evolve

Start or monitor an evolutionary development loop

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/evolve/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 body delivers a well-sequenced, highly actionable workflow with strong validation and recovery checkpoints, but it is held back by a severely padded Frugality-proof section and no real progressive disclosure into bundle files.

Suggestions

Move the dense 'Frugality proof' block into a separate reference file (e.g. references/frugality-proof.md) and summarize the key rule inline, cutting the run-on conditional prose.

Tighten the Frugality-proof paragraph into a short bulleted checklist of PASS requirements instead of one long sentence.

Create the referenced docs/getting-started.md (or remove the dead link) and consider extracting the Key Concepts glossary into a reference file so SKILL.md stays an overview.

Dimension	Reasoning	Score
Conciseness	Most sections are appropriately dense for a complex skill, but the 'Frugality proof' block is a ~35-line run-on of padded conditional clauses that could be heavily tightened, matching anchor 3 rather than 4.	3 / 5
Actionability	Provides concrete copy-paste shell commands and specific MCP tool names with parameters plus per-action handling; the minor gap is that MCP calls are described in prose rather than as literal JSON payloads, fitting anchor 4.	4 / 5
Workflow Clarity	Path A is a numbered 8-step sequence with explicit validation checkpoints (load tools before path decision, branch on action, explicit stop conditions) and a recovery feedback loop for the failed/expired-owner case, matching anchor 5.	5 / 5
Progressive Disclosure	Section headers give some structure, but no bundle files exist, the dense Frugality-proof block is inlined content that belongs in a separate reference, and the lone docs/getting-started.md link is not a real file, fitting anchor 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 short and on-domain but terse: it states what the skill does without any explicit use-when trigger guidance. It is distinctive but lacks natural trigger terms and concrete action detail.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when the user asks to evolve, iterate, or refine an ontology/spec across generations'.

Expand actions beyond the generic 'Start or monitor' to concrete capabilities (e.g. 'iteratively refines an ontology and acceptance criteria across generations, checks lineage status, and rewinds to a previous generation').

Include common synonyms/extensions users might say ('evolve', 'evolutionary loop', 'lineage status') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names a specific domain ("evolutionary development loop") and two actions ("Start", "monitor"), but the verbs are generic and coverage is not comprehensive, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	Gives a clear "what" (start/monitor an evolutionary development loop) but has no "Use when..." trigger clause, so per the missing-trigger guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains the key phrase "evolutionary development loop" but it is niche jargon with no natural synonyms or variations a user would spontaneously say, fitting anchor 3 rather than 2 (a relevant keyword exists) or 4 (no broader coverage).	3 / 5
Distinctiveness Conflict Risk	"evolutionary development loop" is a distinctive niche with minimal conflict risk, though the terse "start or monitor" phrasing leaves minor overlap with related dev-loop skills rather than a fully distinct trigger set.	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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: Q00/ouroboros
Path: skills/evolve/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.