Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Agentlas Core Engine Meta-Agent — measured AI agent skill | DecimalAI

agentlas-ai/agentlas-core-engine-meta-agent

SkillScore82Maintained

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.

agent-toolingby agentlas-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

decimalai skills pull agentlas-ai-agentlas-core-engine-meta-agent

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/agentlas-ai-agentlas-core-engine-meta-agent/SKILL.md

Raw file: /s/agentlas-ai-agentlas-core-engine-meta-agent/SKILL.md ↗ · machine-readable summary at /s/agentlas-ai-agentlas-core-engine-meta-agent.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—-29% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	38%	0%
case-06	✗→✓	▲ Improved	-62%	0%
case-08	✗→✓	▲ Improved	-44%	0%
case-09	✗→✓	▲ Improved	-35%	0%
case-11	✗→✓	▲ Improved	-37%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

agentlas-ai / agentlas-os

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

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v2

Skill contents

SKILL.md

Agentlas Core Engine Meta-Agent

Procedure

Read AGENTS.md.
Read .agentlas/mode-map.json.
Run mode classification.
Ask clarify questions when missing details change files, adapters, or

public/private boundary.

Pick one team member:

Single Agent Builder;
Multi Agent Team Builder;
Agentlas Packager.

Load only the matching support skills.
Emit or repair the Agentlas contracts, including

.agentlas/global-commands.json. Include .agentlas auto-activation seed files when local continuity is part of the output.

Write all generated or repaired runtime agent instructions in English,

including adapters, role prompts, skills, handoff contracts, return contracts, and operating docs. Translate Korean or other-language source material into English agent behavior. Localized public copy and routing trigger examples may use the target user language.

Add the generated command to Claude Code, Codex, Gemini CLI, generic

AGENTS.md, and terminal adapters. For teams, expose the orchestrator/HQ command and route workers through HQ unless direct worker commands were requested.

Verify with scripts/verify-package.sh.

Output

Return status, evidence, output, global_commands, and blockers.

Want to see if agentlas-ai/agentlas-core-engine-meta-agent would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.