CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/self-evolving-single-agent/SKILL.md

The canonical home for this skill is self-evolving-single-agent in agentlas-ai/Agentlas-OS

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 exceptionally lean and well-sequenced with a genuine human-approval gate for risky changes, but its actionability is undermined by dependencies it assumes without providing: an undefined contracts file, undefined domain terms, and an unspecified verification procedure. Resolving the dangling reference and defining what the verification output contains would raise both weak dimensions.

Suggestions

Include `contracts/builder-interview-research-gate.md` in the bundle (e.g., under references/) or inline its gate criteria in SKILL.md so step 2 is executable as written.

Define the core domain terms used as approval criteria — Memory Tickets, Memory Events, Curator verdict, legacy chip, one-use owner approval receipt — either inline or via a well-signaled one-level-deep reference file.

Specify what the `verification` output must contain (e.g., checks run, evidence gathered, pass/fail criteria) so the required output artifact is actionable rather than just named.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout — numbered steps, exact file names, and terse rules like "Never treat a summary, low-risk label, Curator verdict, shell flag, or legacy chip as approval" — with no explanation of concepts Claude already knows. Every token earns its place, matching anchor 5.

5 / 5

Actionability

Concrete guidance exists (specific paths like `.agentlas/memory-map.json`, `docs/prompt-performance-contract.md`, and the 8-12 question bound), but step 2 says "Run `contracts/builder-interview-research-gate.md`" and that file does not exist in the bundle, and terms like "Memory Tickets", "Curator verdict", and "legacy chip" are never defined — key details are missing, matching anchor 3 rather than 4.

3 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced with an explicit approval checkpoint ("wait for human approval before changing tools, connectors, secrets, or core instructions") and mandated staged diffs plus approval receipts, satisfying validation for the risky operations. However, the required `verification` output is named with no steps defining what verification entails, a minor gap that holds it at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The skill is under 50 lines and well-sectioned, but it references `contracts/builder-interview-research-gate.md` while no references/, scripts/, or assets/ directories exist in the bundle, leaving a dangling reference whose location and provenance are ambiguous — structure is present but organization around references is unresolved, matching anchor 3.

3 / 5

Total

15

/

20

Passed

Description

75%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 well-formed with an explicit trigger clause, third-person-compatible phrasing, and a distinctive single-agent-versus-team boundary. Its main weakness is that the enumerated capabilities describe the artifact to be generated rather than the skill's own actions, leaving the 'what' less explicit than it could be.

DimensionReasoningScore

Specificity

Lists several distinct capabilities ("keep learning, track sources, refresh research, propose repairs, or improve itself over time") matching the several-specific-actions anchor, but the actions remain abstract rather than fully concrete, so it falls short of the comprehensive anchor 5.

4 / 5

Completeness

An explicit "Use when..." clause clearly answers when, and "generating a single installable agent" supplies the what, but the capabilities listed describe the generated agent rather than what the skill itself does, so the what is not as explicit as anchor 5 requires.

4 / 5

Trigger Term Quality

Phrases like "keep learning", "improve itself", and "without becoming a multi-agent team" are natural things a user would say, giving good keyword coverage, but common synonyms such as "self-improving" or "autonomous agent" are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The constraint "single installable agent... without becoming a multi-agent team" carves a distinct niche with low conflict risk, though the trigger terms still overlap somewhat with generic agent-generation skills, so it is not the minimal-conflict anchor 5.

4 / 5

Total

16

/

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

agentlas-ai/Agentlas-OS

Path

.agents/skills/self-evolving-single-agent/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.