CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review

Deep code review of PR or materialized candidate-patch changes for correctness, safety, and MAUI conventions. Uses independence-first assessment (code before narrative) and delegates to the maui-expert-reviewer agent for per-dimension sub-agent evaluation. Triggers on: "review code for PR", "code review PR", "review candidate patch", "analyze code changes", "check PR code quality". Do NOT use for: summarizing PRs, describing what changed, general PR questions, running tests, or fixing code.

71

Quality

86%

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

77%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 workflow with excellent sequencing and validation, but it is a long monolithic file that repeats several rules and inlines content that belongs in separate reference files. Tightening the repetition and splitting detailed reference material would materially improve token efficiency and navigation.

Suggestions

De-duplicate restated rules: state 'Authentication is not availability' and the anonymous curl fallback once in Step 1 and reference it from Core Principles and Step 4 instead of repeating the full explanation three times.

Factor the detailed CI exit-code semantics and the Trim/AOT evidence-chain procedure into separate reference files (e.g. references/ci-classification.md, references/trim-aot.md) and link to them from the main workflow to improve progressive disclosure.

Move the full Review Output Format template into a reference file, keeping only a short pointer and the required tables inline in SKILL.md.

DimensionReasoningScore

Conciseness

Much of the 447-line body is genuinely non-obvious operational knowledge (MAUI trim/AOT contracts, gh exit-code semantics), but several rules are restated multiple times — 'Authentication is not availability' plus the curl fallback appears in Core Principles, Step 1, and Step 4, and Rule #6/#7 are repeated across Step 5, Step 6, and Verdict Consistency Rules — which is padding that could be tightened.

3 / 5

Actionability

Provides copy-paste-ready, executable commands throughout — curl anonymous retrieval, 'gh pr diff', the jq-based 'gh api ... reviews --method POST' posting example, 'gh pr checks --required' — plus concrete required output tables and a full output-format template covering the common cases.

5 / 5

Workflow Clarity

Clear sequenced workflow (Step 1 → 1.5 → 1.6 → 2 → 3 → 4 → 5 → 6) with explicit validation checkpoints (CI status classification, prior-review reconciliation, External Output Contract validate→fix→retry loop) and a Completion Criteria checklist for error recovery.

5 / 5

Progressive Disclosure

Sections are well-organized and the one-level reference to '.github/agents/maui-expert-reviewer.md' is clearly signaled, but no bundle files exist and the 447-line body inlines large blocks (detailed CI exit-code semantics, trim/AOT evidence procedure, the full output-format template) that would navigate better split into separate reference files.

3 / 5

Total

16

/

20

Passed

Description

95%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: concrete domain, multiple natural trigger phrases, explicit when/what, and clear negative boundaries that distinguish it from sibling review skills. The only soft spot is action specificity, where 'review for correctness/safety' is slightly more abstract than enumerating concrete review acts.

DimensionReasoningScore

Specificity

Lists several specific actions ('Deep code review of PR or materialized candidate-patch changes for correctness, safety, and MAUI conventions', 'delegates to the maui-expert-reviewer agent for per-dimension sub-agent evaluation'), but 'review for correctness/safety' stays somewhat abstract, leaving minor coverage gaps versus a fully comprehensive action list.

4 / 5

Completeness

Explicitly answers both 'what' (deep code review for correctness/safety/MAUI conventions) and 'when' ('Triggers on:' with concrete trigger phrases), matching the anchor for clearly and explicitly answering both.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases including synonyms — 'review code for PR', 'code review PR', 'review candidate patch', 'analyze code changes', 'check PR code quality' — plus a 'Do NOT use for' list adding more natural terms users actually say.

5 / 5

Distinctiveness Conflict Risk

Clear MAUI-conventions niche with explicit trigger phrases and an explicit 'Do NOT use for' negation (summarizing, describing, general questions, running tests, fixing code), giving minimal conflict risk with adjacent review skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
dotnet/maui
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.