CtrlK
BlogDocsLog inGet started
Tessl Logo

review

Read-only correctness review with actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary.

59

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./crates/tui/assets/skills/review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 exceptionally lean and well-structured for a simple read-only review skill, with a clear workflow sequence; its main weakness is that the workflow steps lack concrete templates or formatting examples that would make execution fully unambiguous.

Suggestions

Add a short findings-list template or example (e.g., severity label, file:line, one-line fix) so the 'list findings by severity' step is copy-paste ready.

Include a brief residual-risk summary template (e.g., a one-line merge verdict with risk level) to lift actionability toward a 4–5.

Add an explicit re-verification step (e.g., 're-read the diff for missed findings before writing the summary') to push workflow_clarity to a 5.

DimensionReasoningScore

Conciseness

The body is lean with no padding or restating of concepts Claude already knows; every line ('Read-only by default. Do not edit unless asked.', 'Do not bury findings under style nits.') earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.

5 / 5

Actionability

The workflow steps give concrete direction ('List findings by severity with file/line evidence', 'Call out residual risk and missing tests') but provide no templates, formatting examples, or specific commands, leaving execution gaps that fit the 'some concrete guidance but incomplete' anchor rather than a 4.

3 / 5

Workflow Clarity

A clear 4-step sequence runs from scope through findings, residual risk, and a merge summary; the destructive-operation cap does not apply because the skill is explicitly read-only, but it lacks explicit re-verification feedback loops, so it stops just short of a 5.

4 / 5

Progressive Disclosure

At ~15 lines with no need for external references and clearly organized sections (When to use, Non-goals, Workflow), the skill qualifies for the under-50-lines simple-skill exception and matches the 'well-organized sections' criterion for a 5.

5 / 5

Total

17

/

20

Passed

Description

58%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 specific and reasonably distinctive about what the review skill produces, but it omits an explicit trigger ('Use when...') and lacks natural user-facing phrasing, capping completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g., 'Use when reviewing a diff, PR, or named change set for correctness before merge.'

Surface common user phrasings like 'review this PR', 'check this diff', or 'is this change correct?' to improve trigger-term coverage.

Name the concrete output deliverable more precisely (e.g., 'a severity-ranked findings list with residual-risk verdict') to push specificity toward a 5.

DimensionReasoningScore

Specificity

The description enumerates several concrete review attributes — 'actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary' — listing multiple specific actions with only minor coverage gaps, placing it just above the score-3 anchor but not yet comprehensive enough for a 5.

4 / 5

Completeness

A clear 'what' is present (read-only correctness review with listed attributes) but there is no explicit 'Use when...' trigger clause, so per the guideline a missing trigger caps completeness at 3.

3 / 5

Trigger Term Quality

It includes some relevant natural terms like 'correctness review' and 'findings' but misses common variations or synonyms users would actually say (e.g., 'review this PR/diff', 'check this change'), matching the score-3 anchor of partial keyword coverage.

3 / 5

Distinctiveness Conflict Risk

'Read-only correctness review' is a fairly specific niche with minimal conflict risk; the only overlap is with closely related general code-review skills (it is aliased to code-review), matching the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

14

/

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
Hmbown/CodeWhale
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.