team-lifecycle-v4
Full lifecycle team skill with clean architecture. SKILL.md is a universal router — all roles read it. Beat model is coordinator-only. Structure is roles/ + specs/ + templates/. Triggers on "team lifecycle v4".
44
46%
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-lifecycle-v4/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description reads like internal developer notes about the skill's architecture rather than a functional description for skill selection. It fails to communicate what the skill does, when it should be used, or provide natural trigger terms a user would employ. The description is almost entirely structural metadata with no actionable content.
Suggestions
Replace architectural notes with concrete actions the skill performs (e.g., 'Manages team roles, assigns tasks, tracks project milestones, generates status reports').
Add a 'Use when...' clause with natural trigger terms users would actually say, such as 'team management', 'project coordination', 'role assignment', or 'sprint planning'.
Remove internal implementation details like 'SKILL.md is a universal router' and 'Structure is roles/ + specs/ + templates/' that describe file organization rather than user-facing capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'full lifecycle team skill with clean architecture' and 'universal router' without describing any concrete actions the skill performs. No specific capabilities are listed. | 1 / 3 |
Completeness | The 'what' is extremely vague — it never explains what the skill actually does. The 'when' is limited to the artificial trigger phrase 'team lifecycle v4' with no real-world usage context. Both dimensions are very weak. | 1 / 3 |
Trigger Term Quality | The only explicit trigger is 'team lifecycle v4', which is not a natural phrase any user would say. Terms like 'universal router', 'coordinator-only', and 'roles/ + specs/ + templates/' are internal jargon, not user-facing keywords. | 1 / 3 |
Distinctiveness Conflict Risk | The very specific (if artificial) trigger phrase 'team lifecycle v4' and mention of a particular file structure (roles/ + specs/ + templates/) provide some distinctiveness, but the overall vagueness of 'full lifecycle team skill' could overlap with many team management or project skills. | 2 / 3 |
Total | 5 / 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-crafted orchestration skill that serves as an effective router for a complex multi-agent system. Its greatest strengths are actionability (concrete API call templates, exact file paths, explicit tool permission tables) and workflow clarity (sequenced wave execution with validation checkpoints and error recovery). Minor verbosity exists in some repeated patterns and the model selection table, but the complexity of the domain largely justifies the length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly dense and information-rich, but includes some redundancy (e.g., the supervisor spawn/wake/shutdown pattern is explained twice across sections, and the delegation lock table restates what could be a single rule). The ASCII architecture diagram and model selection guide add bulk but are mostly justified for a complex orchestration skill. Some tightening is possible. | 2 / 3 |
Actionability | Highly actionable with concrete spawn_agent/followup_task/close_agent call templates, specific JSON-like API invocations, exact file paths, named agent targeting examples, and a complete delegation lock table with explicit ALLOWED/BLOCKED verdicts. The wave execution engine is a step-by-step executable algorithm. | 3 / 3 |
Workflow Clarity | The Wave Execution Engine provides a clear 10-step sequence with explicit validation checkpoints (skip failed deps, handle block verdicts, timeout cascades). The supervisor lifecycle (spawn -> wake -> shutdown) is clearly sequenced. Error handling table covers failure modes with specific resolutions including respawn and recovery. Feedback loops are present (block -> user input -> override/revise/abort). | 3 / 3 |
Progressive Disclosure | SKILL.md acts as a clear router/overview with well-signaled one-level-deep references to roles/ (8 role files linked in the registry table) and specs/ (3 spec files linked at bottom). Content is appropriately split: the router contains orchestration logic while domain-specific instructions live in role files. Navigation is straightforward via the Role Registry table and Specs Reference section. | 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.