Loading...
Loading...
Found 78 Skills
Frames coding-agent work sessions with explicit intent capture and drift monitoring. Use when a session transitions from planning/Q&A to implementation for coding tasks, refactors, feature builds, bug fixes, or other multi-step execution where scope drift is a risk.
Discover, create, update, archive, and assign work to Multica agents. Also covers attaching workspace skills to an agent and inspecting an agent's task history. Use when the user asks which agents exist, who can do X, wants to spin up a new agent, change its model or instructions, or hand a task off to a managed agent.
Semantic search skill using Exa API for embeddings-based search, similar content discovery, and structured research. Use when you need semantic search, find similar pages, or category-specific searches. Triggers: exa, semantic search, find similar, research paper, github search, 语义搜索, 相似内容
Global integrated development and collaboration workflow skill that covers the entire lifecycle stages including requirement evaluation, development, testing, quality assurance, documentation, submission, and release. It can integrate all basic atomic skills to realize PDTFC+ cycle automation and optimize division of labor and cooperation.
Simple operations on user-provided text files including summarization.
Writes agent outputs to numbered thread stage files. Called by agents after domain work completes. Maps agent type to stages, updates frontmatter status, and records completion metadata. Stage 1 (1-input.md) is never written by this skill.
Skill for writing and updating codebase documentation. Use when creating or editing markdown documentation files in the docs/ directory, README files, or any documentation-related content. Also activates when maintaining the documentation index.
Use before committing to a task. Provides complexity analysis and scope assessment. Invoke when user asks "how complex" or before large features.
Use when a skill, plan, or rule file needs a frozen Starlark governance rule block generated, or an existing frozen block drift-checked against a candidate. Invoke explicitly — not for general rule discussion.
Wind MCP Data Bridge Skill (v1.1.0, 6 servers / 19 tools). Route by `server_type`: (1) `quote` for market data (A-shares/Hong Kong stocks snapshots, daily/weekly/monthly K-lines, minute-level data); (2) `fund_data` for fund-related data (profile/finances/holdings/performance/holders/management company); (3) `stock_data` for in-depth stock data (profile/financial fundamentals/equity structure/events/technical indicators/risk); (4) `financial_docs` for document RAG (announcements/financial news); (5) `economic_data` for EDB macro + industry economic indicators; (6) `analytics_data` for general NL → Wind data. WIND_API_KEY is required (obtained by logging into the Developer Center at aimarket.wind.com.cn). Trigger scenarios: A-shares/Hong Kong stock codes/K-lines/minute-level data, any dimension of funds, stock financial reports/valuation, listed company announcements/financial news, macroeconomic data, cross-comparison of targets. **Excluded**: US stocks/European stocks/Japanese stocks, exchange rates/futures quotes, cryptocurrencies, non-financial data.
Deploy a previously rendered Hyperscribe HTML file to Vercel and return a live shareable URL. Use whenever the user asks to "share", "publish", "deploy", or "send" a Hyperscribe output. Requires the `vercel` CLI (`npm i -g vercel`, then `vercel login`) and the `hyperscribe` skill for the share script.
Shared rules, routing preferences, execution boundaries, and workflow references for released PostPlus skills. Use this before any PostPlus skill that mentions shared release-shell rules, research preferences, product-selection preferences, TikTok music workflow, or ads workflow.