CtrlK
BlogDocsLog inGet started
Tessl Logo

capability-evolver

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.

53

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

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

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-organized, actionable API reference with concrete executable examples, but it ignores its own bundled scripts, duplicates configuration between frontmatter and body, and omits explicit validation checkpoints for the destructive solidify/rollback evolution flow. It is a competent reference that underuses progressive disclosure.

Suggestions

Add a section linking to and briefly describing the 20 bundled scripts in scripts/ (e.g., what a2a_export.js, gep_append_event.js, validate-suite.js do) so the bundle is navigable rather than orphaned.

Document the core evolution workflow as an explicit numbered sequence with validation checkpoints (analyze -> propose -> review -> solidify -> verify -> rollback-on-failure) rather than leaving solidify/rollback implied in the Safety bullets.

Remove the duplicated Configuration table or the frontmatter env_declarations so environment config lives in one place.

DimensionReasoningScore

Conciseness

The body is a lean API reference (tight request/response code blocks, tables, minimal prose) that avoids explaining concepts Claude already knows, but the Configuration section duplicates the frontmatter env_declarations and the Message Types table re-states info already shown in the API sections, so it could be tightened.

2 / 3

Actionability

It provides copy-paste-ready HTTP examples with request bodies and responses ('POST {PROXY_URL}/mailbox/send', '{"type": ..., "payload": {...}}'), concrete run commands ('EVOMAP_PROXY=1 node index.js --loop', 'node index.js --review'), and a config table with defaults — fully executable guidance.

3 / 3

Workflow Clarity

Sequences exist (asset submit then 'Later, poll for the result'; task claim then poll for claim result), but the core destructive evolution/solidify flow (which writes to src/**) is never laid out as an explicit validate-then-proceed sequence with checkpoints, and the judging guidelines cap workflow_clarity at 2 when destructive operations lack validation steps.

2 / 3

Progressive Disclosure

The body has clean section organization, but it never references or navigates to the 20 bundled scripts/ files or assets (the bundle is orphaned), and the inline API reference is content that could be split into separate reference files — 'some structure but references not clearly signaled; content that should be separate is inline'.

2 / 3

Total

9

/

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 in correct third person and stakes out a distinctive niche, but it lacks an explicit 'when to use' trigger and leans heavily on project-specific jargon that limits natural trigger-term coverage. It is solid but not exemplary.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., when the user wants an AI agent to improve itself from runtime history).

Replace or gloss jargon like 'protocol-constrained evolution' and 'EvoMap Hub' with natural user-facing terms such as 'self-improve', 'evolve', or 'optimize an agent'.

Expand the action list with more concrete, tangible verbs (e.g., 'detect failing runs', 'generate patches', 'roll back failed changes') to raise specificity.

DimensionReasoningScore

Specificity

It names the domain ('self-evolution engine for AI agents') and several actions ('Analyzes runtime history to identify improvements', 'applies protocol-constrained evolution', 'Communicates with EvoMap Hub via local Proxy mailbox'), but 'protocol-constrained evolution' is abstract jargon rather than a concrete, comprehensively enumerated action list, so it falls short of the multiple-specific-concrete-actions anchor.

2 / 3

Completeness

It clearly answers 'what' (analyze history, apply evolution, communicate via proxy) but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

'self-evolution engine for AI agents' supplies a couple of natural keywords, but the description is dominated by ecosystem-specific jargon ('EvoMap Hub', 'local Proxy mailbox', 'protocol-constrained evolution') that users would rarely say verbatim, leaving common variations uncovered.

2 / 3

Distinctiveness Conflict Risk

The EvoMap/self-evolution niche with Proxy mailbox communication is a clear, narrow domain unlikely to be confused with or trigger for unrelated skills.

3 / 3

Total

9

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
EvoMap/evolver
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.