В каталоге 183 730 навыков в 14 категориях.
Progressive four-tier URL content scraping with automatic fallback strategy. USE WHEN user says "scrape this URL", "fet...
Progressive URL scraping with four-tier fallback - WebFetch, Curl, Browser Automation, Bright Data MCP. USE WHEN scrape...
Progressive URL scraping. USE WHEN Bright Data, scrape URL, web scraping tiers. SkillSearch('brightdata') for docs.
Discover TikTok influencers by keyword search using Bright Data API
Use when implementing CQRS command dispatching, request pipelines, and asynchronous task queues with Paramore Brighter i...
8-mode brightness system implementation with CSS custom properties. Use when implementing theme switching, color tokens,...
Banking interface for AI bots and automation. Get a bank account, issue a Mastercard, buy and sell crypto, send payments...
The on-ramp for any Built GTM analyst skill when your tools are not connected yet. Tells you exactly what to paste or up...
Query Briscoes NZ homewares product search, sale/deal snapshots, SKU detail, and store-finder. Use for Briscoes product...
Enforce British English spelling, grammar, and conventions in all written content
Author-guideline skill for British Food Journal (Emerald, ISSN 0007-070X). Use to format or check a manuscript for BFJ —...
Re-explain the previous assistant message, or any text typed after the command, in a much simpler way. For when a reply...
Restate the last message in plain human language, with no jargon.
Say your previous reply again in plain, everyday language with the jargon removed, shorter and simpler. Use for "/bro",...
Restates the previous response in plain, concise language. Use only when the user invokes bro or explicitly asks for a s...
Use when the previous technical answer needs a direct, jargon-free restatement.
Restate the last message in plain human language, with no jargon
Explain the previous answer or connected thread so its practical meaning is clear. Use on /bro, /bro shorter, or request...
Restate the last message in plain human language, with no jargon. Use for /bro or when asked to say it plainly.
Use when the user asks to restate or explain the last message in plain, jargon-free language.
Restate the last message in plain human language with no jargon, or explain a topic simply to a non-technical listener....
This skill intentionally requests broad tool access.
当需要为专业或小众内容吸引初始流量和广泛关注时
Apply the same change across multiple repos simultaneously using parallel agent teams. Creates worktrees, applies change...
Turn Innovation project updates into clear, audience-specific status communications for Slack, email, and executive summ...
Expert skill for Broadcom
Name | Type | Description | Notes
Generates premium, multi-page, mobile-optimized (1:1 aspect ratio) PDF marketing brochures for exclusive retreats, works...
Placeholder skill so the bundle passes plugin-format validation.
This SKILL.md has no YAML frontmatter fence. It must still be listed (with the directory name as its name and empty trig...
Security testing skill for A01:2025 Broken Access Control — the #1 OWASP risk for two consecutive cycles. Use this skill...
Detects missing ownership checks, broken role enforcement, and IDOR vulnerabilities that let users access other users' r...
Use when auditing metadata, crawlability, structured data, or indexability related to Fix malformed HTML structure. Veri...
Greets the user in the style described in references/style.md. Use when the user asks for a greeting or says hello.
Customer reports broken links, missing resources, or 404 errors on the website or in course materials.
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports...
Scan the vault for broken [[wiki-links]] and suggest fixes using parallel Sonnet sub-agents.
Scan a codebase for broken links — dead URLs in Markdown/HTML, broken file references, invalid import paths, stale ancho...
Use when the request mentions `.lando.yml`, `lando rebuild` or a fixture runner and you need a contract-compliant exampl...
A skill with broken cross-references
作業の途中で見つけた割れ窓と人間の指摘を、別コンテキストで起票する。
Message broker setup patterns (Redis, RabbitMQ, SQS) for Celery including connection strings, SSL configuration, high av...
Add a broker to OpenAlgo Desktop or change an existing Rust broker adapter under src-tauri/src/brokers/. Use when portin...
Connect Claude to Indian brokers and use them safely: official MCP servers for Groww, Zerodha Kite, Dhan, Upstox, Fyers...
Alpaca broker limitations: crypto shorts blocked (broker doesn't support), stock shorts allowed. Trigger when: (1) short...
Persist a ratified arc42 architecture Workfile into the target project by its layout map — creating the fixed folder lay...
Create and maintain technical documentation and project documentation.
Perform local git operations — branching, staging, committing — without modifying existing history.
Distill reviewed findings into Yggdrasil Memory — the persistent, source-cited knowledge base; establish, consolidate, a...
