CtrlK
BlogDocsLog inGet started
Tessl Logo

team-review

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

53

Quality

60%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/team-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured orchestration skill that clearly defines a multi-agent code review pipeline with concrete templates, explicit delegation rules, and thorough error handling. The progressive disclosure is excellent with clear routing to role-specific files. Minor verbosity in some sections (architecture diagram + role router overlap, repeated pipeline pattern descriptions) prevents a perfect conciseness score, but overall the content is highly actionable and well-organized.

DimensionReasoningScore

Conciseness

The skill is fairly dense and information-rich, but includes some redundancy (e.g., the architecture diagram and role router section overlap, the agent coordination section repeats pipeline pattern info). Some tables could be tighter, but most content is non-obvious orchestration logic that Claude wouldn't inherently know.

2 / 3

Actionability

Provides concrete spawn_agent templates with exact parameter structures, specific tool call allow/block lists, exact file paths, CLI commands, timeout values, and copy-paste ready code for agent spawning, health checks, and completion actions. The delegation lock table is highly actionable.

3 / 3

Workflow Clarity

The sequential 3-stage pipeline (scan -> review -> fix) is clearly defined with explicit skip conditions (0 findings -> skip review+fix, user declines fix -> skip fix). Timeout handling has a clear escalation sequence (wait -> STATUS_CHECK -> FINALIZE -> close). Agent health reconciliation is specified. Error handling table covers edge cases with concrete resolutions.

3 / 3

Progressive Disclosure

SKILL.md serves as a clear router/overview pointing to one-level-deep role specs (roles/coordinator/role.md, roles/scanner/role.md, etc.) and spec files (specs/pipelines.md, specs/dimensions.md, etc.). References are well-signaled with relative paths and a role registry table. Content is appropriately split between the overview and role-specific files.

3 / 3

Total

11

/

12

Passed

Description

35%

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 the high-level concept (a multi-role code review pipeline) but lacks concrete action details for each role and relies on an internal trigger term rather than natural user language. It would benefit significantly from explicit 'Use when...' guidance and natural keywords users would actually say when requesting code reviews.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'code review', 'review my PR', 'pull request review', 'check my code', 'review changes'.

Expand the role descriptions with concrete actions, e.g., 'Scans for bugs and style issues, reviews logic and architecture, and auto-fixes common problems'.

Replace or supplement the internal trigger 'team-review' with user-facing language describing when this skill should be selected over a simpler single-pass code review skill.

DimensionReasoningScore

Specificity

Names the domain (code review) and describes the pipeline structure (3-role: scanner, reviewer, fixer), but doesn't explain what each role concretely does — e.g., what does the scanner scan for, what does the fixer fix?

2 / 3

Completeness

The 'what' is partially addressed (code review with a 3-role pipeline), but the 'when' is only implied via 'Triggers on team-review' — there is no explicit 'Use when...' clause describing user scenarios or natural trigger conditions.

2 / 3

Trigger Term Quality

The only trigger term is 'team-review', which is a technical/internal command rather than a natural keyword a user would say. Missing natural terms like 'code review', 'review my PR', 'pull request', 'review changes', etc.

1 / 3

Distinctiveness Conflict Risk

The 3-role pipeline concept and 'team-review' trigger give it some distinctiveness, but 'code review' is broad enough to overlap with other review-related skills. The internal trigger name helps somewhat but isn't user-facing.

2 / 3

Total

7

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

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

Warning

Total

10

/

11

Passed

Repository
catlog22/Claude-Code-Workflow
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.