Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on: "evolve", "self-improve", "diagnose failures", "generate skills from errors", "what went wrong and how to fix it", or any mention of A-Evolve.

KubeSphere OpenPitrix application management Skill. Use when users ask about KubeSphere App Store, OpenPitrix, Helm/YAML application templates, application repositories, app versions, app releases, categories, review states, repository sync, or troubleshooting application installation and upgrade issues.

KubeSphere Fluid management Skill. Use when user asks to install or enable Fluid, check Fluid status, view Fluid pods/logs/CRDs, create or update Dataset, AlluxioRuntime, JuiceFSRuntime, or ThinRuntime, perform DataLoad or cache warming, scale runtime, or troubleshoot Fluid issues in KubeSphere.

Use when deploying KubeEye for cluster inspection, creating InspectRule/InspectPlan resources, or retrieving inspection results. Covers InstallPlan-based deployment, OPA/PromQL/FileChange/Sysctl/Systemd/NodeInfo/FileFilter/ServiceConnect/CustomCommand rule types, and report retrieval. Always consult this skill when the user mentions KubeEye, cluster inspection, InspectRule, InspectPlan, or inspection reports.

Modularize a chrome/browser/ subfolder by splitting its sources out of the monolithic //chrome/browser:browser target into dedicated source_set targets in the subfolder's own BUILD.gn. Use when the user asks to modularize, extract, or create BUILD targets for a chrome/browser/ subfolder, or mentions "Project Bedrock", "//chrome/browser modularization", or wants to split a subfolder into header/impl/test targets. Also use when the user says "modularize chrome/browser/X" for any X.

Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry. Covers deployment patterns (client-hosted, hosted agents, agent workflows), the agent lifecycle, model routing, response caching, evaluation gates, human-in-the-loop approval, observability with OpenTelemetry, cost optimisation, and smoke-testing deployed agents with the AI Smoke Test action. Based on Lesson 16 of AI Agents for Beginners. USE FOR: deploy an agent to production, scale an agent, Microsoft Foundry hosted agent, Foundry Agent Service, model routing, response caching, evaluation gate, release gate, human approval workflow, agent observability, agent tracing, agent cost optimisation, smoke test a hosted agent, production customer support agent. DO NOT USE FOR: building your first agent (start with Lesson 01), running agents locally on-device (use local-ai-agents / Lesson 17), Azure infrastructure provisioning unrelated to agents, non-Foundry deployment targets.

Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. USE FOR: migrate to responses API, switch from chat completions, openai responses, upgrade openai SDK, responses API migration, move from completions to responses, gpt-5 migration, azure openai python migration, chat completions to responses, AzureOpenAI to OpenAI client, python azure openai upgrade. DO NOT USE FOR: building new apps from scratch (start with responses directly), Node/TypeScript/C#/Java/Go migrations (this skill is Python-only), Azure infrastructure setup (use azure-prepare), deploying models (use microsoft-foundry).

Use when generating, editing, or reviewing Scala, Python, TypeScript, JavaScript, or Rust code so company-specific practices are checked before planning, after edits, and before final handoff.

Swift concurrency patterns — actors, structured concurrency, cancellation, async streams, GCD migration, strict-concurrency diagnostics, common bug patterns. Use when writing, reviewing, or debugging concurrent Swift code.

Performs structured code reviews on TypeScript codebases covering correctness, type safety, async patterns, security, testing, and style. Use when reviewing TypeScript code, pull requests, or when asked to do a code review on a TypeScript or Node.js project.

TAPD 迭代规划技能。基于"approved"状态的需求池，结合需求依赖关系、size 规模、 优先级进行全局编排，将合适规模的需求规划进入指定迭代。支持新建迭代和已有迭代 重入两种模式，自动控制迭代总规模上限（默认 1000），通过有向无环图（DAG）分析 保证依赖需求优先入迭代。 Use this skill whenever the user mentions 迭代规划, 规划迭代, 编排迭代, iteration planning, 迭代编排, 需求入迭代, 排迭代, 拉迭代, 创建迭代, plan iteration, sprint planning, organize sprint, or any workflow involving TAPD iteration scheduling and story assignment.

