CANN Image Release Engineer
You are a software development engineer responsible for automating and executing the CANN Docker image release pipeline.
Apply Patch
Apply AI-generated code edits from a response file to the local codebase.
devup-ui
Zero-runtime CSS-in-JS preprocessor for React. Transforms JSX styles to static CSS at build time. TRIGGER WHEN: - Writing/modifying Devup UI components (Box, Flex, Grid, Text, Button, etc.) - Using styling APIs: css(), globalCss(), keyframes() - Configuring devup.json theme (colors, typography, extends) - Setting up build plugins (Vite, Next.js, Webpack, Rsbuild, Bun) - Debugging "Cannot run on the runtime" errors - Working with responsive arrays, pseudo-selectors (_hover, _dark, etc.) - Using polymorphic `as` prop or `selectors` prop - Working with @devup-ui/components (Button, Input, Select, Toggle, etc.)
follow-up
Find emails needing follow-up -- unanswered sent emails, flagged unreplied, draft contextual responses
webperf-core-web-vitals
Intelligent Core Web Vitals analysis with automated workflows and decision trees. Measures LCP, CLS, INP with guided debugging that automatically determines follow-up analysis based on results. Includes workflows for LCP deep dive (5 phases), CLS investigation (loading vs interaction), INP debugging (latency breakdown + attribution), and cross-skill integration with loading, interaction, and media skills. Use when the user asks about Core Web Vitals, LCP optimization, layout shifts, or interaction responsiveness. Compatible with Chrome DevTools MCP.
Io.Github.Codeturion/Codesurface
Indexes your codebase's public API and serves it via compact MCP tool responses.
learned-codex-proxy-tool-calls-parse
Parse ChatGPT Codex backend SSE for tool_calls (content_part.added, output_item.done, function_call_arguments.delta/done) and return OpenAI Chat Completions format. Use when implementing or fixing tool call parsing in a Codex reverse proxy (OpenAI-compatible /v1/chat/completions) that consumes Responses API-style SSE.
API Development
Build REST APIs with proper error handling, status codes, request validation, response formatting, and rate limiting. Apply when creating API routes, handling errors, validating input, or designing API responses.
Bionicforms Mcp
Build forms, manage responses, and run AI analysis via the BionicForms API.
graffiti-best-practices
Use when generating or refactoring Graffiti UI markup so output is class-first, semantic, accessible, responsive, and aligned with current Graffiti capabilities.
api-endpoint-generator
Scaffold complete REST API endpoints with input validation, error handling, typed request/response, JSDoc or docstrings, and a unit test stub. Use when asked to create a new API route, endpoint, controller, handler, or REST resource in Express.js (TypeScript) or FastAPI (Python). Produces production-ready code following immutable patterns, Zod/Pydantic validation, and RFC 7807 error responses.
37signals-api
Builds REST APIs using respond_to blocks with Jbuilder templates following the 37signals same-controllers-different-formats philosophy. Use when adding API endpoints, JSON responses, token authentication, or when user mentions API, JSON, REST, or Jbuilder.
chat-sdk
Build multi-platform chat bots with Chat SDK (`chat` npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI streaming, (3) Set up webhook routes or multi-adapter bots, (4) Send rich cards or streamed AI responses to chat platforms, (5) Build or maintain a custom adapter or state adapter. Triggers on "chat sdk", "chat bot", "slack bot", "teams bot", "google chat bot", "discord bot", "telegram bot", "whatsapp bot", "@chat-adapter", "@chat-adapter/state-", "custom adapter", "state adapter", "build adapter", and building bots that work across multiple chat platforms.
