team-review
Unified team skill for code review. 3-role pipeline: scanner, reviewer, fixer. Triggers on team-review.
58
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex/skills/team-review/SKILL.mdQuality
Discovery
50%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 general purpose (code review) and hints at a unique architecture (3-role pipeline), but lacks concrete action descriptions for each role and a proper 'Use when...' clause. It relies on a specific trigger command ('team-review') rather than describing natural user scenarios, which limits its effectiveness for skill selection among many options.
Suggestions
Add a 'Use when...' clause describing natural user scenarios, e.g., 'Use when the user asks for a comprehensive code review, wants automated scanning and fixing of code issues, or mentions team-review.'
Describe what each role (scanner, reviewer, fixer) concretely does, e.g., 'Scans code for bugs and style issues, provides detailed review feedback, and auto-fixes common problems.'
Include natural trigger terms users might say, such as 'review my code', 'PR review', 'pull request feedback', 'code quality check'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (code review) and mentions a specific architecture (3-role pipeline: scanner, reviewer, fixer), but doesn't describe concrete actions like what each role does or what outputs are produced. | 2 / 3 |
Completeness | The 'what' is partially addressed (code review with a 3-role pipeline), and 'Triggers on team-review' hints at when, but there's no explicit 'Use when...' clause describing the scenarios or user intents that should activate this skill. | 2 / 3 |
Trigger Term Quality | Includes 'code review' and 'team-review' as keywords, but misses common natural variations users might say like 'review my code', 'PR review', 'pull request', 'code feedback', or 'lint'. The trigger term 'team-review' is a specific command rather than a natural user phrase. | 2 / 3 |
Distinctiveness Conflict Risk | The '3-role pipeline' and 'team-review' trigger give it some distinctiveness, but 'code review' is broad enough to overlap with other review-related skills. The specific trigger command 'team-review' helps reduce conflict but isn't well explained. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
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 tool boundaries, and proper error handling. Its main strength is the high actionability — the delegation lock, spawn templates, and timeout escalation are immediately executable. Minor verbosity in a few sections (unused message semantics row, some conceptual overlap between architecture and pipeline pattern) prevents a perfect conciseness score.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly dense and information-rich, but includes some redundancy (e.g., the architecture diagram and the role router section overlap conceptually). The delegation lock table and agent coordination sections are well-structured but could be tightened. Some sections like 'Message Semantics' include a 'Not used in this skill' row which wastes tokens. | 2 / 3 |
Actionability | Provides concrete spawn_agent templates with exact parameter structures, specific tool call allowlists/blocklists, exact file paths, CLI commands, and copy-paste ready code for agent spawning, health checks, and completion actions. The delegation lock table is immediately actionable with clear verdicts. | 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 with interrupt -> mark timed_out -> close). Agent health check reconciliation provides a feedback loop for orphaned tasks. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: SKILL.md serves as a router/overview pointing to role-specific files (roles/coordinator/role.md, roles/scanner/role.md, etc.) and spec files (specs/pipelines.md, specs/dimensions.md, etc.) with clear one-level-deep references. The role registry table provides a clean navigation index. | 3 / 3 |
Total | 11 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
5ff5e86
- 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.