Skills covering Upstash Search quick starts, core concepts, and TypeScript/JavaScript SDK usage. Use when a user asks how to get started, how indexing works, or how to use the TS client.

Upstash's UI design system. Use when building interfaces inspired by Upstash's aesthetic - light mode, Inter font, 4px grid.

When the user wants to create, optimize, or validate URL slugs for content pages. Also use when the user mentions "URL slug," "URL path," "blog URL," "article URL," "short URL," "clean slug," "permalink," "slug optimization," "URL structure," "SEO-friendly URL," "create URL slug," or "SEO slug." For site-wide URL policy, use url-structure.

When the user wants to create, optimize, or audit use case pages. Also use when the user mentions "use cases," "use case page," "for [role]," "by persona," "by scenario," "by business goal," "ICP pages," or "audience-specific pages." For sitewide page planning, use website-structure.

Synthesize qualitative and quantitative user research into structured insights and opportunity areas. Use when analyzing interview notes, survey responses, support tickets, or behavioral data to identify themes, build personas, or prioritize opportunities.

This skill should be used when the user needs to locate a plugin's installation path, when ${CLAUDE_PLUGIN_ROOT} doesn't expand in markdown files, or when invoked via /utils:find-claude-plugin-root. Generates a CPR resolver script at /tmp/cpr.py.

Use this skill when building Python packages, configuring build backends, publishing to PyPI, or setting up pyproject.toml build systems. Activates on mentions of uv build, uv_build, build backend, Python packaging, sdist, wheel, pyproject.toml build-system, PEP 517, PEP 621, uv publish, package publishing, setuptools migration, hatchling, flit, build system, or Python distribution.

Multi-perspective UX review combining usability heuristics, WCAG accessibility checks, and interaction design analysis. Use when reviewing UI components before release, evaluating user flows for usability issues, conducting design critiques, or auditing accessibility compliance.

Use when writing, reviewing, or refactoring React or Next.js code, optimizing React performance, fixing re-render issues, reducing bundle size, eliminating waterfalls, or improving data fetching patterns

Use when claiming task completion or marking items as done. Covers completion evidence requirements, verification methods, and anti-rationalization patterns.

Use before claiming any task is complete, any feature works, or any bug is fixed - enforces fresh verification evidence through a 5-step HARD-GATE protocol that prevents false completion claims

Verify a competitive programming or LeetCode solution for correctness, edge cases, and performance. Use when asked to "verify my solution", "check my code", "is this solution correct", "test my solution", "review my competitive programming answer", "validate my algorithm", or any solution verification request.

Analyze local or downloaded social video files with the official Gemini API, especially for TikTok/Reels shot beats, timelines, voiceover or on-screen text capture, creative strategy, and natural Markdown outputs. Use this when you need video-level analysis beyond metadata, including uploading video files, prompting gemini-3.5-flash, and linking results back to source metadata.

Assemble final video from generated clips, audio, and assets using FFmpeg or Remotion. Handles concatenation, audio mixing, transitions, titles, and export. Use when combining multiple production outputs into a final deliverable.

Control video generation requests before execution. Use this when the user asks for a simple clip, storyboard video, UGC video, podcast clip, reference video, talking-head, image-to-video, text-to-video, or research-handoff video and the skill must classify the request before handing it to video-request-architect and a runner such as seedance-submitter or video-batch-runner.

Write video scripts. Use when: creating YouTube, TikTok, Reels, LinkedIn, demo, or explainer video content.

Generate keyword strings for images, screenshots, or visual references — optimized for fuzzy search, not alt text or prose. Use when the user says 'keywords for this image', 'tag this for search', 'visual keywords', or wants searchable labels on an Eagle asset.

Deploy and manage vLLM for high-throughput LLM inference. Configure continuous batching, tensor parallelism, quantization, and OpenAI-compatible API endpoints for production LLM serving.

Generate and manage persona-aware voice assets for short-form video production, including voice design, script-specific audio takes, and future reusable voice identities. Use this when persona registries and scripts already exist and you need local audio assets, voice manifests, and reviewable voice iterations without losing continuity across many videos.

Apply when designing or implementing asynchronous processing in VTEX IO services through events, workers, and background handlers. Covers event handler structure, idempotency, retry-safe processing, and moving expensive work out of request-response routes. Use for event-driven integrations, delayed processing, or background jobs in VTEX IO apps.

