CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

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.

The content is a well-structured orchestration skill: a clear sequenced spine with validation checkpoints and error-recovery loops, paired with disciplined one-level-deep progressive disclosure. The only weakness is sentence-level density in a few procedural steps that could be tightened for token efficiency.

Suggestions

Split the long compound sentences in Stage 3d and the Stage 4 dispatch step into shorter bullet points to reduce parse load and recover conciseness toward 5.

Inline one or two of the most load-bearing executable specifics (e.g., the blocking-collection bound or the exact reviewer-return contract) so the spine is more self-contained, reducing reliance on references for actionability.

DimensionReasoningScore

Conciseness

The body is dense, rule-bearing prose that assumes Claude's competence and avoids explaining known concepts, but several compound sentences (e.g., Stage 3d and the Stage 4 dispatch step) pack many conditions into one sentence and could be split or trimmed.

4 / 5

Actionability

It gives concrete, ordered instructions ("Read references/modes-and-output.md first", "Dispatch the selected local reviewers as one concurrent batch") with named files and terminal-outcome rules, though much of the executable detail is deferred into reference files rather than inline.

4 / 5

Workflow Clarity

The seven-stage Execution spine is explicitly ordered with validation checkpoints (depth gate before Stage 2, Stage 6 verifying requirements against the plan, validator launch) and error-recovery feedback loops (failed/uncollected reviewers recorded, peer fallback conditions).

5 / 5

Progressive Disclosure

The body is a concise overview that signals one-level-deep references by exact filename and the stage at which each is read (references/modes-and-output.md, scope.md, intent-and-plan.md, etc., all confirmed present in ./references/), keeping bulk detail out of SKILL.md.

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.

The description is strong: it pairs a concrete what with multiple explicit when triggers and disambiguates a sibling skill. Minor gaps in action enumeration and trigger synonyms keep specificity and trigger quality at 4 rather than 5.

Suggestions

Add a couple of natural trigger synonyms (e.g., "audit a diff", "lint a change", "critique a PR") to broaden trigger-term coverage toward 5.

Expand the action list slightly beyond review categories (e.g., "triage findings, write a review receipt, apply fixes locally") to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

"Review a named diff or PR for bugs, regressions, tests, and standards" names the domain plus several concrete review actions, but the actions are review categories rather than fully enumerated operations, leaving minor coverage gaps.

4 / 5

Completeness

It explicitly states both what ("Review a named diff or PR for bugs, regressions, tests, and standards") and when via multiple concrete "Use when..." trigger clauses, satisfying the top anchor.

5 / 5

Trigger Term Quality

"Use when asked to review code", "when a shipping skill needs a review receipt", and "apply this review's findings locally" give good natural-phrase coverage, though a few common synonyms (audit, lint, critique) are absent.

4 / 5

Distinctiveness Conflict Risk

"Use ce-resolve-pr-feedback for feedback already left on a PR" draws an explicit boundary from a sibling skill and carves a clear niche, but "review code" still overlaps generically with other review skills, keeping it just below the top anchor.

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.

Validation15 / 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
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.