Loading...
Loading...
Found 21 Skills
Authoritative meta-skill for creating, auditing, and improving Agent Skills. Combines skill-coach expertise with skill-creator workflows. Use for skill creation, validation, improvement, activation debugging, and progressive disclosure design. NOT for general Claude Code features, runtime debugging, or non-skill coding.
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
Create, improve, and manage Droid skills. Use when the user wants to: - Create new skills from scratch or from session learnings - Improve existing skills based on user preferences - Analyze sessions to identify patterns worth codifying - Understand best practices for agentic skill design This is a meta-skill for self-improvement and continuous learning.
A meta-skill for creating/writing custom Skills for the Aike Smart Parking Open Platform CLI (openydt), benchmarked against Feishu's lark-skill-maker. It is used when users want to encapsulate a specific openydt interface or a business process into a reusable Skill, create a new openydt domain Skill, standardize the directory structure and frontmatter of SKILL.md, extract the catalog command list, add --yes to write operations, or learn how to write an openydt Skill. Trigger words: create openydt skill, write an openydt skill, encapsulate openydt interface, create a parking domain skill, openydt skill maker, skill template, SKILL.md specification, how to write frontmatter, how to list command list, turn this interface into a skill, benchmark against lark-skill-maker, parking open platform skill, skill scaffolding, skill directory structure.
Dual-mode meta-skill for (A) pre-plan field validation of business ideas through Customer Development and (B) post-plan auditing of market claims against evidence. Integrates Customer Development methodology (Blank/Dorf), rapid validation (Kagan), customer discovery steps (Cooper/Vlaskovits), and empathy-based research (Alam).
A meta-skill that establishes a 'One Brain' portable memory folder (.agent/). It persists context, user preferences, identity rules, and execution history across different AI harnesses (Claude Code, Cursor, Windsurf, OpenClaw).
Research and add new strategic frameworks to the system (meta-skill). Use when user wants to add framework not in library; discovered new framework in their domain; asks "Can you add [Framework]?"; or no existing framework fits their need. Uses web search for comprehensive research, validates quality, creates framework files, and integrates into system.
Orchestrator that runs scope then language then framework then library then cognitive review skills in order and aggregates all findings into one report. Does not perform analysis itself.
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)