CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

team-review

Unified team skill for code review. 3-role pipeline: scanner, reviewer, fixer. Triggers on team-review.

Quality

65%

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/skills/team-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 a well-organized, token-efficient router that correctly delegates detail to separate files, but the bundle is missing all referenced roles/ and specs/ files, breaking progressive disclosure and leaving the actionable core incomplete. Validation checkpoints for the destructive fix step are also only implicit.

Suggestions

Ship the referenced bundle files (roles/coordinator|scanner|reviewer|fixer/role.md and specs/pipelines.md, dimensions.md, finding-schema.json, team-config.json) so the one-level references resolve.

Add an explicit validation checkpoint in the body for the fixer step (e.g. verify build/tests pass before marking FIX complete, rollback on failure) to lift workflow clarity above the destructive-operation cap of 3.

Inline a minimal fallback for the core scan/review/fix loop so the skill remains actionable even before the role files are loaded.

DimensionReasoningScore

Conciseness

The body is a lean router using tables, an architecture diagram, and compact templates; it assumes Claude's competence and avoids explaining concepts Claude already knows, with only minor trim opportunities in the spawn/completion templates.

4 / 5

Actionability

Provides concrete, executable templates (the Agent() spawn call, AskUserQuestion completion, shared constants, CLI tool names), but the actual per-role executable instructions live in roles/<name>/role.md and specs/*.md files that do not exist in the bundle, leaving key execution details missing.

3 / 5

Workflow Clarity

The pipeline sequence is present (coordinator -> spawn -> scan/review/fix via the architecture diagram and role router) and an error-handling table covers failure modes, but validation checkpoints are implicit rather than sequenced; since the fixer mutates code (a destructive operation) without explicit validate-before-proceed steps in the body, workflow clarity is capped at 3.

3 / 5

Progressive Disclosure

The body is well-structured with clearly signaled one-level references to roles/*.md and specs/*.md, but none of those bundle files exist, so every reference is a dead link and the disclosure is non-functional in practice.

2 / 5

Total

12

/

20

Passed

Description

62%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 cleanly states what the skill does and gives an explicit trigger, landing above midpoint on completeness and distinctiveness. It is held back from the top band by role-named (rather than verb-named) actions, missing trigger-term variations, and a broad 'code review' domain.

Suggestions

Reword actions as explicit verbs (e.g. 'Scans code, reviews findings, applies fixes') instead of role nouns to lift specificity.

Expand the trigger clause to natural situations: 'Use when the user asks to review a PR, diff, or changeset, or invokes team-review.'

Add file/extension-style concrete triggers (e.g. 'review staged changes', 'review a branch') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ('code review') and three concrete action-roles ('scanner, reviewer, fixer'), but the actions are expressed as role nouns rather than explicit verbs and 'code review' is a broad domain, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('3-role pipeline: scanner, reviewer, fixer') and when ('Triggers on team-review'); the when is explicit but minimal and could name more triggering situations, so it sits at 4 rather than 5.

4 / 5

Trigger Term Quality

Includes the natural term 'code review' and the explicit trigger 'team-review', but misses common variations a user would actually say such as 'review my PR', 'review the diff', or 'review these changes'.

3 / 5

Distinctiveness Conflict Risk

The explicit 'Triggers on team-review' command and the distinctive 3-role pipeline give it a clear niche with minimal conflict risk, though 'code review' still overlaps slightly with generic review skills.

4 / 5

Total

14

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 8 missing, 4 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

catlog22/Claude-Code-Workflow

Path

.claude/skills/team-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.