CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-cycle

Chain-loaded review cycle. 3-mode routing for session, module, or fix review.

Quality

59%

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 ./.claude/workflow-skills/review-cycle/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

47%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 body is token-efficient but underspecified: it enumerates chain_loader commands without sequencing, validation, or guidance on choosing a mode, and references phases/variables with no bundle files or navigation. It reads as a terse command index rather than actionable skill content.

Suggestions

Sequence the commands as a numbered workflow with an explicit validation/checkpoint step (e.g., confirm review_status and fix_count before finishing a fix review).

Add a short 'When to use each mode' table or list so the session/module/fix entry points are actionable rather than just enumerated.

Either provide the referenced bundle (phases under .claude/skills/review-cycle/) or inline the key phase instructions, and clearly signal what lives where instead of a bare 'Phases from ...' line.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence ('Use chain_loader to execute', four commands, a phase path, and two variables), with no padding or explanation of concepts Claude already knows; it is efficient with only minor terseness, matching 'Efficient; minor instances of over-explanation that could be trimmed' (here, if anything, slightly under-explained rather than padded).

4 / 5

Actionability

It lists concrete `chain_loader start` commands but gives no guidance on when to pick each entry point or how to use the variables, leaving execution incomplete — 'Some concrete guidance but incomplete; missing key details'.

3 / 5

Workflow Clarity

The four commands are presented as an unordered list rather than a sequenced workflow, with no validation checkpoints or feedback loops for a review/fix process; this matches 'Rough sequence present but many gaps; steps poorly defined; validation absent'.

2 / 5

Progressive Disclosure

No bundle files exist and the body references 'Phases from .claude/skills/review-cycle/' and bare variables (review_status, fix_count) with no signaling or navigation, so structure is minimal and references are buried, matching 'Minimal structure; references are buried'.

2 / 5

Total

11

/

20

Passed

Description

50%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 conveys a clear purpose (a chain-loaded 3-mode review cycle) but omits any 'Use when...' trigger guidance and lacks keyword variations, capping several dimensions at 3. It is specific enough to be distinguishable but not comprehensive.

Suggestions

Add an explicit 'Use when...' clause naming the natural trigger phrases (e.g., 'Use when reviewing a session, module, or a recent fix').

Include keyword synonyms and natural phrasings users would actually say, such as 'code review', 'review changes', or 'review a patch'.

List the concrete actions more comprehensively (e.g., what the session/module/fix modes actually do) to lift specificity above 3.

DimensionReasoningScore

Specificity

Names the domain ('review cycle') and concrete actions ('3-mode routing', 'session, module, or fix review') but the actions are minimal and coverage is not comprehensive, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'.

3 / 5

Completeness

It has a clear 'what' (chain-loaded review cycle with 3-mode routing) but no 'Use when...' or equivalent trigger guidance, so completeness is capped at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Contains relevant keywords like 'review', 'session', 'module', and 'fix' but lacks common synonyms and natural phrasings a user would say, fitting 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The 'review cycle' niche is somewhat specific but could still overlap with other general review skills, matching 'Somewhat specific but could still overlap with similar skills'.

3 / 5

Total

12

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

catlog22/Claude-Code-Workflow

Path

.claude/workflow-skills/review-cycle/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.