CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-core-engine-meta-agent

Use when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into Agentlas architecture. Make sure to use this for /meta-agent requests.

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 ./.agents/skills/agentlas-core-engine-meta-agent/SKILL.md
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.

A token-efficient, well-sequenced procedure whose beginning and end are concrete but whose middle (steps 3-8) defers all substance to external artifacts that are neither bundled nor clearly located. Adding paths for the referenced artifacts and an explicit failure-recovery step would lift it substantially.

Suggestions

Concretize steps 3-7: state what mode classification checks, where the support skills live (paths or filenames), and what the Agentlas contracts consist of, so the workflow is executable without undocumented external context.

Add a feedback loop after the step 10 verification scripts: what to inspect and fix when verify-generated-package.sh, verify-team-package.sh, or public_safety_check.sh fail, and re-run until they pass.

Fix the step 9 duplication ('Codex, Codex') and clarify how ENGINE is resolved for readers who lack the /hep-build context.

DimensionReasoningScore

Conciseness

The body is a lean procedural list with zero concept explanations and no padding; every step carries operational content. The only waste is the duplicated 'Codex, Codex' typo in step 9, which is a correctness slip rather than verbosity.

5 / 5

Actionability

Step 10 is fully executable ('bash "$ENGINE/scripts/verify-generated-package.sh" "$PACKAGE_ROOT"', 'public_safety_check.sh'), but the core steps 3-8 are abstract directives ('Run mode classification', 'Emit or repair the Agentlas contracts', 'Load only the matching support skills') whose specifics live in artifacts that are neither bundled nor located, so key details are missing.

3 / 5

Workflow Clarity

Steps 1-10 are clearly sequenced and step 10 provides an explicit validation checkpoint (three verification scripts plus a public safety gate). It falls short of 5 because there is no error-recovery feedback loop describing what to do when verification fails.

4 / 5

Progressive Disclosure

The body is short and sectioned (Procedure, Output), but it depends on external references that are present yet not clearly signaled: 'AGENTS.md', '.agentlas/mode-map.json', unnamed 'support skills', and '/hep-build'/ENGINE whose locations are never resolved, and no bundle files exist to back them.

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.

A solid description with an explicit trigger clause, a clear niche, and three concrete capability actions. Its main weakness is that the 'what' is merged into the 'when' clause and never states what the skill actually emits or verifies.

DimensionReasoningScore

Specificity

Lists three concrete actions ('creating a single Agentlas agent', 'creating a multi-agent team', 'packaging an existing local/external agent into Agentlas architecture'), but the actual outputs of the skill (contracts, adapters, package verification) are unstated, leaving minor coverage gaps.

4 / 5

Completeness

An explicit 'Use when...' clause plus '/meta-agent requests' clearly answers when, and the creation/packaging actions answer what; however the 'what' is folded into the trigger clause and does not state what the skill produces, so it is not a fully explicit 5.

4 / 5

Trigger Term Quality

Natural phrases like 'creating a multi-agent team', 'packaging an agent', and the explicit '/meta-agent' command give good keyword coverage, though common synonyms such as 'wrap', 'integrate', or 'onboard an agent' are missing.

4 / 5

Distinctiveness Conflict Risk

Every trigger is scoped to 'Agentlas architecture' and the '/meta-agent' command, giving a clear niche with minimal conflict risk; generic phrases like 'creating a multi-agent team' could still overlap with non-Agentlas agent-building skills, keeping it below 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/agentlas-core-engine-meta-agent/SKILL.md

Revision

2b4e27b

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill