evolve

Start or monitor an evolutionary development loop

Quality

67%

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/evolve/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 with clear, well-sequenced workflows and feedback loops. Its main weaknesses are a padded, repetitive MCP-loading guard section and a broken/out-of-band reference to docs/getting-started.md given no bundle files are present.

Dimension	Reasoning	Score
Conciseness	The body is largely operational and concrete, but the "CRITICAL — deferred-schema guard" section is heavily padded with repeated IMPORTANT/CRITICAL emphasis and restates the load-before-every-call rule several times, so it could be tightened.	2 / 3
Actionability	It gives exact MCP tool names and parameters, specific CLI commands (ooo evolve "…", --no-execute, --status <lineage_id>, --rewind), and concrete tool-discovery query strings, yielding copy-paste-ready guidance.	3 / 3
Workflow Clarity	The multi-step process is clearly numbered with a Path A/B decision, explicit action-response handling (continue/converged/stagnated/exhausted/failed), feedback loops, and validation checkpoints (load tools before deciding, check action, repeat until non-continue).	3 / 3
Progressive Disclosure	No bundle files exist and the ~140-line body is a single inline document; it references docs/getting-started.md, which is not present in the bundle, so navigation is not clearly signaled against the actual structure.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 occupies a clear niche, but it lacks explicit "when to use" trigger guidance and leans on jargon rather than natural user phrasing. Adding a Use-when clause and more natural trigger terms would materially improve it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to start, monitor, or rewind an evolutionary development loop, or mentions evolving an ontology/design across generations."

Replace or supplement the jargon noun with natural trigger terms users would actually say (e.g., "evolve a design", "iterate on requirements", "ontology refinement loop").

Reflect the full capability set surfaced in the body — start, monitor (status), and rewind — so specificity is comprehensive rather than partial.

Dimension	Reasoning	Score
Specificity	The phrase "Start or monitor an evolutionary development loop" names the domain (evolutionary development loop) and two actions (start, monitor), but omits other capabilities the body documents (rewind, status) and is not comprehensive, matching the level-2 anchor.	2 / 3
Completeness	It states what the skill does (start/monitor an evolutionary loop) but provides no "Use when…" clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	"Start" and "monitor" are natural action verbs, but the core noun phrase "evolutionary development loop" is niche jargon with no common variations a user would naturally say, so it falls short of full coverage.	2 / 3
Distinctiveness Conflict Risk	"Evolutionary development loop" is a specialized, distinctive niche with clear triggers unlikely to fire for unrelated skills, matching the level-3 anchor.	3 / 3
	Total	9 / 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: Q00/ouroboros
Path: .claude-plugin/skills/evolve/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.