- 📁 references/
- 📁 templates/
- 📄 SKILL.md
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Add a new simulation benchmark to the VLA evaluation harness. Use this skill whenever the user wants to integrate, create, or add a new benchmark or simulation environment — e.g. 'add ManiSkill3', 'integrate OmniGibson', 'hook up a new sim'. Also use when they ask how benchmarks are structured or want to understand the benchmark interface.
Create and use brand.yml files for consistent branding across Shiny apps and Quarto documents. Use when working with brand styling, colors, fonts, logos, or corporate identity in Shiny or Quarto projects. Covers: (1) Creating new _brand.yml files from brand guidelines, (2) Applying brand.yml to Shiny for R apps with bslib, (3) Applying brand.yml to Shiny for Python apps with ui.Theme, (4) Using brand.yml in Quarto documents, presentations, dashboards, and PDFs, (5) Modifying existing brand.yml files, (6) Troubleshooting brand integration issues. Includes complete specifications and framework-specific integration guides.
- 📄 appintents-appintent.md
- 📄 appintents-appshortcut.md
- 📄 appintents-overview.md
API reference: App Intents. Query for Siri, Shortcuts, Spotlight integration, exposing app functionality.
Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.
- 📁 .github/
- 📁 api_relay_audit/
- 📁 deploy/
- 📄 .gitignore
- 📄 audit.py
- 📄 CLAUDE.md
Audit third-party AI API relay/proxy services for security risks. Detects hidden prompt injection, prompt leakage, instruction override, identity hijacking (Chinese-market substitutes), jailbreak vulnerabilities, context truncation, tool-call package substitution (AC-1.a), error response header leakage (AC-2 adjacent), SSE-level stream integrity anomalies (AC-1 streaming), and Web3 prompt injection (SlowMist signature isolation). Use when: test relay, audit API, audit relay, detect injection, relay security, API relay audit, is this relay safe, does it inject prompts, test proxy API, check API key, 中转站安全, 测试中转站, 中转站审计.
Manage persistent coding sessions across Claude Code, Codex, Gemini, and Cursor engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, or switching models/tools at runtime. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "switch model", "multi-agent", "coding session", "session inbox", "cursor agent".
Comprehensive kanban board and task management via ktui CLI. Use for project tracking, todo lists, task dependencies, workflow automation, and board management. Activates when user mentions boards, tasks, kanban, or project management. If the `ktui` command is not available, but `uv` is available utilize `uvx kanban-tui` instead.
巴逆逆反指標分析。觸發時機：使用者要求追蹤巴逆逆、分析反指標、抓取社群貼文並推送 Telegram 時。 能力範圍：透過 CLI 抓取 Facebook 貼文、反指標邏輯分析、連鎖效應推導、Telegram 推送。 目標：由 Claude 作為分析引擎，產出直白中文的反指標分析報告。 --- # banini-tracker — 巴逆逆反指標分析 追蹤「股海冥燈」巴逆逆（8zz）的 Facebook 貼文，由你（Claude）進行反指標分析，推送結果到 Telegram。 ## 前置條件 ```bash # 首次使用：初始化設定 npx @cablate/banini-tracker init --apify-token <TOKEN> --tg-bot-token <TOKEN> --tg-channel-id <ID> # 確認設定 npx @cablate/banini-tracker config ``` ## 工作流程 ### Step 1：抓取貼文 ```bash npx @cablate/banini-tracker fetch -s fb -n 3 --mark-seen ``` 輸出是 JSON 陣列，每篇貼文包含： - `id` / `source` - `text`（貼文內容） - `ocrText`（圖片 OCR 文字，可能包含下單截圖） - `timestamp` / `url` / `likeCount` - `mediaType` / `mediaUrl` `--mark-seen` 會自動記錄已讀，下次不重複抓。 ### Step 2：你來分析 讀取 Step 1 的 JSON 後，進行反指標分析。分析要點： **核心邏輯**（方向完全相反，不要搞混）： | 她的狀態 | 反指標解讀 | |---------|-----------| | 買入/加碼 | 該標的可能下跌 | | 被套（還沒賣） | 可能繼續跌（她還沒認輸） | | 停損/賣出 | 可能反彈上漲（她認輸 = 底部訊號） | | 看多/喊買 | 該標的可能下跌 | | 看空/喊賣 | 該標的可能上漲 | **分析原則**： - 只根據貼文明確提到的操作判斷，不要腦補 - 停損 = 她之前買了（做多），現在賣掉認賠。不是「放空」 - 標的用正式名稱（信驊、鈦昇），不用她的暱稱（王、渣男） - 當天貼文最重要，注意時序（她的想法可能幾小時內改變） - 語氣越篤定/興奮 → 反指標信號越強 - 善用 WebSearch 查詢標的最新走勢，豐富分析 **連鎖效應推導**： - 她買油正二被套 → 油價可能繼續跌 → 原物料成本降 → 製造業利多 - 她停損鈦昇 → 鈦昇可能反彈 → IC 設計族群連動上漲 - 她停損賣出油正二 → 油價可能反彈 → 通膨壓力回來 ### Step 3：推送 Telegram 將分析結果寫入暫存檔再推送（多行訊息用 `-m` 會被 shell 截斷，務必用 `-f`）： ```bash # 寫入暫存檔後推送（推薦） npx @cablate/banini-tracker push -f /tmp/report.txt # 短訊息可用 -m npx @cablate/banini-tracker push -m "短訊息" # 純文字（不解析 HTML） npx @cablate/banini-tracker push -f /tmp/report.txt --parse-mode none ``` ## 其他指令 ```bash # 去重管理 npx @cablate/banini-tracker seen list # 列出所有已讀 ID npx @cablate/banini-tracker seen mark <id...> # 手動標記已讀 npx @cablate/banini-tracker seen clear # 清空已讀紀錄 # 查看/修改設定 npx @cablate/banini-tracker config # 顯示設定（token 遮蔽） # 手動編輯: ~/.banini-tracker.json ``` ## 費用參考 Facebook 每次抓取約 $0.02（Apify CU 計費）。 ## 報告格式建議 推送到 Telegram 時建議用以下 HTML 格式。注意： - 每篇貼文附上原文連結（從 fetch 的 `url` 欄位取得） - `<` `>` `&` 必須轉義（`<` `>` `&`），避免 HTML 解析錯誤 - 多行內容務必寫入檔案後用 `-f` 推送 ``` <b>巴逆逆反指標速
- 📁 language/
- 📁 util/
- 📄 index.rs
- 📄 lang.rs
- 📄 main.rs
Prefer cx over reading files. Escalate: overview → symbols → definition/references → Read tool.
Search and retrieve agent skills at runtime. This skill should be used when the agent needs to find specialized capabilities, workflows, or domain knowledge to accomplish a task. Skyll aggregates skills from skills.sh and returns full SKILL.md content ready for context injection.
Add an MCP server to pi. Use when asked to "add mcp server", "configure mcp", "add mcp", "new mcp server", "setup mcp", "connect mcp server", or "register mcp server". Handles both global and project-local configurations.
