writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

Quality

46%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/writing-plans/SKILL.md

Quality

Content

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, well-structured planning skill with excellent actionability — the task structure template, anti-pattern list, and self-review checklist are all highly concrete and useful. The workflow is clearly sequenced with appropriate validation checkpoints. Minor weaknesses include some redundancy between sections (the 'Remember' section largely restates earlier content) and the content being entirely inline rather than leveraging any bundle structure for the longer template sections.

Suggestions

Remove the 'Remember' section or merge its unique points into the relevant earlier sections to eliminate redundancy and save tokens.

Consider extracting the full task structure template into a separate reference file (e.g., TASK_TEMPLATE.md) to improve progressive disclosure and keep the main skill leaner.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and provides genuinely useful guidance, but includes some redundancy (e.g., 'DRY, YAGNI, TDD, frequent commits' appears twice, and some sections like 'Remember' largely repeat earlier content). The 'No Placeholders' section is valuable but slightly verbose. Overall it respects Claude's intelligence but could be tightened.	2 / 3
Actionability	Highly actionable with concrete, copy-paste-ready templates for plan headers, task structures with exact markdown formatting, specific step examples with actual code blocks, exact commands with expected outputs, and explicit anti-patterns to avoid. The task structure template is fully executable and specific.	3 / 3
Workflow Clarity	The workflow is clearly sequenced: scope check → file structure mapping → task decomposition → plan writing with specific header → self-review checklist → execution handoff. The self-review section provides explicit validation steps (spec coverage, placeholder scan, type consistency) with clear feedback loops ('If you find issues, fix them inline'). The TDD cycle within each task is also a validation loop.	3 / 3
Progressive Disclosure	The skill references two sub-skills (subagent-driven-development, executing-plans) and a git-worktrees skill appropriately, but all content is inline in a single file. The document is moderately long and some sections (like the full task structure template) could potentially be split out. However, for a planning skill this level of inline detail is reasonable. No bundle files are provided to support further disclosure.	2 / 3
	Total	10 / 12 Passed

Description

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 weak: it provides no information about what the skill actually does, only a vague trigger condition. Without concrete actions or capabilities listed, Claude cannot meaningfully distinguish this skill from others or understand its purpose. The description reads more like a partial usage hint than a proper skill description.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Breaks down specifications into an ordered implementation plan with discrete steps, identifies dependencies, and creates a task checklist.'

Expand trigger terms with natural user language like 'plan', 'break down', 'implementation steps', 'task breakdown', 'decompose requirements', 'project planning'.

Restructure to clearly separate 'what' and 'when', e.g., 'Analyzes specifications and requirements to create step-by-step implementation plans. Use when the user has a spec, PRD, or requirements document and needs to plan the coding approach before writing code.'

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions at all. It doesn't say what the skill does—only vaguely when to use it. 'Multi-step task' and 'before touching code' are abstract and don't describe any specific capabilities.	1 / 3
Completeness	The 'what' is entirely missing—there is no description of what the skill actually does. It only provides a vague 'when' clause ('before touching code' with a spec), making both halves weak or absent.	1 / 3
Trigger Term Quality	It includes some relevant terms like 'spec', 'requirements', and 'multi-step task' that users might naturally say, but it's missing many common variations (e.g., 'planning', 'breakdown', 'implementation plan', 'design', 'architecture').	2 / 3
Distinctiveness Conflict Risk	The description is extremely generic—'multi-step task' and 'before touching code' could apply to planning, architecture, design, task decomposition, or many other skills. It would easily conflict with other planning or analysis skills.	1 / 3
	Total	5 / 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.

Repository: obra/superpowers
Commit: 6fd4507

Reviewed: 15 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.