auto

Automatically converge from goal to A-grade Seed and execute it

Quality

44%

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/auto/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 is highly actionable and well-sequenced with concrete MCP tooling guidance and validation feedback loops, but it is over-padded in places and bundles everything into one monolithic file with no progressive disclosure.

Suggestions

Move the per-host observer-delegation details and the stop_reason_code / interview-closure taxonomies into reference files and link to them from SKILL.md.

Tighten the repeated relay-loop instructions in Background monitoring UX §3 into a single canonical statement.

Surface a concise 'Quick start' / dispatch summary at the top before the detailed orchestration policy.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly operational, but the observer/relay-loop material is restated across multiple subsections and could be tightened, matching anchor 3 ('Mostly efficient but includes some unnecessary explanation or could be tightened'); not anchor 2 because it largely assumes competence rather than padding with basics.	3 / 5
Actionability	It provides concrete, executable guidance — named MCP tools (ouroboros_start_auto, ouroboros_job_wait, ouroboros_session_signal), exact arguments, a CLI-flag-to-MCP-arg table, and full call shapes — matching anchor 4 ('Mostly executable guidance; concrete code or commands with minor gaps').	4 / 5
Workflow Clarity	A clear numbered Behavior sequence and Background monitoring UX with explicit terminal/non-terminal handling, fail-closed sentinel validation, and resume feedback loops align with anchor 4 ('Clear sequence with most checkpoints present'); it is not anchor 5 because some checkpoints are implicit rather than explicit validation steps.	4 / 5
Progressive Disclosure	The skill is a single 279-line SKILL.md with no bundle files or external references, and content that could live in separate files (stop_reason taxonomy, per-host observer delegation) is inlined, matching anchor 3 ('Some structure but could be better organized; content that should be separate is inline'); section headers keep it above anchor 2.	3 / 5
	Total	14 / 20 Passed

Description

25%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 but opaque: it states a niche Ouroboros action with no natural trigger phrasing and no 'Use when' guidance. It scores well only on distinctiveness.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when the user asks to build a full product from a single goal description').

Replace jargon ('converge', 'A-grade Seed') or pair it with plain-language action verbs a user would actually say.

Spell out 2-3 concrete capabilities (interview, seed generation, repair-to-A-grade, execution) to raise specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('converge from goal to A-grade Seed') and two actions ('converge', 'execute it'), but the verbs are generic and the actions are minimally specified, matching anchor 2 ('Names the domain but actions are minimal or generic') more than anchor 3.	2 / 5
Completeness	A rough 'what' is present (converge to a Seed and execute it) but it is jargon-obscured and there is no 'when'/'Use when' guidance; per the rubric a missing 'Use when' clause caps completeness at 3, and the vague 'what' pulls it down to anchor 2.	2 / 5
Trigger Term Quality	It contains no natural user trigger phrases, only technical jargon ('converge', 'A-grade Seed'), matching anchor 1 ('No natural keywords; only technical jargon or entirely generic language').	1 / 5
Distinctiveness Conflict Risk	The Ouroboros-specific terms ('A-grade Seed', 'converge from goal') carve a clear niche with minimal overlap risk, sitting at anchor 4 ('Mostly distinct; minor overlap risk with closely related skills').	4 / 5
	Total	9 / 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/auto/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.