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.

Quality

53%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/workflow-tdd-plan/SKILL.md

Quality

Content

39%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill has excellent workflow clarity with well-defined phases, conditional branching, validation checkpoints, and error recovery paths. However, it is severely over-long and monolithic — cramming ~500+ lines of implementation code, diagrams, and repeated TDD principles into a single file with no progressive disclosure. The code is mostly actionable but has some incomplete sections (Phase 4) and syntax issues (Phase 7).

Suggestions

Split implementation phases into separate files (e.g., phases/phase-1-session.md, phases/phase-5-task-gen.md) and reference them from the main SKILL.md overview

Remove redundant explanations of Red-Green-Refactor — it's defined in the overview, repeated in Phase 5 instructions, Phase 6 validation, Phase 7 verification, and the 'TDD Compliance Requirements' section

Fix incomplete code in Phase 4 (undefined 'conflicts' variable, unclear ccw cli integration) and Phase 7 syntax error in the if condition

Consolidate the ASCII pipeline diagram and data flow diagram into a single concise representation — both convey largely the same information

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~500+ lines. The ASCII pipeline diagram, data flow diagram, session structure tree, and full implementation code are all included inline. Much of this could be split into separate files. The TDD principles section repeats the same Red-Green-Refactor concept multiple times across the document. The 'Compact Protection' and 'Iron Law' sections restate what's already covered.	1 / 3
Actionability	Contains substantial executable JavaScript code with concrete spawn_agent calls, file operations, and validation logic. However, Phase 4's conflict resolution code is incomplete (references undefined 'conflicts' variable, uses a 'ccw cli' command without clear integration), and Phase 7 has a syntax error in the if condition. Some code is more illustrative than truly copy-paste ready.	2 / 3
Workflow Clarity	The 7-phase pipeline is clearly sequenced with explicit conditional branching (Phase 4 only when risk ≥ medium), validation checkpoints (Phase 6 TDD structure validation with fix-and-retry loop), quality gates (Phase 7 APPROVED/CONDITIONAL/BLOCKED), and a clear confirmation gate between phases 6 and 7. Error handling table covers recovery for each failure mode.	3 / 3
Progressive Disclosure	Monolithic wall of text with no bundle files to reference. The entire implementation, all phase details, data flow diagrams, session structure, error handling, and compliance requirements are all inline in a single massive file. Content like the full implementation code, ASCII diagrams, and TDD compliance requirements should be split into separate referenced files.	1 / 3
	Total	7 / 12 Passed

Description

67%

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 technically detailed and specific about what the skill does, listing concrete pipeline stages and output artifacts. However, it reads more like internal architecture documentation than a skill description, using heavy jargon ('spawn_agent', 'multi-mode routing') that users wouldn't naturally use. The lack of an explicit 'Use when...' clause means Claude may struggle to know when to select this skill.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases like 'Use when the user wants to plan a TDD implementation, create test-driven development tasks, or generate an implementation plan with test coverage.'

Replace internal implementation details like '(spawn_agent)' and 'multi-mode routing (plan/verify)' with user-facing language describing the benefit, e.g., 'Analyzes existing code and tests to generate a structured TDD implementation plan.'

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 specifies concrete outputs (IMPL_PLAN.md, task JSONs, TODO_LIST.md).	3 / 3
Completeness	The 'what' is well-covered with the pipeline steps and outputs, but there is no explicit 'Use when...' clause or equivalent trigger guidance telling Claude when to select this skill. The 'when' is only implied by the technical context.	2 / 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 its specific TDD planning pipeline, named outputs (IMPL_PLAN.md, TODO_LIST.md), and multi-mode routing concept. Unlikely to conflict with other skills due to its very specific niche.	3 / 3
	Total	10 / 12 Passed

Validation

72%

Warnings & errors only

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: 07491b0

Reviewed: 20 days ago

Table of Contents

Discovery Implementation Validation

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.