Use when you have a spec or requirements for a multi-step task, before touching code
65
57%
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 ./skills/writing-plans/SKILL.mdQuality
Discovery
14%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 critically fails to explain what the skill actually does - it only provides vague timing guidance ('before touching code'). The lack of concrete actions and the extremely generic language ('multi-step task') make it nearly impossible for Claude to distinguish this skill from others or understand its purpose.
Suggestions
Add explicit capability statements describing what the skill does (e.g., 'Breaks down specifications into implementation steps, creates task lists, identifies dependencies')
Expand trigger terms to include natural variations users would say: 'spec', 'specification', 'requirements doc', 'PRD', 'planning', 'task breakdown', 'implementation plan'
Restructure to follow the pattern: '[What it does]. Use when [explicit triggers].' to clearly separate capabilities from usage guidance
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions - it only describes when to use the skill ('have a spec or requirements') but never states what the skill actually does. 'Multi-step task' is extremely vague. | 1 / 3 |
Completeness | The description only addresses 'when' (before touching code, when you have specs) but completely fails to explain 'what' the skill does. There is no indication of the skill's actual capabilities or outputs. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'spec', 'requirements', and 'multi-step task' that users might naturally say, but lacks common variations like 'specification', 'planning', 'breakdown', 'implementation plan', or 'architecture'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Multi-step task' and 'before touching code' are extremely generic and could apply to countless skills including planning, architecture, design, task breakdown, or project management skills. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that provides comprehensive, actionable guidance for writing implementation plans. It demonstrates strong workflow clarity with embedded TDD validation loops, explicit self-review checklists, and clear execution handoff options. The content is concise while being thorough, with concrete templates and explicit anti-patterns to avoid.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, assuming Claude's competence as a developer. It avoids explaining basic concepts and focuses on specific, actionable guidance for plan creation. Every section earns its place. | 3 / 3 |
Actionability | Provides fully concrete guidance with exact file path conventions, complete code block templates, specific markdown structure, and copy-paste ready task formats. The 'No Placeholders' section explicitly defines what NOT to do with concrete examples. | 3 / 3 |
Workflow Clarity | Clear multi-step workflow: scope check → file structure → task decomposition → self-review → execution handoff. Each phase has explicit validation (self-review checklist) and the task structure itself embeds TDD validation loops (write test → verify fail → implement → verify pass → commit). | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections that build logically. References to sub-skills (subagent-driven-development, executing-plans) are one level deep and clearly signaled. The plan document header template and task structure template are appropriately inline since they're the core deliverable. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%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.
eafe962
Table of Contents
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.