writing-skills

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

Quality

84%

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

The canonical home for this skill is writing-skills in obra/superpowers

Quality

Content

81%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 highly actionable with concrete templates, verification commands, and a clearly sequenced TDD workflow including validation checkpoints. Its main weakness is conciseness — repeated restatements of the same principles inflate length — and a few referenced support files are not actually present in the bundle.

Suggestions

Consolidate the repeated TDD/Iron Law statements and description-guidance into a single authoritative section to reduce redundancy and trim token cost.

Either add the referenced bundle files (anthropic-best-practices.md, persuasion-principles.md, testing-skills-with-subagents.md, render-graphs.js, graphviz-conventions.dot) or remove the dangling references so navigation is complete.

Tighten the CSO section, which restates frontmatter/description rules already covered in 'SKILL.md Structure', to lift conciseness above anchor 3.

Dimension	Reasoning	Score
Conciseness	The ~650-line body is mostly high-signal (tables, code, checklists) but repeats the TDD mapping in both table and prose, restates the 'Iron Law' three times, and reiterates description guidance across the SKILL.md Structure and CSO sections, fitting anchor 3's 'mostly efficient but could be tightened'.	3 / 5
Actionability	It provides copy-paste-ready frontmatter templates, directory-layout examples, concrete bash verification commands ('wc -w skills/path/SKILL.md'), and a full checklist, matching anchor 5's fully executable guidance covering common cases.	5 / 5
Workflow Clarity	The RED-GREEN-REFACTOR cycle is explicitly sequenced with validation checkpoints (run scenarios WITHOUT skill, then WITH skill to verify compliance) and a feedback loop ('Re-test until bulletproof'), matching anchor 5's clear sequence with explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	Sections are well-organized and references are one-level-deep and clearly signaled ('See @testing-skills-with-subagents.md', 'see anthropic-best-practices.md'), but several referenced files (anthropic-best-practices.md, persuasion-principles.md, render-graphs.js) are not present in the bundle, leaving minor organization gaps that cap it at anchor 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

87%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, starts with 'Use when', and explicitly states concrete triggering conditions for creating, editing, and verifying skills. It clearly answers both what and when with low conflict risk, though trigger-term synonyms could be richer.

Dimension	Reasoning	Score
Specificity	Names the skill-authoring domain and lists three concrete actions — 'creating new skills, editing existing skills, or verifying skills work before deployment' — giving several specific actions with only minor coverage gaps, which fits anchor 4 rather than the more comprehensive anchor 5.	4 / 5
Completeness	It starts with 'Use when' and gives explicit triggering conditions that answer both what (skill authoring/editing/verifying) and when (before deployment), matching the anchor 5 example that clearly answers both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases users would say ('creating new skills', 'editing existing skills', 'verifying skills') are present with good coverage, but it lacks synonyms and file-extension variants, placing it above anchor 3 yet short of the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The skill occupies a clear niche (writing Claude skills) with distinct triggers that are unlikely to fire for unrelated skills, matching the anchor 5 example of a clear niche with minimal conflict risk.	5 / 5
	Total	18 / 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 (656 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: langbot-app/langbot-docs
Path: .agents/skills/writing-skills/SKILL.md
Commit: 159b044

Reviewed: 2 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.