Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Use Raymon’s MCP server to search and inspect Ray-style logs. Use when you need to (1) set up Raymon as an MCP server (local or remote with auth), (2) search stored entries with filters/pagination, or (3) fetch full entry payloads by UUID for debugging/triage.
Use this skill when the user asks to use SAGAN to fit a spectrum, do spectral fitting with SAGAN, or fit AGN or galaxy emission-line or absorption-line spectra with SAGAN.
Domain-grounded judgment for creation: code, visuals, documents, design, data artifacts, and other output where quality depends on choosing what not to include. Use this skill when the user wants something to feel authored rather than generated, when the brief says a draft feels off, when polish alone is insufficient, or when the deliverable is externally visible and the quality bar is shaped by practitioner norms. Triggers on requests like 'use taste', 'apply taste', 'make this good', 'tighten this', 'clean this up', 'less is more', 'this feels generated', or any creation task where judgment matters more than coverage. Do not use for exhaustive extraction, rote transformation, or work where comprehensiveness is the explicit goal.
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher-cli tool.
>
Initialize a repository for ASDLC adoption with AGENTS.md and directory structure
We need this skill because decisions are only as good as the quality and visibility of data. This specific skill prevents unnoticed quality drift after updates.
Plan-spec-implement workflow for structured development. Only use when explicitly directed by user or when mentioned in project AGENTS.md file. Generates ephemeral plans in ~/.dot-agent/, applies specs to project docs, then implements test-first.
Use this skill when loading and managing resources in PixiJS v8. Covers Assets.init, Assets.load/add/unload, bundles, manifests, background loading, onProgress, caching, spritesheets, video textures, web fonts, bitmap fonts, animated GIFs, compressed textures, SVG as texture or Graphics, resolution detection, per-asset data options, and forcing a specific loader with the parser field (for extension-less URLs). Triggers on: Assets, Assets.load, Assets.init, loadBundle, manifest, backgroundLoad, Spritesheet, Cache, LoadOptions, unload, parser, loadParser, loadWebFont, loadBitmapFont, loadVideoTextures, GifSource, VideoSourceOptions.
Foundry is a Rust-based toolkit for developing, testing, and deploying Ethereum smart contracts using Solidity.
GRC (Governance, Risk, Compliance) manages organizational policies, risks, and regulatory compliance.
Writing SAiST static analysis rules in Lua — both shipped rules in the auditor-addon repo and custom per-engagement rules in audit workspaces. Use when the user wants to create a new detection rule, add a security check, implement a code smell detector, turn a confirmed finding into a reusable rule, or extend the rule set. Covers rule types (scope/deep/map), the Lua API, language scoping, finding kinds, custom rules, and testing patterns.
Create a ComfyUI workflow from a template
>-
Plan mode for clawg — inspect context, write a markdown plan into the active workspace's `.clawg/plans/` directory, and do not execute the work.
Search code across ComfyUI repositories from the terminal using [cs.comfy.org](https://cs.comfy.org).
>-
You are a specialist in Argo CD 3.3, the current release as of April 2026. For foundational ArgoCD knowledge, refer to the parent technology agent. This agent focuses on what is new or changed in 3.3.
>-
Prepare for a customer or prospect call using Common Room signals. Triggers on 'prep me for my call with [company]', 'prepare for a meeting with [company]', 'what should I know before talking to [company]', or any call preparation request.
Expert waterproofing specialist with deep knowledge of membrane systems, liquid-applied coatings, and moisture management. Use when addressing waterproofing design, material selection, failure analysis, or quality inspection. Use when: construction, skilled-trades, waterproofing, moisture-control, membrane.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Triage failing PR checks with gh CLI, identify first actionable root cause, and derive exact local repro commands.
Set up continuous integration and deployment with GitHub Actions, build verification, and deployment gates.
Communication specialist - generates Worker instructions and formats user feedback
Analyzes source code or requirements to generate high-fidelity screen and state transition diagrams. Specialized in SPA state mapping.
Guided workflow for creating a new Volon plugin — ideation, requirements, spec, plan, tasks.
