Explore

Guide for creating Terraform files for Azure API Management (APIM) and related Azure services. Use when users want to create, modify, or understand Terraform configurations for APIM instances, APIs, backends, subscriptions, policies, products, loggers, diagnostics, and supporting infrastructure using the azurerm provider. This skill provides HCL syntax, resource definitions, and patterns from the Terraform Registry and this repository.

Guide for creating Azure API Management (APIM) XML policies. Use when users want to create, modify, or understand APIM policies including inbound/outbound processing, authentication, rate limiting, caching, transformations, AI gateway policies, and policy expressions. This skill provides policy syntax, examples, and C# policy expressions for request/response manipulation.

Guide for creating Kusto Query Language (KQL) queries for Azure API Management tables in Azure Monitor (Log Analytics Workspace). Use when users want to query, analyze, or monitor APIM logs including gateway logs, LLM/AI logs, MCP logs, WebSocket logs, and Application Insights data. This skill provides KQL syntax, table schemas, and query patterns for APIM monitoring scenarios.

Guide for building Bicep files for Azure API Management (APIM) and related Azure services. Use when users want to create, modify, or understand Bicep templates for APIM instances, APIs, backends, subscriptions, policies, products, loggers, diagnostics, and MCP servers. This skill provides Bicep syntax, patterns from Azure Verified Modules, and examples from this repository.

Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Read source URLs from X/Twitter, articles, YouTube, Bilibili, podcasts, WeChat, Xiaohongshu, Telegram, RSS, and the open web. Use when the user provides a link and wants the original content, evidence, transcript, summary, or source-grounded analysis.

Transcribe and summarize video or podcast links, including YouTube, Bilibili, X video, Xiaoyuzhou, Apple Podcasts, and direct media URLs.

Turn source content or a verified transcript into a structured, evidence-grounded analysis with key insights, risks, and action items.

Write idiomatic, well-structured Rust for Wassette — single-responsibility design, anyhow error handling, Arc/Mutex for shared state, and the required formatting and linting with cargo +nightly fmt, cargo clippy, and cargo machete. Use when adding or refactoring Rust code in this repository.

Validate Wassette changes end-to-end by running the MCP server with just and driving it with the MCP Inspector CLI over Streamable HTTP — listing tools, resources, and prompts, and calling tools. Use before committing server changes or when debugging tool exposure and behavior.

Build, serve, and write Wassette's mdBook documentation under docs/ — concise, code-first prose, the multi-version URL layout, and navigation in SUMMARY.md. Use when editing docs/ pages or previewing the documentation site.

Ensure every Rust (.rs) file in Wassette starts with the required Microsoft copyright header, using the idempotent scripts/copyright.sh helper. Use when adding new Rust files or when a copyright-header check fails.

Build the Wassette workspace and run its test suite with the just recipes — debug and release builds, example and test components, and the combined unit plus documentation tests. Use when compiling Wassette, building example components, or running and debugging tests.

Generate a sanitized UniFi Protect support bundle, help the user review it locally, and prepare it for a bug report without posting it

Configure the UniFi Protect MCP server for a supported MCP client — set NVR host, credentials, and permissions. Also use when the unifi-protect server failed to start or its tools are missing, especially right after a plugin update, because in Claude Code the plugin no longer reads settings an earlier version saved in the project's .claude/settings.local.json, and this skill migrates them

How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person detection, vehicle search, face recognition, Known Faces, license plates, snapshots, RTSP streams, floodlights, sensors, chimes, arming/disarming the alarm, or any UniFi Protect task.

Generate a security digest summarizing events across UniFi Protect cameras, Access door events, and Network firewall activity. Use when asked about what happened overnight, security summary, event digest, recent activity, or reviewing camera and access events.

Generate a sanitized UniFi Network support bundle, help the user review it locally, and prepare it for a bug report without posting it

Configure the UniFi Network MCP server for a supported MCP client — set controller host, credentials, and permissions. Also use when the unifi-network server failed to start or its tools are missing, especially right after a plugin update, because in Claude Code the plugin no longer reads settings an earlier version saved in the project's .claude/settings.local.json, and this skill migrates them

How to manage UniFi network infrastructure — devices, clients, firewall, VPN, routing, WLANs, Traffic Flows, and statistics. Use this skill when the user mentions UniFi, Ubiquiti, network management, WiFi configuration, firewall rules, port forwarding, VPN, QoS, bandwidth, traffic flows, connected clients, network devices, or any UniFi networking task.

