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".
56
46%
Does it follow best practices?
Impact
Pending
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 implementation notes rather than a functional skill description. It focuses on architecture details (roles/, specs/, templates/) instead of explaining what the skill does or when it should be used. It lacks concrete actions, natural trigger terms, and any meaningful 'Use when...' guidance.
Suggestions
Replace architectural jargon with concrete actions the skill performs, e.g., 'Coordinates team workflows, assigns roles, tracks project milestones, manages task dependencies.'
Add a 'Use when...' clause with natural trigger terms users would actually say, e.g., 'Use when the user asks about team coordination, project planning, role assignment, or task management.'
Remove implementation details like 'roles/ + specs/ + templates/' and 'universal router' that describe file structure rather than user-facing capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract, jargon-heavy language like 'full lifecycle team skill with clean architecture', 'universal router', and 'coordinator-only' 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', 'beat model', and 'clean architecture' are internal jargon, not user-facing keywords. | 1 / 3 |
Distinctiveness Conflict Risk | The highly specific but artificial trigger 'team lifecycle v4' would unlikely conflict with other skills, but the vague domain description ('full lifecycle team skill') could overlap with any team management or project coordination skill. | 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-structured orchestration skill that serves effectively as a universal router for a multi-agent team lifecycle. Its greatest strengths are the highly actionable spawn templates, clear delegation lock enforcement, and well-sequenced wave execution engine with explicit validation checkpoints. Minor conciseness improvements could be made by consolidating some repeated patterns (supervisor coordination appears in multiple sections), but overall the content density is justified by the complexity of the orchestration task.
| 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 both in templates and again in the coordination section). The ASCII architecture diagram and extensive tables are useful but could be tighter. It mostly avoids explaining things Claude already knows, though some table entries are somewhat obvious. | 2 / 3 |
Actionability | Highly actionable with concrete spawn_agent/assign_task/close_agent call templates, specific JSON structures, exact file paths, named agent targeting examples, and precise tool-call verdicts. The delegation lock table is immediately executable as a decision matrix. Worker and supervisor spawn templates are copy-paste ready. | 3 / 3 |
Workflow Clarity | The Wave Execution Engine provides a clear 10-step sequence with explicit validation checkpoints (step 8: checkpoint verdicts, step 9: block handling with user input). The supervisor lifecycle (spawn -> wake per checkpoint -> shutdown) is clearly sequenced. Error handling table covers failure recovery including supervisor crash respawn and orphaned task reconciliation via agent health checks. | 3 / 3 |
Progressive Disclosure | SKILL.md serves as a clear router/overview pointing to one-level-deep role files (roles/<name>/role.md) and spec files (specs/pipelines.md, specs/quality-gates.md, specs/knowledge-transfer.md). The Role Registry table provides direct links. Content is appropriately split — SKILL.md handles routing and coordination patterns while delegating domain-specific instructions to role files. | 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
0f8e801
- 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.