writing-plans

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

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/superpowers/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 highly actionable planning methodology with concrete templates, executable examples, and an explicit self-review validation loop. Its main weakness is mild redundancy and that all content is inline with no progressive disclosure into separate reference files.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and avoids explaining concepts Claude already knows (TDD/DRY/YAGNI are used, not defined), but DRY/YAGNI/TDD/frequent-commits is restated across the Overview and Remember sections and the File Structure section editorializes somewhat.	2 / 3
Actionability	It provides copy-paste-ready artifacts: an exact plan document header, a full task template with executable python/pytest/git commands and expected output, exact save paths, and an exact execution-handoff script.	3 / 3
Workflow Clarity	The workflow is clearly sequenced (Overview through Execution Handoff) and includes an explicit Self-Review validation checklist plus TDD verify-fail/verify-pass checkpoints as feedback loops.	3 / 3
Progressive Disclosure	Sections are well-organized and the referenced skills are one-level invocations, but everything lives in a single ~150-line file with no bundle references; the detailed plan-header and task-structure templates could be split out to keep SKILL.md leaner.	2 / 3
	Total	10 / 12 Passed

Description

22%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description excels at stating when to invoke the skill via an explicit "Use when..." trigger, but it omits what the skill actually does, leaving its capabilities implicit. Adding a concrete action clause (e.g. "Write detailed, bite-sized implementation plans...") would raise both specificity and completeness.

Suggestions

Add a concrete what-it-does clause before the trigger, e.g. "Write detailed, bite-sized implementation plans from a spec, before touching code. Use when..."

Include more natural trigger variations users would actually say, such as "implementation plan", "plan out", or "break down this task".

Make the skill's output explicit (e.g. "produces a task-by-task plan document with file paths, code, and test steps") to distinguish it from adjacent planning skills.

Dimension	Reasoning	Score
Specificity	The description states only the trigger condition ("have a spec or requirements for a multi-step task, before touching code") and names no concrete actions the skill performs; per the guideline not to infer, the act of writing plans is not explicitly stated here.	1 / 3
Completeness	It has an explicit "Use when..." clause answering the "when", but the "what does this skill do" is entirely absent from the description field — rubric score 1 covers "missing what OR when".	1 / 3
Trigger Term Quality	Phrases like "spec", "requirements", "multi-step task", and "before touching code" are reasonably natural trigger words, but common variations a user might actually say (e.g. "implementation plan", "plan out", "break down this task") are missing.	2 / 3
Distinctiveness Conflict Risk	The "spec/requirements for a multi-step task, before touching code" framing carves a planning niche, but it can still overlap with the sibling superpowers planning skills (brainstorming, executing-plans, subagent-driven-development) referenced in the body.	2 / 3
	Total	6 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/superpowers/skills/writing-plans/SKILL.md
Commit: 11c74d6

Reviewed: about 10 hours 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.