Run a UniFi network health check — diagnose device status, connectivity issues, firmware updates, and system health. Use when asked to check network health, find what's down, diagnose connectivity issues, or get a network status summary.

Manage UniFi firewall policies using natural language — create, modify, and review firewall rules, content filters, and traffic policies. Use when asked to block traffic, create firewall rules, manage content filtering, set up time-based access controls, or review firewall configuration.

Audit visitor activity by reading Access door events and setting them beside Network evidence from the cloud worker's timeline near the same doors. Needs the cloud worker with a connected relay. Use when the user wants recorded access activity and nearby network activity, with identity limits.

Review retrieved activity at one area in a given time window from the cloud worker's merged Network and Protect timeline, with Access door events read separately. Needs the cloud worker with a connected relay. Use when the user asks about activity at a door, entrance, room, or area.

Investigate one UniFi Network device incident (a switch, AP or gateway going offline, disconnecting or misbehaving) over an explicit, bounded time window, with Protect camera context, using only the local read-only evidence tools. Produces a cited report that states its coverage. Use when the user asks what happened to a Network device at a given time.

Generate a sanitized UniFi Access support bundle, help the user review it locally, and prepare it for a bug report without posting it

Configure the UniFi Access MCP server for a supported MCP client — set controller host, credentials, API key, and permissions. Also use when the unifi-access server failed to start or its tools are missing, especially right after a plugin update, because in Claude Code the plugin no longer reads settings an earlier version saved in the project's .claude/settings.local.json, and this skill migrates them

How to manage UniFi Access door control — locks, credentials, visitors, access policies, and events. Use this skill when the user mentions UniFi Access, door locks, door access, building access, NFC cards, PIN codes, visitor passes, access policies, access schedules, door readers, or any UniFi Access task.

Orchestrate related unifi-mcp community PRs across a bounded review team, sharing subsystem context while retaining per-PR evidence, independent verification, and integration decisions. Use for a contribution batch or an explicitly requested parallel review.

Use this skill when adding any tool that talks to the UniFi public Integration API (X-API-Key auth, /proxy/network/integration/...). The integration API uses a different ID namespace and field schema from the V2 controller API, so these tools form their own "families" with scoped IDs. Covers when to start a new family vs join an existing one, how to scope IDs in tool descriptions, the narrow conditions under which silent ID translation is allowed (rare), how to wire auth, and how to bridge between ID spaces (explicit named bridging tools only). Applies whether you are adding a read tool, a mutation tool, or a paired family of both.

Apply optional presentation conventions when the user requests Excel report formatting or a new reader-facing report through Excel MCP tools. Use for readable headers, meaningful number formats, financial-model colours, and report layout. Do not load for ordinary reads, raw exports, targeted data updates, Power Query or Data Model work, or failure recovery without a report-formatting request.

Apply optional presentation conventions when the user requests Excel report formatting or a new reader-facing report through excelcli. Use for readable headers, meaningful number formats, financial-model colours, and report layout. Do not load for ordinary reads, raw exports, targeted data updates, Power Query or Data Model work, or failure recovery without a report-formatting request.

Discover and launch the Excel CLI for ordinary Excel workbook requests on Windows, including reads, writes, formulas, data refreshes, and workbook automation. Use the installed excel-cli plugin's npx launcher and native help to find commands; report presentation conventions are a separate optional skill.

Review and validate claims using counter-hypothesis testing. Use when verifying technical content, checking references, validating API endpoints, or performing quality assurance on deliverables.

通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。

Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's native MCP endpoint.

Pre-build reality check. Scans GitHub, HN, npm, PyPI, and Stack Overflow for existing competitors before you build. Use when starting a new project, evaluating a side project idea, or doing a build-vs-buy decision.

Use when building with the yahoo-finance2 TypeScript/Deno/npm library, using its Yahoo Finance data modules, CLI, or MCP server, or contributing to the yahoo-finance2 repository including modules, validation schemas, cached fixtures, and npm/JSR build output.

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser. Use for structured website tasks, and authenticated site access with Unbrowse.

Maintain persistent, domain-neutral project memory for AI agents using Open Knowledge Format (OKF) v0.2 bundles and the deterministic okf Go toolchain. Use whenever project knowledge, decisions, runbooks, research, client notes, or domain discoveries must survive conversational resets.

