writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Quality

71%

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 ./skills/writing-skills/SKILL.md

Quality

Content

63%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 delivers strong, non-obvious authoring guidance with concrete examples and a clear TDD-derived workflow, but it is notably redundant, inlines content that belongs in separate files, and references five supporting files (including its core testing methodology) that are not bundled. It also uses @-links despite explicitly forbidding them in its own guidance.

Suggestions

Bundle or inline the referenced files — especially @testing-skills-with-subagents.md, which holds the skill's core methodology — so no reference dangles; alternatively inline the essential testing steps directly in SKILL.md.

Deduplicate the RED-GREEN-REFACTOR explanation (present in the mapping table, the dedicated section, and 'The Bottom Line') into a single canonical statement and remove the duplicate '### 4.' Cross-Referencing heading.

Follow the skill's own anti-@-link rule: replace '@graphviz-conventions.dot' and '@testing-skills-with-subagents.md' with plain skill-name references to avoid force-loading context.

Dimension	Reasoning	Score
Conciseness	Most content is valuable skill-authoring guidance, but RED-GREEN-REFACTOR is explained three times (mapping table, dedicated section, 'Bottom Line'), the description guidance and Iron Law are repeated, gerunds and flowcharts are over-explained, and a duplicate '### 4.' heading exists — noticeably tightenable but not padded fluff.	3 / 5
Actionability	Concrete good/bad YAML and description examples, directory structures, a wc -w verification command, and a full creation checklist give mostly executable guidance; the gap is that the core testing methodology is deferred to @testing-skills-with-subagents.md rather than specified here.	4 / 5
Workflow Clarity	The RED→GREEN→REFACTOR sequence is clearly ordered with validation checkpoints (run baseline, verify compliance, re-test until bulletproof), feedback loops, and a checklist, but the concrete execution of those validation steps is deferred to a missing reference, a minor validation gap.	4 / 5
Progressive Disclosure	Section structure exists and references are explicitly signaled, but all five referenced files (anthropic-best-practices.md, persuasion-principles.md, @graphviz-conventions.dot, render-graphs.js, @testing-skills-with-subagents.md) are absent from the bundle, leaving dangling references, and heavy content (CSO, rationalization tables, testing methodology) is inlined rather than split.	3 / 5
	Total	14 / 20 Passed

Description

78%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 is well-formed: third person, explicit "Use when" trigger, three concrete lifecycle actions, and a distinct niche with low conflict risk. Its main limitation is that the 'what' is folded into the trigger conditions rather than stated separately, and a few natural synonyms are absent.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — "creating new skills, editing existing skills, or verifying skills work" — which exceeds the 1-2 action anchor but stops short of comprehensive granular operations, fitting the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	The explicit "Use when" clause clearly answers when, and the action verbs convey what, but the 'what' is merged into the trigger rather than stated separately as in the anchor-5 example, leaving it one step below fully explicit.	4 / 5
Trigger Term Quality	Natural phrases a user would say ("creating new skills", "verifying skills work", "before deployment") give good coverage, but synonyms like "writing"/"authoring"/"building skills" are missing, so it is not the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Skill authoring is a clear niche and triggers like "creating new skills" / "verifying skills work before deployment" are distinct with minimal overlap risk, matching the clear-niche anchor.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (671 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: lucianghinda/superpowers-ruby
Path: skills/writing-skills/SKILL.md
Commit: 99fac3d

Reviewed: 6 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.