seed

Generate validated Seed specifications from interview results

Quality

61%

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 ./skills/seed/SKILL.md

Quality

Content

70%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 skill is a well-sequenced, highly actionable multi-step workflow with strong validation feedback loops, but it is monolithic and verbose: a 480-line body with repeated guard rails and no bundle files to offload the detailed QA-loop and lateral-thinking material.

Suggestions

Move the Wonder->Reflect->Refine->Restate cycle and ouroboros_lateral_think parsing details into a reference file (e.g. references/qa-refinement.md) and link to it from the main loop, reducing the body substantially.

De-duplicate the repeated 'do not present the seed as final' and deferred-schema-load warnings into a single stated rule referenced where needed.

Trim the explanatory prose around the python resolver (e.g. rationale on path overrides) to the essential contract, since Claude can infer standard Python-fallback behavior.

Dimension	Reasoning	Score
Conciseness	The body is procedural and dense, but several guard rails are repeated verbatim ('do not present the seed as final' appears 3+ times, deferred-schema warnings recur), so it is mostly efficient with notable tightening possible, fitting score 3 over the leaner score 4.	3 / 5
Actionability	Provides concrete executable elements (bash python resolver, full MCP argument blocks, JSON gate templates, prefs.json update script) with only minor gaps from runtime-abstract steps, matching score 4 rather than the fully-copy-paste score 5.	4 / 5
Workflow Clarity	The QA Refinement Loop gives a clear sequence with explicit validation (QA verdict), PASS/REVISE/FAIL feedback loops, max-iteration handling, and an audit-trail checklist, matching the score-5 anchor; validation is present so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist and the ~480-line body inlines large blocks (the full Wonder->Reflect->Refine->Restate cycle and lateral-think parsing) that belong in separate reference files, so it has structure but content that should be split is inline, fitting score 3.	3 / 5
	Total	15 / 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 is concise and third-person with a clear 'what', but it omits any 'Use when...' trigger guidance and offers only one main action with limited keyword variation, leaving it mid-pack across most dimensions.

Suggestions

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

List 2-3 concrete actions (e.g. 'extract requirements, calculate ambiguity score, generate Seed YAML, run QA refinement') to lift specificity and trigger coverage.

Include natural synonyms and the invocation phrase (e.g. 'seed spec', 'crystallize', 'generate seed') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Names the domain ('Seed specifications', 'interview results') and 1-2 concrete actions ('Generate', 'validated') but does not list several specific actions, matching the score-3 anchor rather than the multi-action score-4 anchor.	3 / 5
Completeness	Gives a clear 'what' ('Generate validated Seed specifications from interview results') but has no 'Use when...' trigger clause, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('Seed specifications', 'interview results') but lacks common synonyms or variations users might say, fitting the score-3 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Seed specifications from interview results) but the generic word 'seed' carries minor overlap risk with unrelated skills, placing it at score 4 rather than the minimal-conflict score 5.	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: skills/seed/SKILL.md
Commit: 80333ae

Reviewed: 3 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.