Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.

Cancel a Paddle subscription from a Next.js Server Action — auth, ownership check, safe `effectiveFrom` default, revalidation, and the `canceled` vs `scheduledChange` distinction.

Render country-localized prices on a Next.js pricing page using Paddle.js PricePreview — country detection, billing frequency toggle, and currency formatting.

Prepare Langfuse weekly production reviews covering failures, fixes, open issues, and tracking gaps. Use for "what broke last week," production bugs, Datadog alerts or error patterns, incident.io activity, or pager load.

Bind Insight tests to the requirements they prove, the canonical Studio way: a FEATURE's Definitions of Done are what tests verify, a test names the DoD or flow ID it proves, and quality vectors stay on the PRD's NFRs. Use when choosing the suite for a check, linking a test to its FEATURE, checking a DoD item off, or reviewing whether a feature's requirements are proven.

Quick-action diagnostic skill to audit installed CLI binaries and authentication states across Quintet providers (Claude, Codex, Antigravity, Copilot, Qwen, OpenCode). Use when verifying provider pools or diagnosing CLI readiness via /doctor.

AI 文案去味器。用户提供 AI 生成的文本（公众号/小红书/电商文案等），觉得“太 AI 味”要改得更自然、更像人写的时使用。输出自然有人味的中文。De-AI writer: rewrite AI-generated copy (WeChat articles, Xiaohongshu, e-commerce) into natural, human-sounding Chinese text.

Usar tras definir el sector de un proyecto: prepara un dossier en español con contexto, normas aplicables, patrones UX y riesgos, distinguiendo fuentes verificadas de hipótesis.

Collects and synthesizes open-source intelligence (OSINT) about threat actors, malicious infrastructure, and attack campaigns using publicly available data sources, passive reconnaissance tools, and dark web monitoring. Use when investigating external threat actor infrastructure, performing pre-engagement reconnaissance for authorized red team assessments, or enriching CTI reports with publicly available adversary context. Activates for requests involving Maltego, Shodan, OSINT framework, SpiderFoot, or infrastructure reconnaissance.

Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific proof obligation benefits from formal verification; use proof-writer for ordinary mathematical drafting.

Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved, with a fresh landing review and human approval. Base Codex review is same-family provisional. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says "渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html", or wants a polished web-rendered view of a Markdown artifact.

Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.

Use when writing or reviewing Python code in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers `client.agent.v1.connect()`, `AgentV1Settings`, `send_settings`, `send_media`, event handling, and function/tool calling. Full-duplex STT + LLM + TTS with barge-in. Use `deepgram-python-text-to-speech` for one-way synthesis, `deepgram-python-speech-to-text` / `deepgram-python-conversational-stt` for transcription only. Triggers include "voice agent", "agent converse", "full duplex", "interactive assistant", "barge-in", "agent.v1", "function calling", "AgentV1Settings".

Use when the user wants to modernize iOS code to iOS 17/18 patterns, migrate from ObservableObject to @Observable, update @StateObject to @State, or adopt modern SwiftUI APIs.

Use when the user has a crash log (.ips, MetricKit JSON, legacy .crash text, .xccrashpoint bundle, or pasted text) that needs analysis.

Extract, suggest, and sync tags and categories for blog posts across all major CMS platforms. Supports WordPress REST API, Shopify GraphQL, Ghost Content API, Strapi REST/GraphQL, and Sanity GROQ. Generates tag suggestions from content analysis (keyword frequency, heading extraction, semantic grouping), enforces minimum post-count thresholds to prevent thin tag archives, and syncs taxonomy via authenticated API calls. Use when user says "tags", "categories", "taxonomy", "tag suggestions", "sync tags", "WordPress tags", "Shopify tags".

Use when bundling a new plain Java/Kotlin plugin into MPS distribution archives, debugging packaging/layout issues in `build/mps*.xml`, tracing where per-plugin artefacts end up, or editing `plugins/mps-build/solutions/mpsBuild/models/build.mps` (the source of truth that generates every `build/mps*.xml`). The skill covers the generated Ant pipeline, plugin-to-distribution wiring, and the per-plugin / aggregator / distribution layers.

Import and use Kubb's generated code (types, clients, hooks, schemas, mocks). Use when writing app or test code that consumes a Kubb build.