writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
79
46%
Does it follow best practices?
Impact
82%
4.31xAverage score across 10 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/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 is critically incomplete—it only provides a vague 'when' trigger without explaining what the skill actually does. The lack of concrete actions makes it impossible for Claude to understand the skill's purpose, and the overly broad language creates high conflict risk with other skills. The description needs a fundamental rewrite to include specific capabilities.
Suggestions
Add a clear 'what' clause describing concrete actions the skill performs, e.g., 'Breaks down specs and requirements into an ordered implementation plan with discrete steps, dependencies, and acceptance criteria.'
Make the trigger terms more specific and natural by adding keywords like 'plan', 'implementation plan', 'break down', 'task breakdown', 'decompose', 'step-by-step plan'.
Narrow the scope to reduce conflict risk—specify what kind of multi-step tasks (e.g., 'feature implementation', 'refactoring') and what the output looks like (e.g., 'ordered checklist', 'implementation roadmap').
| 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 'generates', 'plans', 'breaks down', etc. 'Multi-step task' is extremely vague. | 1 / 3 |
Completeness | The description only addresses 'when' (when you have a spec/requirements before coding) 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 'before touching code' which could naturally appear in user requests. However, it misses common variations like 'plan', 'design', 'architecture', 'breakdown', 'implementation plan', etc. | 2 / 3 |
Distinctiveness Conflict Risk | 'Multi-step task' and 'before touching code' are extremely broad and could apply to many skills—planning, architecture, task decomposition, code review, etc. This would easily conflict with other skills in a large skill set. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
77%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, actionable skill that provides clear templates and workflows for writing implementation plans. Its greatest strength is the explicit TDD workflow with validation checkpoints at every step and concrete, copy-paste-ready templates. Minor weaknesses include some verbosity in the overview and the fact that all content is inline rather than leveraging separate reference files for the templates.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some redundancy - the overview paragraph explains principles that could be more terse, and phrases like 'assuming the engineer has zero context for our codebase and questionable taste' add flavor but not actionable value. The task structure template is well-formatted but the 'Remember' section partially repeats what's already shown in the template. | 2 / 3 |
Actionability | Highly actionable with concrete templates, exact file path conventions, complete code examples in the task structure, specific commands with expected outputs, and a clear naming convention for plan files. The task structure template is copy-paste ready and the execution handoff provides specific next steps. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally clear: each task is broken into explicit numbered steps with validation checkpoints (run test to verify fail, run test to verify pass), feedback loops are built into the TDD cycle, and the execution handoff provides clear branching paths. The bite-sized task granularity section explicitly defines step boundaries. | 3 / 3 |
Progressive Disclosure | The skill references other skills (superpowers:executing-plans, superpowers:subagent-driven-development, brainstorming skill) which is good progressive disclosure, but all content is inline in a single file. The plan document header, task structure, and execution handoff sections are well-organized but the skill itself is moderately long and could benefit from separating the template examples into a referenced file. | 2 / 3 |
Total | 10 / 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.
- Repository
- sc30gsw/claude-code-customes
- Commit
7aff694
- 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.