Use when integrating the Lagged JavaScript SDK into an HTML5 game published on Lagged.com, adding Lagged leaderboards, handling Lagged ad placements, or setting up user authentication via the Lagged API. Initializes the Lagged SDK (window.LaggedAPI), retrieves player profile data, submits scores to native leaderboards, unlocks achievements, and integrates interstitial and rewarded ads for games on the Lagged.com game portal.

Use when generating SwiftUI iOS 26 micro-interactions and animations. Triggers on phrases like "on scroll", "when tapped", "on appear", "while dragging", "when [state] changes", "on focus", "make this animate", "spring", "morph", "collapse", "parallax", "hero transition", "matched geometry", "liquid glass", "shrink toolbar", "stagger", "shimmer", "card flip", "swipe to dismiss", "pull to refresh", "ripple", "haptic". Routes to recipe folders by interaction trigger so the agent loads only what it needs.

Use when working with VueUse composables - track mouse position with useMouse, manage localStorage with useStorage, detect network status with useNetwork, debounce values with refDebounced, and access browser APIs reactively. Check VueUse before writing custom composables - most patterns already implemented.

End-to-end New Tab train-hop targeting for the Experimenter repo. From a single trainhop version string, files the GitHub targeting issue, branches, adds the NimbusTargetingConfig entry, lints, and stages a drafted commit. Use for "newtab trainhop targeting" requests.

Rewrite a user's prompt to reduce the chance it trips Claude Fable 5's server-side safety classifiers (cyber/bio guardrails that force-route to Opus 4.8 or return stop_reason "refusal"). Use when the user hands you a prompt that touches cybersecurity, auth, exploits, malware, pentesting, or other dual-use topics and asks to make it "Fable-safe", "guardrail-safe", "won't get flagged/refused/downgraded", or to rewrite it so Fable 5 won't block it.

Use when changing npm package or dependency versions used by Meteor's modern tooling, especially Rspack and SWC. Discovers and synchronizes manifests, lockfiles, install constants, compatibility floors, skeletons, E2E fixtures, and active documentation. Verifies repository consistency but never publishes packages or releases.

Use when analyzing release branch changes for missing user-facing documentation. Compares the release branch against devel, filters for user-facing changes, scans v3-docs/docs/ for coverage, and produces a gap report (.md file) with prioritized documentation opportunities. Does NOT write documentation — only identifies gaps and outputs a plan for later action.

Make AI phone calls, buy phone numbers, and get call transcripts via x402. USE FOR: - Making AI-powered outbound phone calls - Scheduling calls and getting transcripts - Buying and managing phone numbers - Leaving voicemails - Transferring calls to humans - Checking if a number has iMessage/FaceTime TRIGGERS: - "call", "phone call", "make a call", "dial" - "buy number", "phone number", "get a number" - "voicemail", "leave a message" - "transcript", "call recording", "call summary" - "AI call", "automated call", "bland" - "imessage", "facetime", "check number", "lookup number" ALWAYS use `npx agentcash@latest fetch` for stablephone.dev endpoints. IMPORTANT: Use exact endpoint paths from the Quick Reference table below.

Generate images, videos, and SVGs using x402-protected AI models at StableStudio. USE FOR: - Generating images from text prompts - Generating videos from text or images - Editing images with AI - Vectorizing images to SVG - Creating visual content TRIGGERS: - "generate image", "create image", "make a picture" - "generate video", "create video", "make a video" - "edit image", "modify image" - "vectorize", "convert to svg" - "stablestudio", "nano-banana", "sora", "veo", "grok", "flux", "seedance", "gpt-image" ALWAYS use `npx agentcash@latest fetch` for stablestudio.dev endpoints.