--- name: index1-doctor description: Diagnose index1 environment - check Python, Ollama, models, index health. version: 2.0.3 license: Apache-2.0 author: gladego tags: [index1, diagnostics, mcp, troub
小花专用自我迭代技能 - 基于 self-improving-agent 增强，集成 OpenClaw 工作流、MEMORY.md、百度千帆、看想做找四部曲。专为国内部署优化。
Self-reflection + Self-criticism + learning from corrections. Agent evaluates its own work, catches mistakes, and improves permanently.
End-to-end runbook for deploying, operating, troubleshooting, and monitoring RAGFlow (runtime ops only).
Automates monitoring and self-repair of OpenClaw Gateway on Windows using Task Scheduler, with AI diagnosis and Telegram alert notifications.
Conduct quarterly vendor reviews using KPI scoring across delivery, quality, communication, cost, and alignment to guide renewal, improvement, or offboarding...
Rotate IP addresses automatically for web scraping. Per-request rotation, sticky sessions, country-based rotation, and distributed crawling strategies to avo...
Delegate PREQSTATION coding tasks to Claude Code, Codex CLI, or Gemini CLI with PTY-safe execution (workdir + background + monitoring). Use when building, re...
此 skill 用于检查、执行和修复项目代码规范。当用户需要为项目建立代码风格标准、 检查代码是否符合规范、自动修复格式问题、生成代码质量报告，
Redesign paywall and upgrade screens to maximize free-to-paid conversion. Use when a user wants to improve their SaaS upgrade screen, paywall copy, plan stru...
Search YouTube videos, get channel info, fetch video details and transcripts using YouTube Data API v3 via MCP server or yt-dlp fallback.
Scan installed agent components (MCP servers, skills, agent tools) for security vulnerabilities using snyk-agent-scan. Use only when running uvx snyk-agent-s...
Detects and maps complexity imbalances across system boundaries. When one side of an interface absorbs all the complexity while the other stays artificially...
A cognitive protocol for safely managing and auditing OpenClaw application upgrades. Analyzes configuration-level risks (schema, defaults) and runtime-level...
A lateral thinking engine for stuck moments. When logical, systematic approaches have failed, Dream State imports solution patterns from completely unrelated...
--- name: bazi-pillars-from-datetime description: Deterministic four-pillar (bazi) calculation from datetime. --- # Scope This skill defines a deterministic, reproducible calculation contract for fou
AI short drama generation - account management, script writing, video production. Integrated X2C billing for commercial deployment.
Optimize your ClawHub skill for maximum discoverability. Analyzes and rewrites SKILL.md description for vector search ranking, suggests keyword coverage, che...
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...
提交与建 PR 桥接自动化。负责将“可提交”改动落成 commit、推送分支并创建 PR，衔接 peter-code-review 与 peter-pr-ops。用于用户提到“帮我提交”“推分支
Runs autonomous iterative AI loops for requirements, planning, or building phases using structured prompts and fresh context per iteration.
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.
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building eval...