403-bypass
Use when encountering HTTP 403 Forbidden responses during pentests or bug bounty hunting, testing access control bypasses, trying to reach restricted endpoints, admin panels, or protected API routes. Also trigger when the user says "403 bypass", "bypass forbidden", "access denied bypass", "forbidden page bypass", or "trying to access restricted endpoint". Use this whenever a 403 needs to be tested - not just blindly accepted.
building-streamlit-chat-ui
Building chat interfaces in Streamlit. Use when creating conversational UIs, chatbots, or AI assistants. Covers st.chat_message, st.chat_input, message history, and streaming responses.
alert-manager
This skill should be used when the user asks to "set up SEO alerts", "monitor rankings", "notify me when rankings drop", "traffic alerts", "watch competitor changes", "alert me if rankings drop", "notify me of traffic changes", or "watch my keywords for changes". Sets up and manages alerts for critical SEO and GEO metrics including ranking drops, traffic changes, technical issues, and competitor movements. Enables proactive monitoring and quick response to issues. For detailed rank analysis, see rank-tracker. For comprehensive reporting, see performance-reporter.
api-connector
Connect to REST APIs, manage authentication, and process responses. Use for API integration tasks.
houtu-dependencies
houtu-dependencies enterprise-grade Spring Cloud microservice foundational framework complete usage guide. GroupId is io.github.lujiafa, covering unified response, exception handling, parameter parsing, session authentication, permission control, signature verification, anti-replay, distributed lock, rate limiting, database field encryption, config decryption, access logging, canary routing, weighted load balancing, Feign enhancement, Sentinel circuit breaking, service discovery, Swagger documentation, crypto utilities, HTTP client, monitoring metrics, and other enterprise-grade capabilities. When the project build file (pom.xml or build.gradle/build.gradle.kts) contains io.github.lujiafa or houtu-related dependencies, or when the user mentions houtu or houtu-dependencies, this Skill must be read and code must be generated strictly following framework conventions. Even if the user is simply doing regular Spring Boot development (e.g., writing Controller, Service, Feign), as long as the project includes houtu, the houtu approach must be used instead of native Spring. When the user explicitly wants to use the houtu framework and the project has not yet included it, proactively add the BOM and required Starters; when the project already includes it, proactively identify and import required module dependencies based on business scenarios during coding, naturally integrating framework capabilities to enhance business services based on business semantics, rather than waiting for the user to specify each one.
animation-best-practices
CSS and UI animation patterns for responsive, polished interfaces. Use when implementing hover effects, tooltips, button feedback, transitions, or fixing animation issues like flicker and shakiness.
gilfoyle
SRE agent that does what you can't. Queries your observability stack. Finds root causes. Doesn't panic. Doesn't guess. Doesn't care about your feelings. Use for incident response, debugging, root cause analysis, or log analysis.
customer-service-expert
Expert guidance for improving customer service assistants. Use when optimizing UX, response time, tone, wording, conversation flow, or evaluating customer service quality.
Io.Github.Crypto Ninja/Github Mcp Server
AI-optimized GitHub MCP server: 112 tools, 98% token reduction, compact responses.
hyperfocus
ADHD-friendly output formatting for Codex. Restructures responses with evidence-based cognitive accessibility: chunking, visual hierarchy, front-loaded key points, and progressive disclosure. Three modes: clean, flow (default), zen. Use when user says "hyperfocus", "focus mode", "adhd mode", "adhd friendly", or invokes /hyperfocus.
castella-a2a
Connect to A2A protocol agents from Castella. Communicate with agents, display agent cards, send messages, handle responses, and stream results.
backend-mvp-guardrails
Use when designing or reviewing a backend MVP with tight budget, evolving schema, and reliance on third-party backends where idempotency, replay, and responsibility attribution are high-risk.
second-thought
Use when an idea, decision, design, plan, response, tool call, or action is about to be accepted or executed, especially during brainstorming, convergence, and pre-execution where shallow agreement or goal drift may occur.
rill
Re-review a PR after the author has pushed updates in response to previous feedback
agent-smoke-e2e
End-to-end smoke check of the moraine MCP server. Exercises every MCP tool against a live moraine stack and prints a per-tool PASS/FAIL matrix. Use inside the dev sandbox after a fresh build to confirm the MCP binary actually serves its tools and returns shaped responses.
Tap into Claude Code API requests via a local reverse proxy. Inspect system prompts, messages, tools, and token usage.
Run real E2E tests against Codex CLI (OpenAI Responses API) through claude-tap proxy
codex-window-debug
Use this skill when you need to verify that messages and responses appear in both: - Codex.app UI - Farfield web UI and server stream data
figma-design-to-code
Implement or update project-consistent UI code from a Figma selection or nodeId using TemPad Dev MCP. Use when the user wants visible Figma UI recreated, ported, or integrated into the target project's framework, styling system, tokens, and existing components when available. Do not use for design critique, product invention, generic code review, or for guessing hidden states, responsiveness, or behavior not shown in design or project evidence.
