skill▌

Detect malicious patterns in installed Claude and OpenClaw skills. Based on SlowMist's analysis of 472+ malicious skills on ClawHub platform.

This skill provides guidance for creating effective skills.

Create and manage Claude Code skills with auto-activation triggers, following Anthropic best practices and the 500-line rule. \n \n Two-hook architecture: UserPromptSubmit for proactive skill suggestions based on keywords and intent patterns, and Stop hook for gentle error-handling reminders after responses \n Three skill types with different enforcement levels: guardrail skills (block critical mistakes), domain skills (suggest best practices), and warning skills (advisory only) \n Configuration

cc-skill-strategic-compact \n Development skill skill. \n When to Use \n This skill is applicable to execute the workflow or actions described in the overview.

Comprehensive guide for creating modular skills that extend Codex's capabilities with specialized knowledge and workflows. \n \n Skills consist of a required SKILL.md file with YAML frontmatter (name, description) and optional bundled resources (scripts, references, assets) organized to manage context efficiently \n Follow a six-step creation process: understand concrete usage examples, plan reusable contents, initialize with init_skill.py, edit SKILL.md and resources, package with package_skill

Use this skill to create new Agent Skills from templates. It generates a properly structured skill directory with a valid SKILL.md file and optional scripts/assets folders.

Automate creation of new CLI skills following Anthropic standards with zero manual setup. \n \n Guides users through interactive brainstorming, prompt refinement, file generation, validation, and installation in five phases with visual progress tracking \n Generates standardized SKILL.md and README.md files from templates, automatically substituting skill name, description, author, and metadata \n Validates YAML frontmatter, content quality, word counts, and writing style against Anthropic best

扫描 ~/.claude/skills/ 下所有已安装技能，生成一目了然的可视化地图。

Search, retrieve, and install reusable AI agent skills from the prompts.chat registry. \n \n Provides two core MCP tools: search_skills for keyword-based discovery with category and tag filtering, and get_skill to retrieve complete skill packages including SKILL.md, documentation, and helper scripts \n Supports installation workflow that creates .claude/skills/{slug}/ directories and verifies file integrity after saving \n Enables skill browsing with result presentation showing title, descriptio

Transform rough notes and workshop content into validated, repo-compliant PM skills. \n \n Guides you through six phases: preflight search, draft generation, tightening, strict validation, repo integration, and optional packaging \n Enforces a strict definition of done including frontmatter validity, metadata limits (name ≤64 chars, description ≤200 chars), and section compliance \n Provides three creation paths: guided wizard for ideas, content-first generator for existing source material, and