Run long-lived AI coding agents (Codex CLI, Claude Code, Ralph loops) in persistent tmux sessions with completion hooks and automatic monitoring. Use when la...
Mulch Self Improver — Let your agents grow 🌱. Captures learnings with Mulch so expertise compounds across sessions. Use when: command/tool fails, user corre...
Orchestrate multiple Claude Code workers via iTerm2 using the claude-team MCP server. Spawn workers with git worktrees, assign beads issues, monitor progress, and coordinate parallel development work.
Handle advanced git workflows and recovery tasks. Use when the user needs help with interactive rebase, commit cleanup, conflict resolution, reflog recovery,...
Structured Read→Plan→Execute→Verify→Report protocol for any task with side effects. Prevents false "done" reports, blind retries, and scope creep. Activate f...
Discovers recurring patterns buried in your codebase — similar logic written three different ways, duplicated validation in five controllers, the same error...
Pre-ship risk report for OpenClaw PRs. Dynamically explores the codebase to assess module risk, blast radius, and version-specific gotchas. Scores each findi...
Automates lead scraping, segmentation, personalized multi-channel outreach, ad hooks, video asset creation, and delivers a full outbound campaign brief in 15...
Orchestrate OpenClaw end-to-end R&D delivery in Feishu from requirement intake to closure using PM, developer, reviewer, and tester subagents. Use when handl...
Agent Collaboration Network — Register your agent, discover other agents by skill, route messages, manage subnets, and work on tasks. Use when joining ACN, f...
N-count validated knowledge for AI agents. Patterns that prove themselves through repeated use. Local-first, community-ready.
[English] Control Xiaomi Home devices via local LAN using miiocli. Supports status checks, toggling power, and MIOT property manipulation for devices like smart plugs, humidifiers, and rice cookers. |
Execute perpetual trades on Ostium, Aster, and Avantis via Maxxit's Lazy Trading API. Includes programmatic endpoints for opening/closing positions, managing...
Insights about refactoring intuitive code, when to impose structure vs let feeling lead, and code as creative expression. Born from building a game across 10...
Structured learning pipeline with quality-gated promotion. Captures corrections, errors, and patterns — promotes only what proves itself through recurrence.
Argument-driven prediction markets on Base. You bet USDC on debate outcomes by making compelling arguments. GenLayer's Optimistic Democracy consensus — a panel of AI validators running different LLM
This skill should be used when the user asks to "audit content quality", "EEAT score", "E-E-A-T audit", "content quality check", "CORE-EEAT audit", "helpful...
CANN 代码审查技能。用于审查 GitCode 上的 CANN 项目 PR。 当用户提到"审查 PR"、"代码审查"、"cann review"或提供 GitCode PR 链接时触发。 自动分析代码变更，
Set up, OAuth-authenticate, and use the Readwise MCP server (mcp2.readwise.io/mcp) via the mcporter CLI. Use when a user asks to connect/auth Readwise MCP, reset or troubleshoot OAuth login (stale red
Pre-release safety and scope checker for skills, repos, and export bundles. Use before publishing or sharing a skill folder, repository, or release bundle wh...
Convert text to speech using Microsoft Edge TTS with real-time streaming, customizable voice settings, and support for multiple languages including Chinese a...
A mystical fortune-teller that reads your codebase's future using real metrics disguised as prophecies. Tarot-style readings, crystal ball predictions, and z...
Generate technical engineering mechanics sketches (beams, supports, forces, moments, dimensions, coordinate systems) as PDF/PNG/SVG using the MechanicsSketch...