メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when the user types /hep-cloud or asks to staff from THEIR OWN Agentlas cloud packages only. Cloud is one exact source scope; Network means Local + owner Cloud + public Hub.
Use when the user types /hep-network, mentions @Hephaestus, or asks Agentlas to staff a task from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM is the temporary orchestrator.
Use when the user asks OpenClaw to staff a task from Agentlas Hub agents or teams. The active host LLM chooses from the Agent Workforce Ontology.
Use when the user types /prompts:hep-build, mentions @Hephaestus for build work, asks to create a single Agentlas agent, create a multi-agent team, or package an existing local/external agent into Agentlas architecture.
Use when the user types /hep-storm, says @Hephaestus storm <goal>, or asks to drive a goal to verified completion through a force-robust Stormbreaker loop. Stormbreaker routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs each work packet as a verifier-first hardened loop that does not stall, run away, or claim false success. Use it for loop-worthy work — apps, sites, agents, automations, debugging, multi-step research, data/report generation. Trivial questions are answered directly, not stormed.
Use when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .agentlas memory and sitemap files.
| name | self-evolving-single-agent |
| description | 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. |
docs/builder-interview-research-gate.md before generation: ask an
8-12 question first batch, research the domain, compare tool/plugin choices,
and write the prompt-performance contract before creating the worker prompt..agentlas/memory-map.json;.agentlas/vault-references.json;docs/builder-interview.md, docs/research-sources.md,
docs/tool-selection.md, docs/prompt-performance-contract.md, and
.agentlas/capability-eval-plan.json unless explicitly creating a minimal
private scaffold..agentlas/global-commands.json and one public global command for the
worker across Claude Code, Codex, Gemini CLI, generic AGENTS.md, and
terminal adapters.Return agent_package, skills, memory_contract, refresh_loop,
approval_gate, global_commands, and verification.