发现 Skills

Execute Tellen workflow agents for multi-step audit procedures. Use this when the user wants to run an automated workflow, list available workflow agents, or retrieve workflow execution results.

Load when making decisions that require external knowledge - technology evaluation, standards/compliance checking, market data, or current best practices not in your training data.

The first security skill to install after setting up OpenClaw — developed by Tencent Zhuque Lab. Acts like an antivirus for your AI environment: audits skills before installation, scans installed skills, and runs a full OpenClaw security health check to prevent data leaks and privacy risks. Backed by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). Invoke when the user asks to start a security health check or security scan for the current OpenClaw environment, for example `start security health check`, `run a security scan`, `perform full security inspection`, or `check OpenClaw security`; also use when the user requests an audit of a specific skill before installation, a supply-chain risk review of installed skills, or an investigation into whether a skill is safe. Do not trigger for general OpenClaw usage, project debugging, environment setup, or routine development requests. Optional cloud mode: set AIG_CLOUD_LOOKUP=off for zero outbound HTTPS; when enabled, only minimal metadata (skill_name, source label, and OpenClaw version) are sent to A.I.G (never skill bodies, chats, or workspace files).

Find and evaluate Claude skills for specific use cases using semantic search, Anthropic best-practice assessment, and fitness scoring. Use when the user asks to find skills for a particular task (e.g., 'find me a skill for pitch decks'), not for generic 'show all skills' requests.

System architecture design for Rust/WebAssembly projects. Creates ADRs, designs APIs, plans module structures, and documents architectural decisions. Never writes implementation code - focuses purely on design and documentation.

Genera documentación llms.txt optimizada para LLMs. Usa cuando el usuario diga "crear llms.txt", "documentar para AI", "crear documentación para LLMs", "generar docs para modelos", o quiera hacer el repo legible para Claude/AI.

Handle tasks that may exceed tool timeouts (model training, large builds, data processing).

In-depth analysis of A-share ETFs, six-module M1–M6 framework (Profile / Tracking / Liquidity / Holdings / Valuation Percentile / Fund Flows)

Write operational runbooks for the on-call engineer at 3am — step-by-step procedures with decision trees, escalation paths, and rollback instructions that assume no prior context.

Use when configuring Playwright BDD projects, setting up defineBddConfig(), configuring feature and step file paths, and integrating with Playwright config.

Import model evaluation results into ReasonScape m12x dataset. Use when importing new models, quantization variants, or adding evaluation data. Keywords - model, import, evaluate, dataset, results, eval, hf, huggingface.

Expert patterns for combat systems including hitbox/hurtbox architecture, damage calculation (DamageData class), health components, combat state machines, combo systems, ability cooldowns, and damage popups. Use for action games, RPGs, or fighting games. Trigger keywords: Hitbox, Hurtbox, DamageData, HealthComponent, combat_state, combo_system, ability_cooldown, invincibility_frames, damage_popup.

Expert blueprint for visual novels (Doki Doki Literature Club, Phoenix Wright, Steins;Gate) focusing on branching narratives, dialogue systems, choice consequences, rollback mechanics, and persistent flags. Use when building story-driven, choice-based, or dating sim games. Keywords: visual novel, dialogue system, branching narrative, typewriter effect, rollback, BBCode, RichTextLabel.

Expert blueprint for Godot 4 project organization (feature-based folders, naming conventions, version control). Enforces snake_case files, PascalCase nodes, %SceneUniqueNames, and .gitignore best practices. Use when starting new projects or refactoring structure. Keywords project organization, naming conventions, snake_case, PascalCase, feature-based, .gitignore, .gdignore.

Expert blueprint for RPG stat systems (attributes, leveling, modifiers, damage formulas) using Resource-based stats, stackable modifiers, and derived stat calculations. Use when implementing character progression OR equipment/buff systems. Keywords stats, attributes, leveling, modifiers, CharacterStats, derived stats, damage calculation, XP.

Expert blueprint for scene loading, transitions, async (background) loading, instance management, and caching. Covers fade transitions, loading screens, dynamic spawning, and scene persistence. Use when implementing level changes OR dynamic content loading. Keywords scene, loading, transition, async, ResourceLoader, change_scene, preload, PackedScene, fade.

Expert blueprint for TileMapLayer and TileSet systems for efficient 2D level design. Covers terrain autotiling, physics layers, custom data, navigation integration, and runtime manipulation. Use when building grid-based levels OR implementing destructible tiles. Keywords TileMapLayer, TileSet, terrain, autotiling, atlas, physics layer, custom data.

Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability.

Create comprehensive, printable tariff and customs guide documents for any country or customs territory. Use when a user asks to write a tariff guide, create a customs handbook, document an import duty system, build a trade compliance reference, or explain how tariffs work for a specific country. Produces both Markdown and self-contained HTML with professional styling, worked examples, comparison tables, and print-ready layout. Accepts a country or customs territory name and optional topic outline.

Use agentkaizen to measure and prove whether your AI coding agent actually follows instructions. Works natively — no installation required. Use this skill when: you want to score a recent Codex or Claude Code session and check rule compliance (did it branch before work? stay within tool limits?); you changed AGENTS.md or config and need before/after evidence; a session used too many tool calls or failed to complete; you want a qualitative blind comparison of two agent outputs. Trigger: any question about measuring, comparing, or verifying agent behavior.

Use Set and Map for O(1) membership lookups instead of array.includes(). Apply when checking membership repeatedly or performing frequent lookups against a collection.

Business management frameworks for strategic analysis, decision making, goal setting, growth strategy, and organizational change. Use when analyzing business situations or making strategic decisions.

This skill should be used when the user asks about "SECI model", "knowledge creation cycle", "tacit vs explicit knowledge", "knowledge conversion", "GRAI framework", "human-AI knowledge collaboration", "socialization externalization combination internalization", "knowledge spiral", "what phase of knowledge creation", or needs to understand which phase of knowledge work a task involves. Provides the theoretical foundation for knowledge management across all contexts.

Embedding backends (InsightFace/PyTorch + ONNX Runtime vs TensorRT). Use when optimizing embedding throughput or debugging numeric drift and fallback behavior.