Design and implement APIs, backend services, databases, frontends, and refactoring with testing discipline across the fu...
Write precise, structured agent definitions, system prompts, and skill files that produce reliable, controllable agent b...
Record one reviewed batch of a test-driven plan as one commit — verify the gating reviews passed, verify or create the p...
Implement a bounded work package by the red-green-refactor cycle — failing tests traced to acceptance criteria first, mi...
How to find, watch and cut B-roll in a vlog - clips with no speech placed by time between talking clips, chosen by their...
Deferred end-of-run B-roll cache eviction. For ONLY the B-roll source video_ids this run ingested (from each broll_plan....
Hard-cut full-frame B-roll cutaways onto a 1080x1920 clip per broll_plan.json. During each [t0,t1] the entire frame is r...
Overlays silent b-roll cutaway clips onto a finished base video — the base audio keeps running underneath while the pict...
Claude picks CONTEXTUAL/scene-level anchors from a clip transcript (literal objects, establishing shots, evocative conce...
Generate detailed AI image prompts for YouTube video B-roll using Imagen. Creates premium, sophisticated visuals for tal...
Load this skill when investigating an incident or answering a question that needs logs from Bronto and the dataset that...
Load this skill when an investigation needs to explain errors in logs held in Bronto - an error surge, a failing service...
Load this skill before writing or running a Bronto log search - counting, grouping, trending or fetching log events with...
End-to-end Bronze layer creation for testing and demos. Creates table DDLs, generates fake data with Faker, copies from...
A cross-platform programmable network tool brook, go, android, cross-platform, decryption, encryption, ios. Use when you...
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebas...
Tech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refac...
Maintenance orchestrator for the brooks-lint plugin itself. Runs a sequential subagent pipeline — author → eval → QA → t...
Combined codebase health dashboard that scores a project across all four quality dimensions — PR quality, architecture,...
AI code reviewer grounded in classic software engineering books for catching design smells, coupling issues, and archite...
PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Con...
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test q...
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of...
CLI for broomva.tech — manage prompts, skills, and context from the terminal. Pull/push prompts, browse the skills roste...
Materialize and apply Broomva's platform-neutral calm blue-axis design system across digital products. Includes a portab...
Generate GPX bike routes via brouter.de. Use when the user wants a bike route as a GPX file between two places, optional...
Workflow for working with existing codebase
Use this skill for this scope: permitted Brownfield Review or preparation before non-trivial existing-system changes. Bo...
Analyzes existing brownfield projects to map documentation structure to SpecWeave's PRD/HLD/Spec/Runbook pattern. Scans...
Derive a complete AI Layer (CLAUDE.md + customized .claude/commands/) for a codebase that has no AI Layer yet. Dispatche...
Enforces architecture boundaries defined in PLAN.md. Use when a PR crosses module/service boundaries, when the dev asks...
Intelligently onboards brownfield projects by merging existing CLAUDE.md backups into SpecWeave structure. Use when inst...
Onboard an existing Spring codebase into the spec-driven workflow without blocking day one. Establish a `_baseline.json`...
Structure brownfield change work across requirements, planning, design, manufacturing, and testing while surfacing unres...
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors....
Use when interactive browser automation is needed for QA, reproduction, visual checks, authenticated flows, or file uplo...
Discover trending topics and content ideas from social feeds for post creation. Use when scanning Twitter timeline or fi...
· Browse/scrape web pages with Lightpanda, Playwright MCP, agent-browser, or fetch. Triggers: 'browse', 'scrape', 'headl...
Drive a real stealth browser from your shell — act on websites (order food, file an expense, pull data behind a login),...
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, d...
Visual feedback browser automation with multi-session, multi-tab, iframe support, and enterprise primitives. Navigate si...
Fast headless browser for QA testing and site dogfooding. (gstack)
Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fet...
Headless Chromium CLI for QA testing and site dogfooding. 100-200ms per command after startup. Persistent state with coo...
Playwright-powered browser automation and E2E testing for SolanaOS Hub. Covers test configuration, agent-driven test gen...
Drives a real browser with `agent-browser` to open, click, fill, or read a web page. Use when a page needs JavaScript or...
面向 QA 测试与真实站点试用的快速无头浏览器。可打开 URL、交互、校验页面状态、 对比前后差异、截图留证、检查响应式布局与表单上传。 (gstack)
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fie...
Use when a task needs a browser: click, type, record. Browse the web and act.
Browse Power Automate environments and flows interactively. Use when the user wants to browse, list, or explore their fl...