicit.

4 / 5

Progressive Disclosure

Clear overview with a routing table pointing to five real, one-level-deep reference files (discovery, triage, fix-workflow, ci-pipeline, fix-recipes), all verified to exist with no nested redirects; content is appropriately split between the overview and references.

5 / 5

Total

17

/

20

Passed

Description

91%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.

The description is strong: it states concrete capabilities, gives comprehensive natural trigger terms, and explicitly covers both what and when. The only soft spots are slight generality on the fix action and minor overlap risk with adjacent CI/review skills.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions — 'analyze open pull requests for CI failures, code review feedback, and quality issues, then fix them in batch' — but the fix side ('fix them in batch') stays generic, so it falls just short of fully comprehensive.

4 / 5

Completeness

Clearly answers both: the 'what' (analyze PRs for failures/feedback/issues, fix in batch) and an explicit 'when' via 'Use this skill when the user asks to...' with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural phrasing users would actually say — 'check PR status, triage CI failures, fix review comments, analyze open PRs, run a scheduled PR health check' — covering the full intent space.

5 / 5

Distinctiveness Conflict Risk

Clear PR review-and-fix niche with distinct triggers, but 'triage CI failures' and 'fix review comments' carry minor overlap risk with general CI-fix or code-review skills.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
TencentCloudBase/CloudBase-AI-Toolkit
Reviewed

Table of Contents

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.