Optimize existing Azure resources and analyze Reservations or Savings Plans. WHEN: "optimize Azure costs", "reduce cloud spending", "rightsize resources", "find idle resources", "orphaned disk", "deleted VM still charged", "public IP still charging", "reservation utilization", "Savings Plan coverage", "commitment recommendation", "why is pay-as-you-go still charged". DO NOT USE FOR: cost spikes, forecasts, pricing estimates, budgets, or governance.

Turn vague "what did I do?" into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates. Uniquely mines Copilot CLI session logs to reconstruct forgotten work, plus git commits and GitHub PRs. Enforces a 3-part impact contract (action → result → evidence). Works standalone with zero dependencies. Trigger for: "brag", "log work", "what did I do", "backfill my work history", "performance review", "self-review", "self assessment", "write impact statement", "review prep", "promo packet", "promotion case", "weekly update", "status report", "accomplishments", "what did I ship", "I forgot to log my work", "summarize my work", "track my wins", "what should I highlight", "end of half", "career growth", "work journal", or any request to document, summarize, or organize work accomplishments.

Builds a pricing model, packaging/tier structure and willingness-to-pay research plan, then grades your existing pricing page or plan. Use when you ask 'how much should we charge', 'what should our pricing model be', 'seat vs usage vs outcome pricing', 'good-better-best tiers', 'what goes in the free plan', 'should we raise prices', 'freemium vs free trial', or 'how do we price our AI product'. Draws on 199 insights from 79 Lenny's Podcast guests including Madhavan Ramanujam, Naomi Ionita and Patrick Campbell.

The "make it right" pass after code works. Tests whether the change meets its requirements and reviews whether it is done correctly, verifies every finding against the source, fixes them, and reports what a human still needs to look at. Use when the user says "make it right", "review and fix", "clean this up before the PR", "get this up to standard", "review my changes", "code review this branch", "is this ready for review", "simplify this", "YAGNI review", or "QA this in the browser".

Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.

Integrate Weavr Secure UI into native Android apps. Covers Gradle dependencies, initialization, secure capture and display, KYC, biometric authentication, and Google Wallet push provisioning. Use when building Android Weavr integrations.

多源研究通道工具箱。当需要检索文献、核验引用、查基准分数、看价格与上下文、找开源实现、扫描社区信号时使用。封装了 arXiv / Crossref / OpenAlex（含引用网络）/ Epoch AI 官方 API / GitHub / Hacker News / Hugging Face / OpenRouter / Vals AI / Scale SEAL / Stanford HAI / ARC Prize / METR 共 14 个通道。触发场景：查文献、验引用、查谁引用了某篇、查某个基准的精确分数、比模型价格、找现成项目、看领域最新动态。

Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.

Create a git commit with a clear, value-communicating message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate message.

Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".

Reads recently edited pages from the notion MCP server (read-only) and writes what it found into a Markdown digest in this repo, then opens a pull request with that change. Runs unattended: it asks no questions and makes no writes to notion.

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog. Use when asked to write a commit message or a changelog entry for a change, or to split a change into commits, even when the diff is pasted inline and the message seems easy to write from it.

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

The telemetry witness: reads what the services recorded during one closed window of traffic another skill produced (ui-verify, verify, a repro), traces each acceptance criterion from web event to backend trace to database, and finds errors behind a green UI, slow paths, and missing signals. Never edits code; run on its own, it posts its receipt to the PR's verify comment. Triggers on "check the telemetry", "prove it with traces", "/telemetry-verify".

Use when creating a new change with all SDD artifacts — proposal, delta specs, design, and tasks. Triggers: "propose a change", "create a change for X", "I want to implement feature Y", "start a new change", "let's build X".

Check domain availability, compare first-year registration and annual renewal estimates, and diagnose DNS records for a domain the owner wants to connect. Use for explicit requests about a domain name, renewal price, CNAME/TXT records, www versus apex, or pending domain verification. General website design belongs to the existing website workflow.

Design and build a responsive frontend website or accessible landing page for a small business or creator from the first brief. Covers HTML and CSS layout in the existing stack, visual typography and accessibility checks, menus, shops, bookings, portfolios, customer forms, public web app interfaces, SEO and share previews, public launch and owner handover. Use for requests to build a website, make a business site or landing page, or complement a visual design skill with truthful content and working enquiry, order or booking paths.

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features