CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-code-review

Review a named diff or PR for bugs, regressions, tests, and standards. Use when asked to review code or when a shipping skill needs a review receipt. Use when asked to apply this review's findings locally. Use ce-resolve-pr-feedback for feedback already left on a PR.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a well-engineered orchestration spine: lean, dense with skill-specific rules, sequenced with explicit gates and failure handling, and structured for progressive disclosure with every reference tied to a governing step. Its weaknesses are stylistic — over-compressed run-on paragraphs that hide checkpoints, and a two-level persona/reference chain — rather than substantive. All four dimensions sit comfortably at the 4 anchor.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence — no concept explanations, no padding; every sentence encodes skill-specific orchestration rules ("Read docs_root from <repo-root>/.compound-engineering/config.yaml only"). It matches anchor 4 rather than 5 because the dense run-on stage paragraphs (Stages 3d, 4, 5-6) restate collection and peer-cleanup rules and could be tightened; it is above anchor 3 because there is no genuinely unnecessary explanation.

4 / 5

Actionability

Guidance is concrete and executable: exact commands ("git rev-parse --show-toplevel"), exact config paths, named reference files per stage, explicit mode tokens (apply:local, mode:agent), and explicit prohibitions ("Never use AskUserQuestion", "Never run gh pr checkout"). It matches anchor 4 rather than 5 because dispatch and collection mechanics are deferred to references rather than given inline, leaving minor gaps in the body itself.

4 / 5

Workflow Clarity

The execution spine is a numbered 1-7 sequence in enforced order with explicit gates ("apply that Review depth gate before Stage 2"), terminal conditions ("Done when:"), and failure-recovery paths (failed reviewer recording, peer cleanup "before returning the failure result"). It matches anchor 4 rather than 5 because checkpoints are embedded in dense prose instead of crisp, checklist-style steps, and validation detail lives in the references.

4 / 5

Progressive Disclosure

The body is a true overview that signals each reference with the stage it governs ("Read references/scope.md and resolve the reviewed diff"), and all eleven referenced files verified present in references/, keeping the main flow one level deep. It matches anchor 4 rather than 5 because persona-catalog.md points into a personas/ subdirectory (a second level) and the leaf finish references add a nested dispatch pattern.

4 / 5

Total

16

/

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.

The description is strong: it states a concrete capability, gives explicit "Use when" triggers for both review and apply, and even routes a neighboring use case to a sibling skill. Its only weakness is keyword coverage that misses a few natural phrasings users might use for code review. It clearly exceeds the quality of the good overall examples in both what/when explicitness and conflict disambiguation.

DimensionReasoningScore

Specificity

"Review a named diff or PR for bugs, regressions, tests, and standards" names the domain and several concrete review actions, plus "apply this review's findings locally" — matching anchor 4 (several specific actions, minor gaps). It is not 5 because coverage centers on a single review capability rather than a comprehensive list of distinct actions, and not 3 because more than 1-2 concrete actions are enumerated.

4 / 5

Completeness

It explicitly answers both what ("Review a named diff or PR for bugs, regressions, tests, and standards") and when ("Use when asked to review code or when a shipping skill needs a review receipt. Use when asked to apply this review's findings locally") with concrete trigger phrases — matching anchor 5 exactly. It is not 4 because the when-clauses are already explicit and specific, not merely improvable.

5 / 5

Trigger Term Quality

Natural trigger phrases like "asked to review code", "diff", "PR", "bugs", and "apply this review's findings" give good keyword coverage, matching anchor 4. A few natural variations users might say ("code review", "check my changes", "look over this diff") are missing, so it falls short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche (reviewing a named diff or PR) with active conflict disambiguation ("Use ce-resolve-pr-feedback for feedback already left on a PR") matches anchor 4's mostly-distinct profile. It is not 5 because "asked to review code" is broad enough to overlap with other review-type skills (security review, general refactoring), and not 3 because the routing clause and diff/PR scoping make wrong-skill triggering unlikely.

4 / 5

Total

17

/

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.

Validation — 15 / 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

EveryInc/compound-engineering-plugin

Path

skills/ce-code-review/SKILL.md

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.