seed

Generate validated Seed specifications from interview results

Quality

63%

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 ./.claude-plugin/skills/seed/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.

The content is highly actionable and its workflow is clearly sequenced with strong validation checkpoints, but it is verbose and ships as a monolithic single file with no progressive disclosure into bundle files. Tightening repetition and offloading long reference-style sections would lift the two 2-scoring dimensions.

Suggestions

Move the long QA Refinement Loop detail, the audit-trail format block, and the full example Seed YAML into separate reference bundle files under references/, keeping SKILL.md as an overview with one-level-deep links.

Tighten repeated warnings — collapse the duplicated 'do not present as final / IMPORTANT / CRITICAL' statements into a single canonical rule referenced where needed.

Cut the Double Diamond conceptual aside ('The seed sits inside the Define diamond...') or compress it to one line, since it explains workflow philosophy Claude can infer from the loop structure.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and accurate, but it is verbose: repeated 'IMPORTANT/CRITICAL — do not present as final' warnings, a Double Diamond conceptual aside, and restated loop-boundary rules could be tightened; it is not a 1 (no basic-concept padding) but not the lean 3 either.	2 / 3
Actionability	It gives exact MCP tool names, full argument blocks, the literal quality_bar string, JSON ask_user gate examples, an executable bash prefs script, and a complete Seed YAML example — copy-paste ready and fully executable.	3 / 3
Workflow Clarity	The flow is explicitly sequenced (Load MCP Tools -> Path A/B -> QA Refinement Loop) with concrete validation checkpoints (pass_threshold 0.90, PASS/REVISE/FAIL branches, max-iteration cap of 5, and error-recovery feedback), matching the anchor with explicit validation and feedback loops.	3 / 3
Progressive Disclosure	No bundle files exist and all content lives inline in one ~450-line file; section structure is good, but detail that could be split (the QA loop, audit-trail format, example output) is inline, and the only references are external one-level repo files, so it is not the well-signaled one-level-bundle 3.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 third-person and states a clear, specific action, but it is a single action with no 'Use when...' trigger guidance and lacks the natural trigger terms users would say. It clears the bar over vague fluff but stops short of the explicit-trigger, multi-action bar.

Suggestions

Add a 'Use when...' clause naming explicit triggers, e.g. 'Use when the user says crystallize, generate seed, or wants to turn interview results into a Seed specification.'

List multiple concrete actions (e.g. 'generate, refine through QA, and validate Seed specifications from interview results') to raise specificity.

Include the natural trigger term 'crystallize' and 'seed'/'generate seed' directly in the description rather than only as body keywords.

Dimension	Reasoning	Score
Specificity	The phrase 'Generate validated Seed specifications from interview results' names the domain (Seed specifications) and one concrete action (Generate) plus its input source, but offers only a single action rather than the multiple specific actions required for a 3.	2 / 3
Completeness	It clearly answers 'what does this do' (generate validated Seed specs from interview results) but provides no 'Use when...' clause or equivalent explicit 'when' guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant keywords ('Seed specifications', 'interview results') but omits the natural trigger terms a user would actually say ('crystallize', 'generate seed') that only appear in the body, so it has some relevant keywords but misses common variations.	2 / 3
Distinctiveness Conflict Risk	The Ouroboros-seed-from-interviews niche is reasonably specific, but with no explicit distinct triggers in the description it could still overlap with sibling Ouroboros skills, matching 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 12 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: f09fa36

Reviewed: about 3 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.