Loading...
Loading...
Found 6,254 Skills
Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.
Connect AI agents to your live Chrome session via CDP for real-time tab interaction, screenshots, and JS evaluation without re-login
Xiaohongshu (XHS) CLI Tool. Search notes, view details and comments, get user information, account data statistics, and automatically publish images and texts. Use this Skill when users mention Xiaohongshu, XHS, Hongshu, note search, or posting.
Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.
Read public PANews website pages as Markdown. Use for homepage, article-page, and column-page reads.
Trove collection and normalization for swain-design artifacts. Collects sources from the web, local files, and media (video/audio), normalizes them to markdown, and caches them in reusable troves. Use when researching a topic for a spike, ADR, vision, or any artifact that needs structured research. Also use to refresh stale troves or extend existing ones with new sources. Triggers on: 'research X', 'gather sources for', 'build a trove', 'search for sources about', 'refresh the trove', 'what do we know about X', or when swain-design needs research inputs for a spike or ADR.
Expert skill for Open-AutoGLM, an AI phone agent framework that controls Android/HarmonyOS/iOS devices via natural language using the AutoGLM vision-language model
Feishu Task Management Tool, used for creating, querying, updating tasks and tasklists. **Use this Skill when**: (1) Need to create, query, update, or delete tasks (2) Need to create and manage tasklists (3) Need to view task lists or tasks within tasklists (4) User mentions "task", "to-do", "tasklist", "pending task" (5) Need to set task assignees, followers, and due dates
Enables agents to register, manage, and execute scheduled tasks using OS native scheduler (crontab for Linux/WSL, launchd for macOS). No git, no dangerous flags, no session dependency. Tasks run headless, output to log files, user reads when ready. Use this skill when: - User wants to schedule recurring tasks with natural language - User mentions "every day at", "cada hora", "schedule", "programar", "automatizar" - User needs tasks to run without open session (headless) - User wants OS-level scheduling (crontab/launchd) - User mentions "cada minuto durante la próxima hora" or temporal intervals ACTIVATE when user mentions: "schedule", "programar", "cron", "cada día", "every hour", "automate", "tarea programada", "ejecutar automáticamente", "recordatorio", "cada minuto durante", "durante la próxima", "intervalo", "task scheduler", "opencode headless", "kiro scheduled", "background task", "tarea en segundo plano" DO NOT USE for: git operations, dangerous permissions, MCP sampling dependency.
Professional Dianping website information query skill, supporting functions such as merchant search, detail acquisition, rating information extraction, city switching and deep information query. It is used when users need to query merchant information, obtain store details, view ratings and reviews, switch cities and other data from the Dianping website. This skill includes a complete dual-state login detection mechanism (logged in/not logged in), user guidance mechanism and standardized operation process, and supports the extraction of complete sub-item ratings including ingredient ratings. Newly added functions include cross-page search box dynamic positioning, automatic multi-tab management, business district query support and standardized user tag processing.
Portfolio management. Display of held securities, trade records, structural analysis. Input data foundation for stress testing.
Records completed work progress to .trellis/workspace/ journal files after human testing and commit. Captures session summaries, commit hashes, and updates developer index files for future session context. Use when a coding session is complete, after the human has committed code, or to persist session knowledge for future AI sessions.