Provider adapter selection and configuration: openaiText, anthropicText, geminiText, ollamaText, grokText, groqText, openRouterText, bedrockText, byteplusText, openaiCompatible. Per-model type safety with modelOptions, reasoning/thinking configuration, runtime adapter switching, extendAdapter() for custom models, createModel(). Generic OpenAI-compatible providers (DeepSeek, Together, Fireworks, etc.) via openaiCompatible({ baseURL, apiKey, models }) from @tanstack/ai-openai/compatible. API key env vars: OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY/GEMINI_API_KEY, XAI_API_KEY, GROQ_API_KEY, OPENROUTER_API_KEY, OLLAMA_HOST, BEDROCK_API_KEY (or AWS_BEARER_TOKEN_BEDROCK). BytePlus needs TWO keys: ARK_API_KEY (ModelArk — chat/video/image) and BYTEPLUS_VOICE_API_KEY (Seed Speech — TTS/transcription); neither is a fallback for the other.

HAR: Multi-angle code, plan, scope review. Security/quality check. Trigger: review, code review, plan review, scope analysis. Do NOT load for: implementation, new features, bugfix, setup, release.

Generate a Progress Tracker HTML for non-engineer vibecoders to glance at session progress (cc:WIP / cc:TODO / cc:完了 counts, percentage, elapsed/estimated minutes, cost so far/estimate, drift alerts). Uses Plans.md as source of truth, renders a single-file HTML with auto-regeneration support. Use when user asks for progress overview, session status snapshot, dashboard, or says: progress tracker, 進捗確認, 進捗ボード, dashboard. Do NOT load for: actual implementation, code review, release work.

Generate a Plan Brief HTML for non-engineer vibecoders before implementation starts. Searches harness-mem (project-only) for relevant past decisions, patterns, and Plans archive entries, then renders a single-file HTML artifact summarizing understanding, options, risks, acceptance criteria, and confidence. Use when the user requests a planning preview, a non-engineer-friendly summary before approval, or says: plan brief, planning preview, 計画概要, 計画レビュー. Do NOT load for: actual implementation, code review, release work.

Generate an Acceptance Demo HTML for non-engineer vibecoders right before ship/wait/reject decision. Reads back the acceptance_criteria that were stored as personal-preference.v1 by harness-plan-brief (joined by user_request_hash), then renders a single-file HTML showing each criterion as verified or unverified along with a ship/wait/reject recommendation. Use when the user asks for an acceptance review, wants to decide whether to ship a delivered task, or says: acceptance demo, accept demo, 受け入れ判断, 受入レビュー, ship/wait/reject 判定, 検収レビュー. Do NOT load for: implementation, code review, release work.

Creates, converts, or modifies Teamskills — the multi-role extension of the Skills standard (specialized roles + workflow + bind constraints). Use when the user wants to author a multi-role agent team, convert a single-agent skill into one, or refactor an existing team. Do NOT use for single-agent Skills — use create-skill instead.

Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was driven by any skill (not just SkVM-compiled ones) when the outcome was a failure, was partial, or the skill's instructions clearly caused confusion or an unnecessary detour. Clean successful runs usually do not need an optimization pass. For general skvm usage (profile/aot-compile/bench/proposals), use the sibling `skvm-general` skill instead.

Turn SOPs, URLs, or stated intent into an installed skill package. Use when the user asks to generate a skill from a document, link, or workflow. Follow SKILL.md, reference/sop-structure-pipeline.md, and reference/generator-worker-spec.md; finish by promoting the draft into the runtime skills directory (see reference/operator-playbook.md) in the same turn.

Build and maintain a persistent knowledge base (LLM Wiki) using native backend tools. Supports ingesting PDFs, Markdown, and TXT files, and querying or linting the data. Use this whenever the user wants to add, retrieve, or manage their own local knowledge base and documents.

以源码为唯一事实来源，系统性核对并更新项目文档，确保内容与实现一致、多语言文档 1:1 对齐、结构完整。

识别代码中可替换为CAM算子的DeepEP算子，基于实际运行参数校验约束，自动完成通信域转换（NCCL->HCCL）、设备适配（CUDA->NPU）及算子替换。

跨会话检索聊天原文（记忆不足时再用）。在回答任何关于历史事件、日期、人物、过去对话的问题时，如果记忆中没有相关信息或不足以回答，则需要使用跨会话检索聊天原文。用 mcp_exec_command 执行 scripts/search_history.py，读 ~/.jiuwenclaw/agent/sessions/*/history.json。支持 channel、session_id、关键词、时间窗。如果搜索结果不足，尝试用不同的关键词再次搜索。

在用户提供 Chrome/Perfetto trace.json、或排查 Ascend 上 MoE/FusedDeepMoe 等算子性能时使用。按 phase、category、core group、tid 统计耗时、overlap、bubble，输出 CSV、Markdown 报告与确定性诊断；可选外部 LLM 扩写分析。默认 phase 映射面向 UMDK FusedDeepMoe，其它 trace 需替换或扩展 config/phase_map.yaml。

代理执行 AKG 算子任务。先检查固定仓库与分支；若 `~/.akg/check_env.md` 不存在则强制 `FULL_SETUP=true`；忽略所有 `akg_cli` 检查和使用；后端代码生成直接执行 `run_workflow.py --workflow kernelgen`。

进阶版日报生成器，支持多数据源采集、工作分析、趋势对比、周报月报聚合

Example custom agent skill — a template to get started.

Execute intentions through the environment.

Fetch the current world observation for this tick.

Persist important outcomes from this step to long-term storage with automatic forgetting curve.