writing-plans

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

Quality

56%

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 ./.cursor/skills/writing-plans/SKILL.md

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, highly actionable instruction skill: concrete templates, exact commands, expected outputs, and a clearly sequenced workflow with an explicit execution handoff. Its only real weaknesses are mild redundancy in the Remember section and a missing self-review checkpoint for the produced plan. Progressive disclosure is handled acceptably for a single-file skill of this size.

Dimension	Reasoning	Score
Conciseness	The body is lean and instructional — templates, exact paths, and commands with almost no explanation of concepts Claude already knows. Minor trimming is possible: the 'Remember' section ("Exact file paths always", "DRY, YAGNI, TDD, frequent commits") restates points already made in Overview and Task Structure, which keeps it below the 'every token earns its place' anchor.	4 / 5
Actionability	Guidance is fully executable and copy-paste ready: a complete plan-header template, a full task template with real test code, exact pytest commands with expected outputs ('Expected: FAIL with "function not defined"'), exact git commit commands, and a concrete save path (docs/plans/YYYY-MM-DD-<feature-name>.md). This matches the top anchor for executable, example-covered guidance.	5 / 5
Workflow Clarity	The overall sequence is clear (announce → write plan → save → offer execution handoff → dispatch to sub-skills) and the task template embeds explicit validation checkpoints (run test to verify it fails, verify it passes). It sits at 4 rather than 5 because the plan-authoring workflow itself has no checkpoint for reviewing the finished plan (e.g., verifying file paths exist or tasks are genuinely bite-sized) — a minor validation gap.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), so all content lives inline; at ~115 well-sectioned lines with clear headers (Overview, Task Structure, Execution Handoff) the structure is good and content is appropriately placed. It does not reach 5 because the two full templates could arguably live in a references file, and cross-skill references ('superpowers:executing-plans', 'superpowers:subagent-driven-development') are named but not clearly signaled as external skill dependencies.	4 / 5
	Total	17 / 20 Passed

Description

31%Weight 40%Scale 1-5

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 provides a reasonable trigger condition but completely omits what the skill does, making it impossible for a user (or Claude) to know from the description alone that this skill produces implementation plan documents. It reads as half of a good description. The missing 'what' is the dominant weakness and drags every other dimension down.

Suggestions

State the capability explicitly, e.g., 'Writes comprehensive implementation plans as bite-sized, TDD-style tasks with exact file paths, code, and commands', followed by the existing 'Use when...' clause.

Add natural trigger synonyms users would actually say, such as 'implementation plan', 'plan this feature', or 'break this spec into tasks', to improve trigger-term coverage.

Clarify the deliverable in the description (plans saved to docs/plans/YYYY-MM-DD-<feature>.md) to sharpen distinctiveness against generic planning or brainstorming skills.

Dimension	Reasoning	Score
Specificity	The description ("Use when you have a spec or requirements for a multi-step task, before touching code") names no concrete action whatsoever — it never states what the skill does (e.g., writes implementation plans). This matches the anchor 'Entirely vague; no concrete actions' even more closely than score 2's 'names the domain', since neither domain nor actions are stated.	1 / 5
Completeness	Only the 'when' is present ("Use when you have a spec or requirements..."); the 'what' — that this skill writes detailed, bite-sized implementation plan documents — is entirely absent. This matches anchor 2 ('only when is present without what') and is below anchor 3, which requires a clear 'what'.	2 / 5
Trigger Term Quality	Phrases like "spec", "requirements", "multi-step task", and "before touching code" are natural things a user would say, but common variations such as "implementation plan", "plan this feature", or "design" are missing. This lands at 'some relevant keywords but missing common variations or synonyms' rather than score 4's good coverage.	3 / 5
Distinctiveness Conflict Risk	The trigger (has a spec, pre-implementation) is somewhat specific, but "multi-step task" is broad and would overlap with planning, brainstorming, or execution skills in a typical skill suite. It fits 'somewhat specific but could still overlap with similar skills' rather than score 4's 'mostly distinct'.	3 / 5
	Total	9 / 20 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: revokslab/ShipFree
Path: .cursor/skills/writing-plans/SKILL.md
Commit: 94c4be7

Reviewed: 7 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.