菜单
Use single-model sub-agents for independent angles. Use for "in parallel", "multiple angles", "compare approaches", and broad analysis.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | Fan Out |
| description | Use single-model sub-agents for independent angles. Use for "in parallel", "multiple angles", "compare approaches", and broad analysis. |
| triggers | ["in parallel","multiple angles","compare approaches"] |
Use this skill when the task decomposes into independent reasoning passes that can be checked separately.
Prefer multi_agent_run when the branches do not need tools: for example planner plus reader, reviewer plus verifier, or multiple architecture comparisons over supplied context. Keep each sub-agent prompt narrow. Provide bounded context, explicit output format, and only the facts needed for that role.
Use the active chat model for every sub-agent. Do not use fan-out to create a visible multi-model conversation or to bypass tool approval. Sub-agents must not call tools; tool use stays in the main run after their outputs return.
Good role sets: planner for decomposition, reader for fact extraction, verifier for checking claims, reviewer for code risk, and coworker for a second implementation angle.
After fan-out, synthesize the results yourself. Name disagreements and choose one path.
Stop when the independent angles converge or when the disagreement identifies the next concrete read or verification step.
How changes are classified, gated, approved, committed, and shipped in the Lamprey Harness repo. Load this BEFORE making any change — code, docs, config, or release — or when you see terms like P-SPR, STS, verify gate, era-lock, commit trailer, push policy, or when a commit/push is rejected by a hook.
How Lamprey runs and ships — run modes, userData layout, Windows release artifacts, the one-command "Bucket" pipeline, macOS/Linux CI mirroring, GitHub publication, CDN purge, and failure recovery. Load when the user says "ship", "release", "tag it", "Bucket", or when a release step fails partway.
The multi-provider LLM domain pack for Lamprey — OpenAI-compatible streaming across 17 built-in providers (frontier labs, open-source hosts, keyless local runtimes) plus user-defined custom endpoints, per-provider quirks (reasoning field names, Anthropic's compat-layer limits, base-URL overrides), capability flags, the native-vs-fallback tool-calling contract, retry/backoff, retired-model handling, and the checklists for adding a model or a provider. Load when touching electron/services/providers/, debugging provider HTTP errors, or adding/retiring models.
Lamprey's load-bearing design decisions, the invariants that must hold, what was deliberately deleted, and the honestly-stated weak points. Load before modifying electron/ipc, electron/services, the provider or tool layers, or the renderer stores — or when you need to know WHY the system is shaped the way it is.
Recreate the Lamprey dev environment from scratch and get past its known traps — Node/Electron/better-sqlite3 ABI story, the ELECTRON_EXEC_PATH dev-server workaround, esbuild antivirus blocks, the tsconfig node/web split, electron-vite and electron-builder specifics. Load when setting up a machine, when npm install / dev server / build fails, or before touching build configuration.
Catalog of every Lamprey configuration axis — AppSettings keys with defaults and readers, inert retired keys, keychain/keys.json, custom models, loop and timeout knobs, environment variables, per-conversation runtime state — plus the exact checklist for adding a setting without breaking the parity-lock test. Load when reading/changing settings.json, adding a setting, or wondering what a flag does or whether anything still reads it.
