workflow-tdd-plan
TDD planning pipeline with multi-mode routing (plan/verify). Session discovery → context gathering (spawn_agent) → test coverage analysis (spawn_agent) → conditional conflict resolution → TDD task generation (spawn_agent) → structure validation → interactive verification. Produces IMPL_PLAN.md with Red-Green-Refactor cycles, task JSONs, TODO_LIST.md.
56
48%
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-tdd-plan/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 is highly specific about its internal pipeline and outputs, making it distinctive, but reads more like internal architecture documentation than a skill description meant for routing. It completely lacks 'Use when...' guidance, and its heavy use of implementation jargon (spawn_agent, multi-mode routing) makes it harder for Claude to match against natural user requests. The description would benefit greatly from user-facing language and explicit trigger conditions.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to plan an implementation using test-driven development, create a TDD plan, or generate test-first task breakdowns.'
Replace internal implementation details like '(spawn_agent)' and 'multi-mode routing (plan/verify)' with user-facing language describing the benefit, e.g., 'Analyzes existing test coverage and generates a structured TDD implementation plan.'
Include natural trigger terms users would say, such as 'test-driven development', 'TDD plan', 'implementation plan', 'test-first approach', 'red-green-refactor workflow'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: session discovery, context gathering, test coverage analysis, conflict resolution, TDD task generation, structure validation, interactive verification. Also names specific outputs (IMPL_PLAN.md, task JSONs, TODO_LIST.md). | 3 / 3 |
Completeness | Describes what it does in detail but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause should cap completeness at 2, and the 'when' here is not even implied clearly, warranting a 1. | 1 / 3 |
Trigger Term Quality | Contains relevant terms like 'TDD', 'test coverage', 'Red-Green-Refactor', and 'IMPL_PLAN.md', but uses heavy technical jargon ('multi-mode routing', 'spawn_agent', 'conditional conflict resolution') that users wouldn't naturally say. Missing common user phrases like 'write tests first', 'test-driven', 'implementation plan'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: TDD planning pipeline producing specific artifacts (IMPL_PLAN.md, TODO_LIST.md, task JSONs). Unlikely to conflict with other skills due to its very specific domain and output format. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill demonstrates excellent workflow clarity with well-defined phases, conditional branching, validation checkpoints, and error recovery paths. However, it is excessively verbose — the three large diagrams (pipeline, data flow, session structure) heavily overlap, and TDD requirements are stated multiple times. Code examples are mostly concrete but contain some incomplete/broken sections (Phase 4's undefined variables, Phase 7's syntax error), reducing actionability.
Suggestions
Reduce redundancy by removing at least one of the three diagrams (pipeline, data flow, session structure) — the pipeline diagram alone conveys the workflow; the data flow and session structure sections largely restate the same information.
Fix incomplete code in Phase 4 (undefined `conflicts` variable, unclear CLI tool integration) and Phase 7 (syntax error in the conditional) to make examples truly executable.
Extract the TDD Compliance Requirements section — it restates rules already embedded in Phase 5's agent instructions and Phase 6's validation logic. A single authoritative statement suffices.
Consider splitting detailed phase implementations into separate referenced files (e.g., phases/phase-2-context.md) to keep the main skill as a concise overview with navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines. The massive ASCII pipeline diagram, the full data flow diagram, and the complete session structure tree all duplicate information. The TDD compliance requirements section at the end restates what's already embedded in Phase 5 and Phase 6. Much of the code could be condensed significantly. | 1 / 3 |
Actionability | The code examples are fairly concrete with JavaScript implementations for each phase, but several are incomplete or have issues — Phase 4 references an undefined `conflicts` variable, Phase 7 has a syntax error (`if (mode === 'verify' || /* auto-verify */)`), and the Phase 4 CLI command references an external tool (`ccw cli`) without clear setup. The spawn_agent instructions are detailed but the actual agent types and their capabilities are assumed. | 2 / 3 |
Workflow Clarity | The multi-step workflow is exceptionally well-sequenced with clear phase numbering, conditional branching (Phase 4 only when conflict risk ≥ medium), explicit validation in Phase 6 with a fix-and-retry feedback loop, and a clear confirmation gate before verification. The error handling table provides recovery strategies for each failure mode. | 3 / 3 |
Progressive Disclosure | All content is monolithically inlined in a single massive file. The ASCII diagrams, data flow, session structure, all 7 phase implementations, error handling, and TDD compliance requirements are all in one document. There are no references to separate files for detailed phase instructions, agent configurations, or the TDD compliance rules — content that would benefit from being split out. | 2 / 3 |
Total | 8 / 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 (754 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
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.