CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review

Review dotnet/macios PRs against established rules. Trigger on "review this PR", a GitHub PR URL, or code review requests. Checks bindings, MSBuild, nullable, formatting, performance, testing, native runtime code, and Apple platform patterns.

69

Quality

84%

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

85%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 well-structured, highly actionable reviewer skill with excellent workflow sequencing, validation checkpoints, and clean one-level progressive disclosure to a real reference file. The only notable gaps are the missing submission command in the final posting step and minor duplicated content that could be trimmed.

Suggestions

Add the concrete command(s) for step 7 (e.g., the gh pr review / gh api invocation for posting inline comments and submitting the COMMENT review event), since that is the one step without an executable command.

Remove the duplicated trivial-PR exception (stated in both Review Mindset and step 7) and consolidate the csigs stop rule so it appears authoritatively in only one place.

DimensionReasoningScore

Conciseness

The body is lean and imperative throughout — no explanations of concepts Claude already knows, and every section carries operational weight. Minor trimmable duplication keeps it below anchor 5: the trivial-PR exception is stated twice (Review Mindset and step 7), and the csigs rule is repeated verbatim in review-rules.md §0.

4 / 5

Actionability

Steps 1–4 provide exact copy-paste gh commands with flags, and the comment JSON schema plus template format are fully concrete. However, step 7 gives no actual command for posting inline comments or submitting the review event (e.g., the gh pr review / gh api invocation), leaving a gap in the final, most important step — anchor 4 rather than 5.

4 / 5

Workflow Clarity

A clear 7-step numbered sequence with explicit validation checkpoints: retrieve the author before any work, form an independent assessment before reading the PR narrative, treat the PR description as claims to verify, check CI with a hard "never post LGTM if failing" rule, and verify concerns to avoid false positives. This matches the anchor-5 pattern of sequenced steps with explicit checkpoints and error-recovery guidance.

5 / 5

Progressive Disclosure

SKILL.md is a workflow overview that defers all rule detail to a single, clearly signaled, one-level-deep reference (references/review-rules.md, step 5), which exists and holds the bulk material. The inline 9-item priority list is an appropriate summary, not content that belongs in a separate file; navigation is easy.

5 / 5

Total

18

/

20

Passed

Description

83%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 description that clearly states a niche capability and includes an explicit trigger clause with natural phrases. The main residual risk is minor overlap with generic code-review skills via the broad trigger phrasing.

DimensionReasoningScore

Specificity

Names a concrete action ("Review dotnet/macios PRs against established rules") plus specific check areas ("bindings, MSBuild, nullable, formatting, performance, testing, native runtime code, and Apple platform patterns"). Not a 5 because the listed items are domains checked rather than multiple distinct concrete actions.

4 / 5

Completeness

Explicitly answers both what ("Review dotnet/macios PRs against established rules... Checks bindings, MSBuild, nullable...") and when ("Trigger on 'review this PR', a GitHub PR URL, or code review requests") with concrete trigger phrases, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

"Trigger on 'review this PR', a GitHub PR URL, or code review requests" includes natural phrases a user would actually say. A few natural variations are missing (e.g., "LGTM", "review PR #123"), which keeps it below the comprehensive-synonyms anchor of 5.

4 / 5

Distinctiveness Conflict Risk

"dotnet/macios" carves out a clear niche with minimal conflict risk, but the generic trigger "code review requests" and broad terms like "formatting, performance, testing" create minor overlap with generic code-review skills. Not 5 because of that overlap; clearly above the 'somewhat specific but overlapping' anchor 3.

4 / 5

Total

17

/

20

Passed

Validation

100%

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
dotnet/macios
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.