This description is critically incomplete—it only specifies when to use the skill but never explains what the skill actually does. The absence of any concrete actions or capabilities makes it nearly impossible for Claude to confidently select this skill over alternatives. While the timing trigger ('before touching code') provides some useful context, the description needs a complete rewrite to include specific capabilities.

Suggestions

Add a clear 'what it does' clause listing specific actions, e.g., 'Breaks down specs and requirements into an ordered implementation plan with discrete tasks, dependencies, and acceptance criteria.'

Expand trigger terms to include natural user phrases like 'plan', 'break down', 'implementation steps', 'architecture', 'design doc', 'project plan', 'task breakdown'.

Rewrite in third person with both what and when, e.g., 'Analyzes specifications and requirements to produce a step-by-step implementation plan with task ordering and dependencies. Use when the user has a spec, requirements doc, or feature description and needs a plan before writing code.'

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions at all. It doesn't say what the skill does—there are no verbs describing capabilities like 'creates plans', 'breaks down tasks', or 'generates implementation steps'. It only describes when to use it, not what it does.	1 / 3
Completeness	The description only addresses 'when' (before touching code, when you have a spec) but completely omits 'what' the skill actually does. There is no explanation of the skill's capabilities or outputs.	1 / 3
Trigger Term Quality	It includes some relevant terms like 'spec', 'requirements', and 'multi-step task' that users might naturally mention. However, it's missing common variations like 'plan', 'design', 'architecture', 'breakdown', 'implementation plan', or 'project planning'.	2 / 3
Distinctiveness Conflict Risk	The phrase 'before touching code' and 'spec or requirements' provides some niche positioning around pre-coding planning, but the lack of specificity about what it actually does means it could overlap with many planning, architecture, or task-management skills.	2 / 3
	Total	6 / 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 strong, well-structured skill that provides highly actionable templates for writing implementation plans. The TDD workflow is clearly sequenced with explicit validation at each step, and the execution handoff section provides clear next-step options. Minor verbosity in the overview and some redundancy between the task structure example and the 'Remember' section are the only notable weaknesses.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but has some redundancy - the 'Remember' section repeats principles already demonstrated in the task structure template, and phrases like 'questionable taste' add flavor but not value. The overview paragraph could be tighter.	2 / 3
Actionability	Highly actionable with complete, copy-paste-ready templates including exact file path conventions, full code examples in task structure, specific pytest commands with expected outputs, and exact git commit commands. The plan document header and task structure templates are immediately usable.	3 / 3
Workflow Clarity	Excellent multi-step workflow with explicit TDD cycle (write failing test → verify failure → implement → verify pass → commit). Each step has validation checkpoints with expected outcomes, and the execution handoff provides clear branching paths with required sub-skills.	3 / 3
Progressive Disclosure	Well-structured with clear sections progressing from overview to granularity definition to templates to execution handoff. References to other skills (brainstorming, executing-plans, subagent-driven-development) are one level deep and clearly signaled with @ syntax and REQUIRED SUB-SKILL callouts.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Reviewed

1 day ago

Table of Contents

Discovery Implementation Validation