CtrlK
BlogDocsLog inGet started
Tessl Logo

self-evolving-single-agent

Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or improve itself over time without becoming a multi-agent team.

75

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A concise, well-sequenced instruction skill that names specific files and includes an approval-gate checkpoint. Its main weakness is actionability: it defers the detailed research-gate procedure to a non-bundled reference and lists output files without specifying their contents.

Suggestions

Inline a brief summary of the research-gate procedure (or bundle docs/builder-interview-research-gate.md) so the core step is actionable without an external file.

Add one-line templates or required fields for each docs/*.agentlas file so 'add these files' becomes concrete guidance rather than a bare file list.

Make the referenced docs explicitly inputs vs. outputs so navigation is unambiguous.

DimensionReasoningScore

Conciseness

The body is a lean ~30 lines with no explanation of concepts Claude already knows; every step is directive and assumes competence, matching the 'lean and efficient' anchor.

3 / 3

Actionability

It names concrete artifacts (e.g. ".agentlas/memory-map.json", "docs/builder-interview.md") and a specific "8-12 question" batch, but the core research-gate procedure is deferred to an unbundled docs/builder-interview-research-gate.md and files are listed to "add" without their contents — concrete but incomplete.

2 / 3

Workflow Clarity

A clear 7-step sequence is present with an explicit approval-gate checkpoint (step 6) and verification/approval_gate named as outputs; this is not a destructive/batch operation, so the absence of a validate-fix-retry loop does not cap the score.

3 / 3

Progressive Disclosure

The skill is under 50 lines, self-contained, and organized into clear Procedure and Output sections with no bundle needed; per the simple-skills note, well-organized sections warrant a 3.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-targeted description: it states concrete capabilities, opens with an explicit 'Use when' trigger, and carves out a distinct niche (single self-evolving agent vs. a multi-agent team). It concisely answers both what and when without padding.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — "track sources, refresh research, propose repairs, or improve itself over time" — matching the anchor that lists multiple specific concrete actions; it is not vague like "Helps with documents."

3 / 3

Completeness

It answers both what (generating a single installable agent) and when ("Use when generating... that should keep learning..."), with an explicit trigger clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

With an explicit "Use when generating a single installable agent..." it covers natural terms a user would say ("keep learning", "refresh research", "propose repairs", "multi-agent team"), giving good coverage rather than jargon.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply defined — a single self-evolving agent "without becoming a multi-agent team" — making it unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentlas-ai/Agentlas-OS
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.