Use when the user needs to compress, condense, or summarize lengthy content while preserving ALL critical details. Triggers: "compress this", "make it shorter but keep everything", "create a cheat sheet", "dense summary", "reference format", "compact version", "information-dense". NOT for casual summaries—only when user explicitly wants maximum density with zero data loss.

Use when the user asks to research, investigate, explore, or analyze a topic requiring multiple sources. Triggers: "research X", "find out about", "what's the current state of", "compare options for", "deep dive into", "gather information on", "write a report about". NOT for simple factual questions answerable in one search—only for multi-source synthesis needing 5+ sources.

Creates image from user prompt. Use when the user wants to generate, create, or edit images using AI. Triggers: "create an image of", "generate a picture", "draw", "make an illustration", "visualize", "edit this image", "modify the photo", "change the background". Supports text-to-image generation and image editing with masks. NOT for image analysis or description—only for creating or modifying visual content.

Use ONLY for complex Python tasks requiring reusable scripts, multi-file processing, or data pipelines. DO NOT USE for: one-off calculations, web fetch + process, simple file transforms, or tasks under 30 lines. For simple tasks, just write inline Python directly with mcp__ag3ntum__Bash without loading this skill.

Run this skill before committing to catch issues early. It runs linting, structural tests, and verifies no debug artifacts remain.

Defines patterns for writing tests, including subsection tests for incremental development and acceptance criteria verification. Use when writing any tests to ensure consistent naming, structure, and coverage patterns.

Complete workflow for implementing a single subsection from the implementation plan. Orchestrates all project skills to ensure consistent, high-quality implementation with full test coverage. Use when implementing any subsection (e.g., 5.1.1, 5.2.3) to automate the entire workflow from requirements to commit.

Short alias for /subsection-implementation. Implements a single subsection from docs/implementation-plan.md with full automation. Usage: /si 5.1.1

Ensures all quality checks pass locally before committing changes. Use this skill to validate code quality, tests, and type checking before creating commits to catch issues early and avoid CI failures.

Guides implementation of features following an established workflow pattern. Use when implementing any feature to ensure consistent process: read requirements, create todos, implement code, write tests, update documentation, commit and push.

Defines the pattern for updating project documentation when completing features. Use when marking features as complete to ensure consistent documentation of implementation status, test coverage, and deliverables.

Ensures all git commits follow the Conventional Commits specification with consistent types and scopes. Use this skill when making any commit to maintain consistent commit message format, improve git history readability, and enable automatic changelog generation.

Defines patterns for implementing FastAPI REST endpoints, including route definition, request/response models, error handling, and integration tests. Use when implementing any API endpoint to ensure consistency and best practices across endpoints.

Best practices and patterns for RilayKit — a headless, type-safe React framework for building dynamic forms and multi-step workflows with builder pattern APIs, Standard Schema validation, and granular Zustand-powered hooks. Use this skill when working on projects that import @rilaykit/core, @rilaykit/forms, or @rilaykit/workflow packages, or when building forms, multi-step flows, component registries, or conditional field logic with RilayKit.

Reference for nimble tasks and batches commands. Load when polling async task status, tracking batch progress, or fetching results. Works for ALL async types: agent run-async, agent run-batch, extract-async, extract-batch, crawl (per-page tasks), search async, map async. CRITICAL: agent tasks use "success"/"error" states; crawl page tasks use "completed"/"failed".

Reference for nimble search command. Load when searching the live web. Contains: all flags, 8 focus modes (general/coding/news/academic/shopping/social/geo/location), search_depth modes (lite/fast/deep), response structure, credit costs.

Reference for nimble map command. Load when discovering URLs on a site before bulk extraction. Contains: all flags (limit 1-100000, sitemap include/only/skip, domain_filter), response structure {links[].url/title/description}, map→filter→extract pattern, map vs crawl comparison.

Reference for nimble extract command. Load when fetching URLs or scraping pages. Contains: render tiers 1-3, all flags, browser actions, network capture, parser schemas, geo targeting, async, parallelization.

Reference for nimble crawl command. Load when bulk-crawling many pages asynchronously. Contains: async workflow (create → status → tasks results), all flags, polling guidelines, CRITICAL: use task_id (not crawl_id) for results, crawl vs map comparison.

Reference for nimble agent commands. Load for Step 0 agent lookup. Contains: full agent table (50+ sites across e-commerce, food, real estate, jobs, social, travel), discover/list/schema/run commands, response shapes (PDP=dict, SERP=list, google=entities), agent memory.

Get web data now — fast, incremental, immediately responsive to what the user needs. The only way Claude can access live websites. USE FOR: - Fetching any URL or reading any webpage - Scraping prices, listings, reviews, jobs, stats, docs from any site - Discovering URLs on a site before bulk extraction - Calling public REST/XHR API endpoints - Web search and research (8 focus modes) - Bulk crawling website sections Must be pre-installed and authenticated. Run `nimble --version` to verify. For building reusable extraction workflows to run at scale over time, use nimble-agent-builder instead.

A building experience: create, test, validate, refine, and publish extraction workflows based on existing or new Nimble agents. For users who want to invest in a durable, reusable workflow for a specific domain — not get data immediately. Trigger phrases: "set up extraction for X site", "I need to extract from this site regularly", "build an agent for", "create a reusable scraper", "generate a Nimble agent", "refine my agent", "add a field to my agent", or when the user wants to run extraction at scale. For getting data immediately, use nimble-web-expert instead.

SEO intelligence toolkit covering the full lifecycle via live web data: keyword research, rank tracking, site audits, content gap analysis, competitor keyword reverse-engineering, AI visibility across five platforms (ChatGPT, Perplexity, Google AI, Gemini, Grok), and GitHub repo SEO. Crawls real sites and SERPs via Nimble CLI — no fabricated metrics. Triggers: "SEO", "keywords", "rank tracker", "site audit", "content gap", "competitor keywords", "AI visibility", "GitHub SEO", "SERP analysis", "keyword research", "technical SEO", "keyword difficulty", "topic clusters", "ranking delta", "on-page SEO", "AI citation audit". Do NOT use for competitor business signals — use `competitor-intel` instead. Do NOT use for competitor messaging — use `competitor-positioning` instead. Do NOT use for general web scraping — use `nimble-web-expert` instead.

Researches meeting attendees and their companies before any meeting using real-time web data. Surfaces roles, recent activity, company context, and talking points — then maps cross-attendee relationships. Use this skill when the user asks to prepare for a meeting, research someone they're meeting, or wants context on attendees. Common triggers: "prepare me for my meeting", "who am I meeting with", "research this person", "meeting prep", "brief me on [person]", "I have a meeting with [person/company]", "get me ready for my call", "what should I know about [person]", "background on [person] before our meeting", "attendee research". Requires the Nimble CLI (nimble search, nimble extract) for live web data. Do NOT use for multi-company competitor monitoring (use competitor-intel) or single-company deep dives without attendees (use company-deep-dive).