发现 Skills

Use cargo for Rust development with check-first workflow. Prefer cargo check over cargo build, use debug builds for testing, AVOID release builds unless explicitly needed.

Use this to perform operations on the langgraph4j project. 1) create a new project release 2) move to next dev release

Start, stop, monitor the Animus daemon — health checks, events, logs, pool sizing, common issues

Intelligent task management via the `task` CLI. Invoke when users ask to: create/list/update/delete tasks, search tasks (text or semantic), track work items with due dates, organize tasks into projects, run batch operations, generate activity reports, or manage recurring tasks. Supports natural language dates and Google Calendar sync.

Add speech-to-text transcription widget to web pages using Whisper server. Creates WhisperWidget JS component that records audio, sends to whisper server, and returns transcribed text. Use when adding voice input to web applications.

DepEd Nexus domain context and business rules

Performs a brutally honest SWOT analysis of the codebase — strengths worth protecting, weaknesses to fix, opportunities being missed, threats that could sink the project. Use when deciding what to build next, evaluating project health, or preparing for strategic decisions.

OBLITERATUS: abliterate LLM refusals (diff-in-means).

Comprehensive repo-level code scanner & reviewer. Spawns multi-agent teams to audit code quality, security, performance, architecture, and testing. Spares no tokens. Saves findings to local artifacts.

Vue component patterns with the Composition API and script setup. Use when creating components, following the script-setup ordering convention, organizing component directories, or implementing component patterns like slideovers, modals, and tables.

Run code-hygiene checks before committing. Use before git commits or when asked to check code quality.

Create new files in knowledge base with directory governance. Use when user wants to save, create, or add content. Reads RULE.md to understand directory purpose and follows specified rules. Recommends target directory based on content analysis.

Structured methods for finding connections across disciplines. Use when exploring how concepts from one field illuminate another, seeking novel applications, or analyzing structural similarities between domains.

Multi-reviewer gate with canonical diff_hash and review rounds.

Decompose human demands into atomic meta skills using OpenClaw Skill Forge Cutter. Run standalone skills (memory_backup, strategy_backtest) or orchestrate OpenClaw skills.

Extract CodeRabbit review findings for the current repository and generate a triaged markdown report. Use this when the user asks about CodeRabbit findings, review issues, or wants to see code review results.

Provides auto-detection heuristics and coordination patterns for Claude Code Agent Teams. Determines when parallel team workflows outperform single-agent execution. Activates when user mentions "agent team", "parallel review", "team debug", or when commands auto-detect team suitability. NOT for single-agent workflows (use Task tool subagents). NOT for subagent coordination within one session.

Query JASPAR for transcription factor binding site (TFBS) profiles (PWMs/PFMs). Search by TF name, species, or class; scan DNA sequences for TF binding sites; compare matrices; essential for regulatory genomics, motif analysis, and GWAS regulatory variant interpretation.

Expert guide for building AI agents with the Claude Agent SDK (Python & TypeScript). Use this skill PROACTIVELY whenever: - Building or configuring AI agents with `claude_agent_sdk` or `@anthropic-ai/claude-agent-sdk` - Working with `query()`, `ClaudeAgentOptions`, `AgentDefinition`, hooks, sessions, subagents, MCP, or custom tools - User asks how to automate tasks, build pipelines, or orchestrate multi-agent workflows with Claude - Implementing permission controls, `canUseTool` callbacks, or tool restrictions - Connecting external services (databases, APIs, browsers) to a Claude agent via MCP - Debugging or optimizing agent behavior, streaming, sessions, or hooks - Any mention of "Claude agent", "agent SDK", "agentic loop", or autonomous Claude workflows Covers the full SDK: query API, built-in tools, hooks lifecycle, session management, subagents, MCP servers, custom in-process tools, permission modes, user input flows, and authentication.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Covers UI/UX design, accessibility (WCAG 2.1), design systems, and responsive patterns.

Covers thermal rating models (CIGRE TB 601, IEEE 738), conductor physics, and electrical properties.

Researches real-world problems, competitor solutions, and customer complaints before test planning. Posts findings as Linear comment for ln-522 and ln-523.