workflow-plan
Planning pipeline with multi-mode routing (plan/verify/replan). Session discovery → context gathering (spawn_agent) → conditional conflict resolution → task generation (spawn_agent or N+1 parallel agents) → plan verification → interactive replan. Produces IMPL_PLAN.md, task JSONs, TODO_LIST.md.
44
33%
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/workflow-plan/SKILL.mdQuality
Discovery
27%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 is highly technical and reads like internal architecture documentation rather than a skill description meant for routing. While it lists specific pipeline steps and output artifacts, it completely lacks natural trigger terms users would use and provides no guidance on when Claude should select this skill. The jargon-heavy language would make it very difficult for Claude to match this skill to user requests.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms like 'plan implementation', 'break down project', 'create task list', 'plan tasks', 'implementation plan'.
Replace or supplement technical jargon (spawn_agent, N+1 parallel agents, multi-mode routing) with user-facing language describing the benefit, e.g., 'Breaks down complex projects into actionable tasks with dependency tracking and conflict resolution'.
Include common user phrasings that would trigger this skill, such as 'plan out the work', 'create a plan', 'organize tasks', 'project breakdown'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: session discovery, context gathering, conflict resolution, task generation, plan verification, interactive replan. Also names specific outputs: IMPL_PLAN.md, task JSONs, TODO_LIST.md. | 3 / 3 |
Completeness | Describes what it does (planning pipeline steps and outputs) but has no 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when...' caps completeness at 2, and the 'when' is entirely absent, warranting a 1. | 1 / 3 |
Trigger Term Quality | Uses highly technical jargon like 'multi-mode routing', 'spawn_agent', 'N+1 parallel agents', 'conditional conflict resolution' — these are not terms a user would naturally say. Missing natural keywords like 'plan', 'create plan', 'implementation plan', 'break down tasks', 'project planning'. | 1 / 3 |
Distinctiveness Conflict Risk | The specific output artifacts (IMPL_PLAN.md, task JSONs, TODO_LIST.md) and the pipeline terminology create some distinctiveness, but the overall 'planning' domain is broad and could overlap with other planning or task management skills. The jargon makes it somewhat specific but not clearly delineated for selection purposes. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a comprehensive and well-structured workflow with clear phase sequencing, conditional branching, and validation gates. However, it is severely over-long for a SKILL.md, inlining hundreds of lines of implementation code that should be in separate files or scripts. Several code sections are incomplete or contain syntax issues that reduce actionability, and the monolithic structure wastes context window tokens.
Suggestions
Extract the detailed JavaScript implementation for each phase into separate referenced files (e.g., phases/phase1-session.js, phases/phase2-context.js) and keep only the workflow overview, key decision points, and agent instruction templates in SKILL.md.
Fix incomplete code sections: define the `conflicts` variable in Phase 3, resolve the syntax error in Phase 5's conditional, and ensure `verificationReport`/`qualityGate` are properly assigned from CLI output.
Remove the redundant data flow diagram — the ASCII pipeline diagram already conveys the same information more completely.
Move the session structure file tree and error handling table to a referenced REFERENCE.md file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It includes extensive inline code that could be in separate files, redundant ASCII diagrams (pipeline + data flow), and over-explains session discovery logic. Much of the JavaScript is implementation detail that bloats the context window without adding proportional instructional value. | 1 / 3 |
Actionability | The code blocks are fairly detailed and provide concrete guidance, but several sections contain incomplete/pseudo-code (Phase 3's conflict handling has undefined variables like `conflicts`, Phase 5 has `/* auto-verify from Phase 4 */` syntax errors and undefined `verificationReport`/`qualityGate` variables). The CLI commands in Phases 3 and 5 reference `ccw cli` with complex inline prompts that aren't fully executable as written. | 2 / 3 |
Workflow Clarity | The multi-phase pipeline is clearly sequenced with explicit conditional branching (conflict risk gate), validation checkpoints (plan confirmation gate, output existence checks), backup before replan, and a clear separation of modes. The ASCII diagram, data flow, and phase-by-phase breakdown make the workflow unambiguous with proper feedback loops. | 3 / 3 |
Progressive Disclosure | The entire implementation is monolithically inlined in a single file with no references to supporting files despite the complexity warranting them. Phase implementations, agent instruction templates, session structure details, and the error handling table could all be split into separate referenced documents. No bundle files are provided to offload any of this content. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (632 lines); consider splitting into references/ and linking | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
227244f
- 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.