skills.guanliai
How-tosAll SkillsCombos
中EN
How-tosAll SkillsCombos

skills.guanliai.com

An AI how-to library organised by scene: which skills to use, how to install, how to prompt, and what traps to avoid.

How-tosAll SkillsCombos

Supported clients

  • Claude Code
  • Cline / Roo Code
  • CodeBuddy
  • CodeGeeX (Zhipu)
  • Comate (Baidu)
  • Cursor
  • Fitten Code
  • Gemini CLI
  • GitHub Copilot
  • Kiro
  • Lingma (Alibaba)
  • MarsCode
  • OpenAI Codex
  • OpenClaw
  • OpenCode
  • Qoder
  • Tencent CloudBase AI
  • Trae
  • VS Code
  • Windsurf
skills.guanliai.com · Agent Skill DirectoryData from GitHub · Next.js + MySQL
HomeAll Skills

All Skills

Total 5 skills · from GitHub & curated sets, updated daily

Category

Featured

China

Global

Tags

Language

Total 5 skills

agent-self-scheduling

sickn33/agentic-awesome-skills/skills/agent-self-scheduling

Automation

Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.

Claude CodeOpenAI Codex
45.6kPythonDetails
agentsautomationcron

agent-launcher-orchestrator

alirezarezvani/claude-skills/agent-launcher/skills/agent-launcher-orchestrator

Automation

Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).

CursorClaude CodeGemini CLI
25.1kPythonDetails
cmaagentlaunch

run-without-you

alirezarezvani/claude-skills/agent-launcher/skills/run-without-you

Automation

Phase 4 of building a Claude Managed Agent — make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven curl trigger, or confirmed on-demand use, then finalize the versioned roadmap. Use when the user says "run it every morning", "put it on a schedule", "nightly", "weekly", "automate this", "make it recurring", or when the orchestrator routes phase=run-without-you. deployment_builder.py builds the POST /v1/deployments payload (initial_events must include user.message; optionally nests a user.define_outcome so each firing self-grades); cron_validator.py validates the 5-field cron + IANA timezone and prints the wall-clock DST note; next_directions_writer.py writes NEXT-DIRECTIONS.md. No tool makes API calls — the deployment is created via BYOK curl. Distinct from grade-iterate (the in-session loop) and wrap-up (closeout).

CursorClaude CodeGemini CLI
25.1kPythonDetails
deploymentcmacron

watchers

NousResearch/hermes-agent/optional-skills/devops/watchers

Automation

Poll RSS, JSON APIs, and GitHub with watermark dedup.

Universal
242.8kPythonDetails
monitoringautomationcron

cron-doctor

sickn33/agentic-awesome-skills/skills/cron-doctor

Automation

Diagnose and validate cron expressions before they ship. Catches the five silent death-traps: impossible dates that never fire, OR-semantics that fire too often, midnight spikes, uneven step drift, and leap-year February 29.

CursorClaude CodeOpenAI Codex
45.6kPythonDetails
debuggingvalidationdevops