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

80%

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

Quality

Content

72%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 concise, well-structured orchestration procedure that delegates to named team members and real artifacts, but several steps stay abstract and the generative workflow lacks an explicit verification-recovery loop. Fleshing out mode-classification logic and the verify->fix->re-verify path would lift actionability and workflow clarity.

Suggestions

Specify the mode-classification logic (e.g., decision rules mapping request types to Single Agent Builder vs Multi Agent Team Builder vs Packager) instead of the bare 'Run mode classification' step.

Add a feedback loop after step 10: if scripts/verify-package.sh fails, list the failure, fix the offending contract/adapter, and re-run verification before returning success.

Define the expected shape of the Output fields (status, evidence, output, global_commands, blockers) so emitted results are concrete rather than implied.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: a terse numbered procedure with no concept padding, assuming Claude's competence and earning every token; the only elaboration (step 8) directly governs behavior.	5 / 5
Actionability	Concrete file and command references (AGENTS.md, .agentlas/mode-map.json, scripts/verify-package.sh) coexist with abstract directives like 'Run mode classification' and 'Emit or repair the Agentlas contracts' whose schemas/logic are not specified inline.	3 / 5
Workflow Clarity	Ten clearly sequenced steps with a clarify checkpoint (4) and a verify step (10), but the generative/batch contract-and-adapter emission lacks an explicit validate->fix->retry feedback loop, capping at 3 per the feedback_loops guidance.	3 / 5
Progressive Disclosure	Under 50 lines with well-organized Procedure and Output sections and no need for bundled documentation files, qualifying for the simple-skill exception; referenced runtime artifacts are not skill docs.	5 / 5
	Total	16 / 20 Passed

Description

87%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 well-constructed description with an explicit trigger clause, third-person imperative voice, and concrete enumerated actions targeting a distinct niche. Its only weakness is slightly abstract action granularity rather than fully comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — 'creating a single Agentlas agent', 'creating a multi-agent team', 'packaging an existing local/external agent' — with only minor granularity gaps, falling just short of the comprehensive 5-anchor.	4 / 5
Completeness	Explicitly answers both 'what' (create/package agents into Agentlas architecture) and 'when' ('Use when...', 'Make sure to use this for /meta-agent requests') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage including 'Agentlas agent', 'multi-agent team', 'packaging', and the '/meta-agent' slash command, missing only a few common synonym variations for a 5.	4 / 5
Distinctiveness Conflict Risk	The 'Agentlas' and '/meta-agent' niche triggers carve a clear, distinct scope with minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 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: .claude/skills/agentlas-core-engine-meta-agent/SKILL.md
Commit: a7988bb

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.