datasheet
Extract structured information from integrated circuit and component datasheets (PDF files or URLs) and generate consistent markdown summaries. Use when the user requests to extract, summarize, analyze, or document information from IC/component datasheets, or when they provide a datasheet and want structured documentation. Triggers on phrases like "extract this datasheet", "summarize this datasheet", "analyze [component name]", "document this IC", or when working with datasheets for hardware design.
What this skill does
# Datasheet Extract focused, goal-oriented information from IC and component datasheets using a specialized autonomous agent. ## Overview This skill delegates datasheet extraction to a specialized autonomous agent (`datasheet-agent`) that: - Processes PDFs (local files) or URLs - Extracts 2 goal-oriented sections: 1. **Circuit Design Information**: Pinout, power requirements, logic levels, package (everything needed to wire the component) 2. **Microcontroller Code Information**: Communication interface, initialization sequence, key registers, operating modes (everything needed to write firmware) - Generates focused markdown files (~90-120 lines) in `datasheets/` directory - Ensures 100% accuracy for critical information (pinouts, communication parameters, register addresses) - Omits detailed electrical tables, timing diagrams, and application circuits available in original datasheet **Context Efficiency**: The agent processes the datasheet in an isolated context. PDF content is loaded into the agent's context and discarded when the agent completes, keeping the main conversation clean and minimizing token usage. ## How to Use When a user requests datasheet extraction: 1. **Identify the input**: User provides either: - Local PDF path: `/path/to/datasheet.pdf` - URL: `https://example.com/datasheet.pdf` 2. **Validate input**: - For local files: Verify the file exists and is accessible - For URLs: Confirm the URL is well-formed 3. **Delegate to agent**: - Use the Task tool to invoke the `datasheet-agent` subagent - Provide clear context about the datasheet source (path or URL) - Let the agent execute the full 6-step extraction workflow autonomously Example delegation: ``` "I'm delegating this datasheet extraction to the datasheet-agent. Please process [URL/path], extract goal-oriented information focused on circuit design and microcontroller code development, and save the focused markdown output to the datasheets/ directory." ``` 4. **Present results**: When the agent completes, show the user: - File location (e.g., `datasheets/74HC595.md`) - Component name and key characteristics - Brief summary of what was extracted - Any issues or notes from extraction (missing sections, ambiguities resolved, etc.) ## Agent Responsibilities The `datasheet-agent` autonomously handles: - **Step 1**: Receive and validate input (PDF path or URL) - **Step 2**: Read datasheet using Read tool (PDF) or WebFetch (URL) - **Step 3**: Extract 2 goal-oriented sections focused on circuit design and code development - **Step 4**: Generate focused markdown file (~90-120 lines) with proper formatting - **Step 5**: Verify completeness, accuracy, and focused scope - **Step 6**: Return summary with file location and key component info For full workflow details, see `.claude/agents/datasheet-agent.md` ## Example Invocations User might say: - "Extract this datasheet: https://www.ti.com/lit/ds/symlink/sn74hc595.pdf" - "Summarize the ATmega328P datasheet for me" - "I need documentation for this IC: /path/to/lm358.pdf" - "Help me understand the 74HC595" - "/datasheet https://example.com/datasheet.pdf" ## Reference Materials - **Example output format**: See `references/example_output.md` for a complete example of expected markdown output - **Agent workflow details**: See `../../.claude/agents/datasheet-agent.md` for complete extraction workflow ## Benefits of Agent-Based Architecture - **Context efficiency**: PDF content stays in agent's isolated context, not main conversation - **Clean conversation**: Main conversation only sees high-level progress and final summary - **Token savings**: ~9,000+ tokens saved in main conversation for typical datasheet (PDF content discarded when agent completes) - **Consistent output**: Agent follows same workflow every time, ensuring reliable results - **Easy maintenance**: Update agent definition without changing skill interface
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.