XiaoLuoLYG/GOD - Page 2

route-recall

Recall familiar routes from memory for grounded movement.

routine-daily

Choose a natural daily movement, interaction, or state from time, role, and current town context.

safety-respond

Respond to urgent or risky events with safety movement, announcement, and memory.

script-automate

Automate a small repetitive computer task.

shop-run

Run ordinary shop work and customer service.

sketch-draw

Draw or sketch a quiet observation.

social-matchmake

Connect two people who may help each other.

social-reply

Reply to a recent direct or group message without inventing unrelated movement.

stall-run

Run a market stall and handle daily stall tasks.

story-localpast

Share a story from the local past.

tools-repair

Inspect and repair a practical tool or device.

vegetable-source

Source vegetables and practical food supplies.

writing-feedback

Give clear feedback on a piece of writing.

writing-hand

Write something by hand with care and attention.

youth-communicate

Communicate with youth in a patient supportive way.

cognition

Produce emotion.json and intention.json from workspace context.

memory

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

observation

Fetch the current world observation for this tick.

plan

Execute intentions through the environment.

economic-reasoning

Economic decision-making for agents in EconomySpace. Activate when the agent observes currency, prices, income, tax, or trading opportunities to make informed financial decisions.

my-custom-skill

Example custom agent skill — a template to get started.

advanced-daily-report

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

Source text: Chinese

akg-agents

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`。

Source text: Chinese

ascend-moe-optimizer-auto-trace

为昇腾算子在源码中接入 TRACE_POINT 与 MoeTracing，串通 trace_preprocessor、profiling tensor、point_map.json、 save_profiling_data 与 trace_collector 生成 Chrome trace。强调门禁 G1–G5：全链路预处理与 OPP、profiling 为数据输出最后一位、 整条编译与示例脚本联调、落盘路径在 spawn 前 resolve。遵循函数级粒度与就地扩展，禁止另注册 xxx_profiling…

Source text: Chinese

ascend-moe-optimizer-trace-analyzer

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。

Source text: Chinese

cross-channel-history-retrieval

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。

Source text: Chinese

delayed-restart-app

安排延迟重启本 Agent 所在的服务（jiuwenclaw app）。执行后当前 Agent 进程会被终止并重新启动，当前会话会断开。用于用户要求重启、配置更新需生效、或服务异常需重载时。使用 bash 调用脚本。

Source text: Chinese

doc-update

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。

Source text: Chinese

financial-document-parser

Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.

Source text: Chinese

llm-wiki

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…

openjiuwen-deepsearch

知识增强型深度检索与深度研究，支持查询规划、信息收集、理解反思、研究报告生成等多 Agent 协同。使用场景：金融分析研报、学术与政策研究、企业级深度搜索等复杂推理任务，可以生成Markdown、Doc和Html格式的研究报告。**每次使用该技能之前都先完整阅读一遍SKILL.md学习技能。**

Source text: Chinese

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…

skill-gen-4-enterprise-doc

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…

skvm-general

Drive the skvm CLI on behalf of a user to profile models, AOT-compile skills, run skill-assisted tasks, run benchmarks, and manage compiled proposals. Trigger when the user asks to "profile", "aot-compile", "bench", "run a single ad-hoc task with a skill", or…

skvm-jit

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…

teamskill-creator

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…

ui-e2e

运行 JiuwenClaw Web UI 端到端测试并收集截图、日志、report.md、report.json。用于验证 Todo 和 Cron Web UI 流程、复现浏览器交互问题、选择运行解释器、准备 Playwright 环境，或返回可操作的失败证据时。

Source text: Chinese