seed

Generate validated Seed specifications from interview results

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude-plugin/skills/seed/SKILL.md

Quality

Content

77%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 and the workflow is exceptionally well-sequenced with strong validation feedback loops, but it is verbose in places and monolithic where progressive disclosure via separate reference files would help. It earns top marks on actionability and workflow clarity.

Suggestions

Move the detailed Wonder/Reflect/Refine/Restate and lateral-think persona instructions into a reference file (e.g., references/qa-refinement.md), keeping SKILL.md as an overview that links to it.

De-duplicate the 'do not present the seed as final' instruction so it appears once, and trim the IMPORTANT/CRITICAL callouts that restate the same deferred-schema guidance.

Tighten the 'Required Skill Capabilities' section, which explains runtime capabilities Claude can infer from their names.

Dimension	Reasoning	Score
Conciseness	Most content is operational Ouroboros-specific detail Claude would not already know, but there is noticeable redundancy — 'do not present the seed as final' is restated multiple times, and IMPORTANT/CRITICAL callouts plus the capabilities section could be tightened.	3 / 5
Actionability	Guidance is fully executable: concrete MCP tool-call templates with exact arguments, a copy-paste Python resolver function, JSON/YAML examples, an audit-trail format, and a runnable prefs.json update script cover the common cases.	5 / 5
Workflow Clarity	Path A/B and the QA Refinement Loop are clearly sequenced with numbered steps, explicit validation checkpoints (pass_threshold 0.90, max 5 iterations), and feedback loops (validate -> fix -> retry) with error-recovery branches for delegation and fallback modes.	5 / 5
Progressive Disclosure	The skill is a single 460-line monolithic file with no bundle; the lengthy Wonder/Reflect/Refine/Restate and lateral-think sections could live in separate reference files. External repo-file references are clearly signaled and one level deep, but content that should be split is inlined.	3 / 5
	Total	16 / 20 Passed

Description

53%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 states a clear, specific purpose but stops at a single action and omits an explicit 'when to use' trigger clause, which caps completeness and trigger-term coverage. It is distinctive within its niche.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when the user says crystallize, generate seed, or asks to turn interview results into a Seed spec').

List 1-2 additional concrete actions (e.g., '...and refine them through a QA loop') to broaden capability coverage.

Include natural synonyms/file extensions users might say (e.g., 'seed', 'spec', 'crystallize') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Names the domain ('Seed specifications') and one concrete action ('Generate... from interview results'), but offers only a single action rather than a list of several, matching the anchor for 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	The 'what' is clear ('Generate validated Seed specifications from interview results') but there is no explicit 'Use when...' trigger clause, and per the rubric guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords ('Seed specifications', 'interview results', 'generate') are present but these are domain-specific terms; common variations and synonyms a user might naturally say are missing.	3 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (validated Seed specifications derived from interview results) with minimal overlap risk against other skills, though trigger phrasing is not maximally distinct.	4 / 5
	Total	13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Q00/ouroboros
Path: .claude-plugin/skills/seed/SKILL.md
Commit: 645a2f0

Reviewed: 2 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.