writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
Install with Tessl CLI
npx tessl i github:sc30gsw/claude-code-customes --skill writing-plans80
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 82%
↑ 3.90xAgent success when using this skill
Validation for skill structure
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'). Without knowing the skill's capabilities, Claude cannot make an informed decision about when to select it. The description reads more like a usage hint than a functional description.
Suggestions
Add explicit capability statements describing what the skill does (e.g., 'Breaks down specifications into implementation steps, creates task lists, identifies dependencies').
Include a proper 'Use when...' clause with specific trigger terms like 'plan implementation', 'break down requirements', 'create task list', 'implementation strategy'.
Specify the output or deliverable of the skill to distinguish it from other planning or code-related skills.
| 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 actual capability or output. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'spec', 'requirements', and 'multi-step task' that users might naturally say, but lacks variations and common synonyms (e.g., 'specification', 'planning', 'breakdown', 'implementation plan'). | 2 / 3 |
Distinctiveness Conflict Risk | 'Multi-step task' and 'before touching code' are extremely generic and could apply to many skills including planning, architecture, task breakdown, code review, or project management skills. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that provides excellent actionable guidance for writing implementation plans. The TDD workflow is clearly sequenced with validation steps, and the task structure template is immediately usable. Minor improvement could come from better progressive disclosure by extracting the detailed templates into reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, using bullet points and code blocks without explaining concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable examples including exact file paths, complete code snippets, specific pytest commands with expected outputs, and git commit commands. The task structure template is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 5-step TDD workflow with explicit validation checkpoints (run test to verify fail, run test to verify pass). The granularity guidance (2-5 minutes per step) and execution handoff options provide excellent sequencing. | 3 / 3 |
Progressive Disclosure | References other skills appropriately (superpowers:executing-plans, superpowers:subagent-driven-development) but the skill itself is somewhat monolithic. The plan document header and task structure could potentially be separate reference files for a cleaner overview. | 2 / 3 |
Total | 11 / 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.
- 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.