Crowdsentinel Mcp Server
AI-powered threat hunting and incident response MCP server for Elasticsearch/OpenSearch
responsecache-development
Cache entire HTTP responses using spatie/laravel-responsecache, including standard caching, flexible (stale-while-revalidate) caching, cache profiles, replacers, and selective cache clearing.
Io.Github.Cvrt Jh/Wordpress Mcp
Lightweight WordPress MCP server - 42 tools, token-optimized (95% smaller responses)
Zigpoll
Analyze Zigpoll survey responses, track trends, and get AI-powered insights.
alicloud-ai-audio-asr
Transcribe non-realtime speech with Alibaba Cloud Model Studio Qwen ASR models (`qwen3-asr-flash`, `qwen-audio-asr`, `qwen3-asr-flash-filetrans`). Use when converting recorded audio files to text, generating transcripts with timestamps, or documenting DashScope/OpenAI-compatible ASR request and response fields.
medialibrary-development
Build and work with spatie/laravel-medialibrary features including associating files with Eloquent models, defining media collections and conversions, generating responsive images, and retrieving media URLs and paths.
call_foundry_agent
Call Foundry agent with a prompt and get the response.
Io.Github.Cvrt Jh/Clickup Mcp
Lightweight ClickUp MCP server - 37 tools, token-optimized (95% smaller responses)
browse
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this".
oz-room-mentions
Poll oz-workspace for @mentions and post agent responses back to rooms.
local-web-search
Use when the user asks for web search that should run via the local-160 Responses API with web_search tool (base URL like https://proxy.example.com, model gpt-5.2-codex(xhigh)). Includes script to query the local endpoint and return summary + citations; use for periodic news monitoring and on-demand searches.
Add Generative Answers
Add `SearchAndSummarizeContent` nodes to generate responses grounded in the agent's knowledge sources.
customer-support-builder
Guide users through building a custom customer support automation skill for their company. Walks through planning integrations, writing scripts for their support stack (Zendesk, HelpScout, Intercom, etc.), creating response templates, and setting up an automated triage workflow. Use when users want to create their own support automation.
/strategic-partner â Chief of Staff for Claude Code
> **Behavioral context trigger.** Activating this skill loads the advisor persona, > startup sequence, and responsibilities. This is not an implementation session.
Io.Github.QuantuLabs/Hivemind
Query multiple AI models (OpenAI, Anthropic, Google) for consensus responses.
picasso
The ultimate frontend design and UI engineering skill. Use this whenever the user asks to build, design, style, or improve any web interface, component, page, application, dashboard, landing page, artifact, poster, or visual output. Covers typography, color systems, spatial design, motion/animation, interaction design, responsive layouts, sound design, haptic feedback, icon systems, generative art, theming, React best practices, and DESIGN.md system generation. Also use when the user asks to audit, critique, polish, simplify, animate, or normalize a frontend. Triggers on any mention of "make it look good," "fix the design," "UI," "UX," "frontend," "component," "landing page," "dashboard," "artifact," "poster," "design system," "theme," "animation," "responsive," or any request to improve visual quality. Use this skill even when the user does not explicitly ask for design help but the task involves producing a visual interface.
ceos-accountability
Manage the Accountability Chart â the organizational structure that defines who owns what seat, what each seat's 5 key responsibilities are, and the reporting hierarchy. Every function of the business has one clear owner. A person can own multiple seats, but every seat needs exactly one owner.
agent-recorder-fixtures
Record real OpenAI/Anthropic HTTP back-and-forth (requests + responses, including streaming text/event-stream) and print paste-ready Swift fixtures for SwiftAgent unit tests (ReplayHTTPClient) using the AgentRecorder CLI or HTTPReplayRecorder. Use when adding/updating any provider adapter tests (text, streaming, structured outputs, tool calls), when payload formats change, or when debugging agent loop mismatches by inspecting recorded JSON/SSE payloads.
azure-ai-docs
Tips and guidance to ensure responsible use of AI when utilizing the GenAI Prompt skill.