Capify an existing project. Scans the repo for already-installed MCP servers, skills, rules, hooks, sub-agents, and plugins (across .claude, .cursor, .codex, .gemini, etc.), consolidates them into shared top-level directories (skills/, rules/, hooks/), and synthesizes a sound capabilities.yaml from the inventory. Use whenever the user says "bootstrap capa", "capify this project", "onboard capa onto an existing repo", "inventory my agent setup", or asks how to turn an ad-hoc Claude/Cursor/Codex configuration into a capabilities file. Use even when the user only mentions one provider — discovery should still sweep all of them.

Summarize or extract text/transcripts from URLs, podcasts, YouTube videos, and local files using the summarize CLI. Use when asked to summarize a link, article, video, or file, or to transcribe a YouTube video.

Edit or create PDFs with natural-language instructions using the nano-pdf CLI. Use when asked to make a PDF, edit a PDF, add pages, change text in a PDF, or convert content to PDF format.

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: local git operations (use git directly), non-GitHub repos, or cloning (use git clone).

Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell. Use when: (1) building new features or apps in a separate project, (2) reviewing PRs, (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit directly), reading code (use read/file tools), or work inside the SwarmClaw workspace itself.

Search and retrieve biomedical data - genes, variants, clinical trials, diagnostic tests, articles, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, and phenotype-disease matching. Use for gene function, variant pathogenicity, trials, diagnostics, drug safety, pathway context, disease workups, and literature evidence.

Do biomedical literature and variant research with the BioMCP CLI, and file what you learn about the tool itself as issues in the biomcp repo.

Search, read and compute over the user's haiku.rag knowledge base through the haiku-rag MCP tools. Use whenever a request could be answered from the user's ingested documents, when asked to find, look up, check or cite something in their documents or knowledge base, or when the question is about the user's own material rather than general knowledge.

Debug haiku.rag ingestion in Logfire. Use when asked to look at Logfire for ingestion, find failed or dead ingestion jobs, investigate retries or circuit-breaker events, trace a document through convert/chunk/embed/store, find which docling-serve instance served a request, spot slow conversions, or tell concurrent ingesters apart. Drives the Logfire MCP against the `haiku-ingester` service.

Debug haiku.rag evaluation runs in Logfire. Use when asked to look at Logfire for an eval run, find failing or low-scoring eval cases, compare runs, check citation quality (cited_map) or judge pass rate (answer_equivalent), or explain why an eval case failed. Drives the Logfire MCP against the `evals` service, or the Logfire HTTP query API when the MCP is not loaded. Also covers monitoring a run that is still in flight.

This skill should be used when the user runs /touchdesigner:snapshot or asks to see, preview, capture, or confirm the visual output of a TouchDesigner TOP — trigger phrases include "show me the output", "what does this look like", "capture the render", "snapshot the TOP", "check the visual output", or "is this TOP rendering correctly".

This skill should be used when writing, editing, or debugging Python code that runs inside TouchDesigner — scripts, expressions, DAT callbacks, Extensions, or one-off snippets passed to execute_python_script — or whenever there is uncertainty about a `td` class's methods, members, or module-level API. Trigger phrases include "TD Python", "op()", "AttributeError in TouchDesigner", "what method does X have", "write a Python expression for this parameter", "does this CHOP/TOP/DAT support Y", and any request to script TouchDesigner behavior.

This skill should be used when the user runs /touchdesigner:perf, or asks to measure where frame time is going in a TouchDesigner project — a cook-time profiling pass across the network producing a ranked list of the slowest operators. Trigger phrases include "measure cook times", "profile my TD project", "which operator is slowest", "fps dropped", and "why is this project slow". It measures and reports the numbers; it does not carry general TouchDesigner optimization advice.

This skill should be used when the user runs /touchdesigner:overview or asks for a project structure report, hierarchy summary, or health check of a TouchDesigner project — trigger phrases include "give me an overview of this TD project", "summarize the project structure", "what's in this TouchDesigner file", "map out the node hierarchy", or "audit this TouchDesigner project".

This skill should be used when the user runs /touchdesigner:launch or asks to "start TouchDesigner", "launch TD", "open TouchDesigner with the MCP component", "set up TouchDesigner from scratch", or says TouchDesigner isn't running yet — it launches the TouchDesigner application with mcp_webserver_base.tox imported and waits until the MCP connection is live. For diagnosing an already-running TouchDesigner, the setup skill applies instead.