CtrlK
BlogDocsLog inGet started
Tessl Logo

contrib-pr-review

Review a contribution PR for safety, quality, and readiness. Checks for security concerns, test coverage, size appropriateness, and intent alignment. Use when reviewing external contributions.

64

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/contrib-pr-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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, highly actionable review protocol with executable commands and explicit conditional checkpoints throughout. The main lever for improvement is tightening the comment-drafting section and de-duplicating the bot-review guidance that appears in both step 1 and step 6.

Suggestions

Move the comment-drafting templates and worked examples (lines ~227–292) into a references file, keeping only the length/style rules inline, to cut the largest single block of tokens.

De-duplicate the Codex/CodeRabbit bot-review note: state it once in step 1 and reference it from step 6 instead of restating it.

Add an explicit verification step after the workflow-enable PUT (e.g. re-check requested_reviewers/workflow status) rather than relying on the `|| echo` fallback.

DimensionReasoningScore

Conciseness

Content is mostly earned — executable gh/jq commands and assessment rubrics rather than explanations of concepts Claude already knows — but the ~70-line comment-drafting section (templates plus two full examples) and the repeated bot-review note in steps 1 and 6 could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready, executable bash (gh api with --paginate and jq filters, grep/find pipelines) plus concrete output templates covering the common review cases end to end.

5 / 5

Workflow Clarity

Steps 1–6 plus final summary are clearly sequenced with conditional checkpoints ('If either bot flagged...', 'If security assessment passes...'); the workflow-enable step is gated on the security check, though verification of that PUT's effect relies only on an echo fallback rather than an explicit validate-fix-retry loop.

4 / 5

Progressive Disclosure

No bundle files exist; the skill is a single well-organized file with clear headers (Context, Review Protocol 1–6, Final Review Summary, Important Notes) and no nested references, though the comment-template content is inlined where a separate reference could carry it.

4 / 5

Total

17

/

20

Passed

Description

75%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 solid, third-person description that covers what the skill does and when to use it, with concrete capability breakdowns. It would reach the top band by adding natural synonyms ('pull request', PR numbers) and more specific trigger conditions for external-contributor scenarios.

DimensionReasoningScore

Specificity

Names the domain (contribution PR review) and lists several concrete checks — 'security concerns, test coverage, size appropriateness, and intent alignment' — giving solid action coverage with only minor gaps (e.g. 'quality' is left abstract).

4 / 5

Completeness

Clearly states both what ('Review a contribution PR... Checks for security concerns, test coverage...') and when ('Use when reviewing external contributions'); the 'when' clause is explicit but fairly generic rather than enumerating concrete trigger situations.

4 / 5

Trigger Term Quality

Includes natural phrases like 'contribution PR', 'reviewing external contributions', and 'security concerns', but omits common synonyms such as 'pull request' and file/number cues that users would naturally say.

4 / 5

Distinctiveness Conflict Risk

The 'external contributions' framing carves a reasonably distinct niche from general code-review skills, though it could still overlap with a generic PR-review skill since no unique triggers separate the two.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
homeassistant-ai/ha-mcp
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.