CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-review

End-to-end PR reviewer for dotnet/maui. Orchestrates 3 phases — Pre-Flight, Try-Fix, Report. Gate runs separately before this skill. Use when asked to 'review PR #XXXXX', 'work on PR #XXXXX', or 'fix issue #XXXXX'.

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

73%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 orchestrator skill with strong workflow sequencing and validation. Main weakness is conciseness: redundant mandatory-emphasis and duplicated rule restatements inflate the token budget.

Suggestions

Consolidate the repeated MANDATORY/NEVER-skip-Phase-2 warnings into one authoritative Critical Rules entry and reference it from the phase sections instead of restating.

Merge the 'Common Mistakes' list with 'Critical Rules' to eliminate duplication of the same guidance (e.g. parallel/background mode, cleanup).

Move the detailed try-fix prompt template and output-file schema into a references/ bundle file, keeping SKILL.md as a lean overview with a one-level-deep pointer.

DimensionReasoningScore

Conciseness

The body is mostly operational and avoids explaining concepts Claude already knows, but repeated emphasis ('MANDATORY' ~6 times, 'NEVER skip Phase 2' restated in Critical Rules, the phase header, Common Mistakes) and duplicated guidance between Critical Rules and Common Mistakes could be tightened.

3 / 5

Actionability

Provides concrete executable commands (e.g. 'pwsh .github/scripts/EstablishBrokenBaseline.ps1 -Restore'), specific model names, and detailed prompt/file templates, but the templates rely on placeholders ({bug description}, {PRNumber}, {file1}.cs) that must be filled, so they are not fully copy-paste ready.

4 / 5

Workflow Clarity

A clear 3-phase sequence with explicit gates, a per-attempt checklist, validation checkpoints (sync mode, cleanup between attempts, 'Wait for each to complete'), and feedback loops (retry table, Common Errors recovery) — matching the top anchor for complex processes.

5 / 5

Progressive Disclosure

Well-structured sections with clearly signaled one-level-deep references ('Read and follow .github/pr-review/pr-preflight.md'), but a substantial amount of phase detail is inlined in SKILL.md and no bundle files (references/scripts/assets) exist in the skill directory.

4 / 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 that concisely states the domain, concrete phases, and explicit natural-language triggers in third-person voice. Minor room to expand specificity of capabilities beyond phase labels.

DimensionReasoningScore

Specificity

Names the domain ('End-to-end PR reviewer for dotnet/maui') and lists several concrete phases ('Orchestrates 3 phases — Pre-Flight, Try-Fix, Report'), though the phases are structural labels rather than fully enumerated capabilities, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' (end-to-end PR reviewer orchestrating 3 phases) and 'when' ('Use when asked to...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Provides three natural trigger phrases users would actually say — 'review PR #XXXXX', 'work on PR #XXXXX', 'fix issue #XXXXX' — covering synonyms (review/work/fix) comprehensively.

5 / 5

Distinctiveness Conflict Risk

The 'dotnet/maui' niche and PR-review-specific trigger phrases make it clearly distinguishable from other skills with minimal conflict risk.

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.