CodeQL suppressions, security vulnerability troubleshooting, and security best practices
Run the Wavecraft CI checks locally. Prefer the native `cargo xtask` commands for speed; use Docker + `act` only when validating GitHub Actions workflows or Linux-specific behavior.
Expert network engineer specializing in cloud and hybrid network architectures, security, and performance optimization. Masters network design, troubleshooting, and automation with focus on reliability, scalability, and zero-trust principles.
Phase guidance for the neuroflow /tool-validate command. Loaded automatically when /tool-validate is invoked to orient agent behavior, relevant skills, and workflow hints for the tool-validate phase.
QA completa landing page: build, Lighthouse, accessibilita, visual check 3 viewport, reduced-motion, CLS. Usa quando l'utente vuole verificare la qualita, testare la landing, o dice lp qa, controlla, verifica, test landing, qualita, lighthouse.
Use when creating or updating JavaScript/TypeScript libraries in this monorepo; require building the library first and then running yarn in `_templates/react_template` so the template picks up the latest local library version.
Use this skill when creating or querying VCSDD Chainlink bead traceability. Provides bead creation patterns, chain traversal, and completeness validation.
Turn ambiguous software requests into BDD-style implementation-ready specs with clear scope, constraints, assumptions, acceptance criteria, validation steps, execution guardrails, and an implementation plan. Use this whenever the user is defining requirements, asking for a plan or spec, wants boundaries clarified before coding, mentions acceptance criteria or BDD, or when coding would be risky without first making done explicit.
Professional finance research toolkit — backtesting (7 engines), factor analysis, options pricing, 71 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 5 data sources (tushare, yfinance, okx, akshare, ccxt).
Interact with skills to extend capabilities. Skills are defined in SKILL.md files located in workspace/skills (system) or project directory (project-specific).
Agent Evaluation System - designs failure modes, metrics, eval test suites, SME labeling, and production data evaluation pipelines
Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant.
Implements OAuth 2.0/2.1 authorization flows in Fastify applications — configures authorization code with PKCE, client credentials, device flow, refresh token rotation, JWT validation, and token introspection/revocation endpoints. Use when setting up authentication, authorization, login flows, access tokens, API security, or securing Fastify routes with OAuth; also applies when troubleshooting token validation errors, mismatched redirect URIs, CSRF issues, scope problems, or RFC 6749/6750/7636/8252/8628 compliance questions.
Monitor X/Twitter post replies for keyword triggers and auto-DM followers with gated content. Use when setting up lead-gen campaigns, gated PDF/repo distribution, or automated DM funnels on X. Handles reply polling, follower verification, DM delivery, follow-nudge replies, unsuccessful_first_dm retry list, ignore list, and per-action cost tracking.
Guides development of Fastify Node.js backend servers and REST APIs using TypeScript or JavaScript. Use when building, configuring, or debugging a Fastify application — including defining routes, implementing plugins, setting up JSON Schema validation, handling errors, optimising performance, managing authentication, configuring CORS and security headers, integrating databases, working with WebSockets, and deploying to production. Covers the full Fastify request lifecycle (hooks, serialization, logging with Pino) and TypeScript integration via strip types. Trigger terms: Fastify, Node.js server, REST API, API routes, backend framework, fastify.config, server.ts, app.ts.
Validate all intermediate calculations during inference are correct using source of truth values
Build specialized user interfaces for interacting with Agents
> **AGENT NOTICE:** This file is the canonical skill definition for all MoltWar agents. It is updated periodically by the platform operators to reflect new APIs, behavioral rules, and capabilities. **
**Role**: QA Tester / Quality Assurance Engineer
Create comprehensive Claude Code Skills through elicitation-driven development
**Version**: 1.0
CI/CD pipeline verification, Docker container security, environment management, and deployment workflow
Master multi-agent swarm orchestration. Spawns and coordinates specialized personas for large projects that exceed single-agent context limits. Manages 10-phase SDLC with checkpoints, memory, and human-in-the-loop gates.