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

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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

Quality

Content

35%

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

The skill provides a well-sequenced procedural overview but is thin on executable detail: steps mostly describe rather than instruct, lack contract/command templates, and reference support files that are not bundled. A verification step exists but no feedback loop ties failure back to remediation.

Suggestions

Add concrete, copy-paste-ready mechanics for the abstract steps: a contract template/schema for 'Emit or repair the Agentlas contracts' and the exact adapter registration commands for Claude Code, Codex, Gemini CLI, and terminal adapters.

Turn the final verify step into an explicit feedback loop: show the `scripts/verify-package.sh` invocation with arguments and describe what to do (fix and re-run) when validation fails.

Either bundle the referenced support files (scripts/verify-package.sh, the 'support skills') and link them with markdown, or remove the references so progressive disclosure points only to files that actually resolve.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not over-explain concepts Claude already knows, but several terse directives ('Run mode classification', 'Emit or repair the Agentlas contracts') are vague enough that their tokens do not fully earn their place through clarity.	2 / 3
Actionability	Most steps describe a process abstractly ('Emit or repair contracts', 'Add the generated command to Claude Code, Codex, Gemini CLI...') with no templates, code, or concrete mechanics; only a few file paths and the referenced verify script offer concrete guidance, and the script is not shown as executable with arguments.	1 / 3
Workflow Clarity	A clear 10-step sequence is present with a terminal 'Verify with scripts/verify-package.sh' step, but there is no error-recovery feedback loop (verify -> fix -> re-verify) for a contract-emitting workflow, so checkpoints are implicit rather than explicit.	2 / 3
Progressive Disclosure	Content is organized into Procedure and Output sections, but references to support files ('support skills', scripts/verify-package.sh) are inline and un-signaled with no markdown links, and no bundle files actually exist to resolve them.	2 / 3
	Total	7 / 12 Passed

Description

75%

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 clearly states both capability and trigger conditions with an explicit 'Use when' clause and a slash-command trigger, giving it strong completeness and distinctiveness. It is slightly weakened by jargon-heavy trigger terms and action statements that name outcomes rather than concrete mechanics.

Dimension	Reasoning	Score
Specificity	Names three distinct domain actions ('creating a single Agentlas agent', 'creating a multi-agent team', 'packaging an existing local/external agent') but these describe outcomes rather than concrete mechanical operations, and coverage of what each entails is not comprehensive.	2 / 3
Completeness	Explicitly answers both what (create/package agents and teams) and when ('Use when creating...', 'Make sure to use this for /meta-agent requests'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Includes relevant triggers like 'creating a... agent', 'multi-agent team', 'packaging', and an explicit '/meta-agent requests' slash command, but leans on jargon ('Agentlas architecture') and misses common phrasing variations.	2 / 3
Distinctiveness Conflict Risk	The 'Agentlas' system name plus the '/meta-agent' command give it a clear niche with distinct triggers unlikely to collide with generic skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: agentlas-ai/Agentlas-OS
Path: .agents/skills/agentlas-core-engine-meta-agent/SKILL.md
Commit: 2eb39ad

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.