CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

evolve

Start or monitor an evolutionary development loop

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/evolve/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary operational skill document: dense, tool-specific, and free of filler, with a fully sequenced workflow that enumerates every outcome branch, validation gates, and error-recovery loops. The only minor improvement would be showing one concrete tool-call example payload.

DimensionReasoningScore

Conciseness

The body is purely operational — every line carries Ouroboros-specific instructions (deferred-schema loading strings, action-value handling, numeric thresholds like "ambiguity ≤ 0.2" and "less than 0.01") with zero padding or explanation of concepts Claude already knows. This matches the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Guidance is highly concrete: named MCP tools with parameters (ouroboros_evolve_step with lineage_id, seed_content, execute), exact discovery strings ("+ouroboros evolve"), copy-pasteable CLI examples, and explicit values for every decision branch. Minor gaps (no example tool-call payloads; "until ambiguity ≤ 0.2" doesn't state where the value is read from) keep it at anchor 4 rather than 5.

4 / 5

Workflow Clarity

The workflow is a clearly numbered sequence (interview → seed → evolve_step → act on action) with explicit handling for every action value, validation checkpoints (QA verdict scores, "never report convergence before a converged action"), and feedback loops for error recovery (stagnated → hand off to ooo unstuck; failed → confirm owner death then a single recover_expired_claim: true call). This matches the top anchor with feedback loops and error-recovery guidance.

5 / 5

Progressive Disclosure

No bundle files exist, and the self-contained ~60-line body is well organized into Usage, Start, Status, Rewind, Benchmark control, and Fallback sections with the single external link appropriately placed. Per the rubric's simple-skill note, well-organized sections with no need for external references warrant a 5.

5 / 5

Total

19

/

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, third-person, and distinct, but it only weakly communicates what the skill actually does and gives no guidance on when to invoke it. Adding a 'Use when...' clause with natural trigger terms would substantially improve it.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to start, check, or rewind an evolutionary refinement loop for a project's ontology and acceptance criteria.'

State what the loop actually does (refine ontology and acceptance criteria across generations until a convergence gate passes) instead of relying on the opaque phrase 'evolutionary development loop'.

Include natural trigger terms and synonyms users would say, such as 'evolve', 'evolutionary loop', 'lineage', or 'iterate on acceptance criteria'.

DimensionReasoningScore

Specificity

"Start or monitor an evolutionary development loop" names the domain and two actions, matching the anchor for naming a domain plus 1-2 concrete actions that are not comprehensive. It stays at 3 because only two generic verbs are listed (not the several specific actions of anchor 4), yet it goes beyond merely naming a domain (anchor 2).

3 / 5

Completeness

A 'what' is stated ("Start or monitor an evolutionary development loop") but there is no 'when' or trigger guidance anywhere, which per the guidelines caps completeness at 3. It is above anchor 2 because the 'what' is present and clear rather than vague or absent.

3 / 5

Trigger Term Quality

Relevant keywords exist ("evolutionary", "development loop", "monitor") but common natural variations users would actually say ("evolve", "iterate on acceptance criteria", "refine ontology") are missing, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"Evolutionary development loop" is a niche, tool-specific concept with minimal overlap risk against other skills, fitting 'mostly distinct; minor overlap risk'. It falls short of anchor 5, which pairs distinct triggers with concrete action detail this thin description lacks.

4 / 5

Total

13

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Q00/ouroboros

Path

skills/evolve/SKILL.md

Reviewed

Table of Contents

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.