dvcrn

监控 OpenClaw GitHub 版本更新，获取最新版本发布说明，翻译成中文， 并推送到 Telegram 和 Feishu。用于：(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明

The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.

Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).

一键发布 Markdown 到微信公众号草稿箱。基于 wenyan-cli，支持多主题、代码高亮、图片自动上传。

Reusable Polymarket + OpenClaw trading operations skill for any workspace. Use when the user needs to set up, run, tune, monitor, and deploy an automated Polymarket trading project (paper/live), including env configuration, risk controls, reporting, and dashboard operations.

Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.

Auto-create a new session when OpenClaw context usage reaches 80% without requiring Mem0 or file memory systems. Use when users want default OpenClaw to proactively rotate sessions and avoid context overflow in long chats.

Triple Layer Memory

Operate the `chainenv` CLI for local secret workflows across macOS Keychain, Linux keyring, and optional 1Password integration. Use when requests mention `chainenv`, `.chainenv.toml`, `chainenv.toml`, keychain vs 1Password, shell export generation, copying secrets between backends, or troubleshooting backend availability and `op` token loading.

Operate the Memrise CLI for community courses, including authentication setup, course/level/word lookup, pool searches, and adding items. Use when requests mention `memcli` commands or the npm package `memrise-cli` (which installs the `memcli` binary), especially for command construction, troubleshooting flags, and script-friendly JSON output.

Operate the WeWork CLI for workspace booking workflows, including authentication setup with `WEWORK_USERNAME` / `WEWORK_PASSWORD`, location and desk discovery, booking creation, booking listing, and calendar export. Use when requests mention `wework` commands or the npm package `wework-cli`, especially for command construction, flag troubleshooting, and safe pre-book checks.

Operate and validate the TripIt CLI for trip and itinerary workflows. Use this skill when users ask to authenticate with TripIt, run `tripit` CLI commands, create/list/get/update/delete trips and child items (hotels, flights, transport, activities), or execute end-to-end validation flows based on README.md and AI_TEST_HARNESS.md.

Operate the DEVONthink CLI for databases, records, search, tags, and AI workflows. Use when requests mention the `devonthink`, `dt`, or `dt-cli` commands, or the npm package `devonthink`, especially for command construction, schema inspection, JSON output, and record/database operations.

Operate the `chainenv` CLI for local secret workflows across macOS Keychain, Linux keyring, and optional 1Password integration. Use when requests mention `chainenv`, `.chainenv.toml`, `chainenv.toml`, keychain vs 1Password, shell export generation, copying secrets between backends, or troubleshooting backend availability and `op` token loading.

Use this skill when a user explicitly wants WeWork actions through the installed `wework` CLI, such as "book a WeWork desk", "list WeWork desks in Tokyo tomorrow", "show my WeWork bookings", "list WeWork locations", or "generate a WeWork calendar export". Do not use it for generic coworking, travel planning, or unrelated calendar requests.

Use the TripIt CLI (`tripit`) to authenticate and manage trips, hotels, flights, transport, activities, and document attachments.

Use memcli when the user wants to inspect or update Memrise teaching courses, levels, items, or pools through the installed memcli or memrise CLI.

Operate the Memrise CLI for community courses, including authentication setup, course/level/word lookup, pool searches, and adding items. Use when requests mention `memcli` commands or the npm package `memrise-cli` (which installs the `memcli` binary), especially for command construction, troubleshooting flags, and script-friendly JSON output.