Language-specific vulnerability detection patterns for JavaScript/TypeScript, Python, Go, Java, Ruby, and PHP. Provides regex patterns and grep commands for common security vulnerabilities.

Vulture and deadcode tools for detecting unused Python code (functions, classes, variables, imports). Use when cleaning up codebases, removing unused code, or enforcing code hygiene in CI. Triggered by: vulture, deadcode, dead code detection, unused code, code cleanup, remove unused.

Multi-agent orchestration that analyzes tasks through specialized expert panels (security, performance, architecture, etc.), synthesizes prioritized actions, then plans and executes. Use when facing complex tasks requiring multiple perspectives, architectural decisions, new features needing security/performance/quality review, or user says "waldstorm", "expert review", "analyze this task".

Generate AI videos using Alibaba Wan 2.6 video models. Use when you need to: (1) create videos from text descriptions, (2) animate static images into videos, or (3) transform and enhance existing videos with AI style transfer.

Initialize warehouse schema discovery. Generates .astro/warehouse.md with all table metadata for instant lookups. Run once per project, refresh when schema changes. Use when user says "/astronomer-data:warehouse-init" or asks to set up data discovery.

Master modern web development. Learn HTML/CSS/JavaScript fundamentals, React/Vue/Angular frameworks, Node.js backend, databases, APIs, and full-stack architectures. Use when building web applications, learning web technologies, or choosing tech stacks.

Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.

Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.

Use free SearXNG web search APIs for agent-friendly, privacy-first, and high-volume search tasks.

Webflow's UI design system. Use when building interfaces inspired by Webflow's aesthetic - dark mode, Inter font, 4px grid.

Plan webinars and virtual events. Use when: designing promotion, content, registration, and post-event follow-up.

This skill enables the agent to create high-converting webinar scripts using the frameworks of Jason Fladlien and Jon Penberthy. It covers the entire process from introduction and content structure to offer presentation, objection handling, and closing sequences. Use this skill for webinar script creation, webinar strategy, and improving webinar performance.

Elicit Scope/Decisions/Context for a plan slice and generate its OpenSpec-formatted feature spec. Use after a slice is approved but before promote-slice, or any time a slice needs decisions captured. Wraps the cross-harness `wipnote plan elicit-decisions` CLI plus `wipnote spec generate --insert`.

Defines context handover format when workers hit turn limit. Posts structured handover to GitHub issue comments enabling replacement workers to continue seamlessly.

Defines behavior protocol for spawned worker agents. Injected into worker prompts. Covers startup, progress reporting, exit conditions, and handover preparation.

Track workouts, log sets, manage exercises and templates with workout-cli. Supports multi-user profiles. Use when helping users record gym sessions, view history, or analyze strength progression.

# Workspace Backup

Resolve and merge git worktrees after swarm completion

Use when completing work in a worktree. Handles PR creation or direct merge, worktree removal, and branch cleanup. Invoke with "/worktrees:finish" or when user mentions "finish worktree", "clean up worktree", "merge worktree", "done with worktree", or "complete worktree work".

Diagnose world-level story problems. This skill should be used when settings feel thin, institutions feel designed rather than evolved, economies don't make sense, or non-human species feel like humans in costume. Keywords: worldbuilding, setting, world, institutions, economy, culture, species, consequences.

Write correct transform blocks for Mission Control canary checks including fan-out, inline, and generated canary patterns. Use when adding transformations to canary checks, splitting a single check into multiple results, modifying check output, or generating child canaries from discovered resources.

Turn the prompt supplied with this skill into a concise, auditable Codex Goal or explain why a Goal is not the right fit. Use when the user asks to draft, formulate, rewrite, tighten, or create a `/goal` from a plain-language task, especially for multi-step work that needs a durable objective, evidence-based completion, constraints, iteration policy, and a default adversarial review loop.

Draft scientific research manuscripts from research data. Use when user wants to write a research paper, has a project folder with papers, data, figures, and a GitHub repository link. Orchestrates context-ingestion, scoping, literature-review, code-analyzer, results-interpreter, synthesis, and assembler sub-skills.

Use when writing or reviewing tests - covers test philosophy, condition-based waiting, mocking strategy, and test isolation

Guides creation of hookify rules in .claude/hookify.{name}.local.md files, including YAML frontmatter fields (name, enabled, event, pattern, action, conditions), event types (bash, file, stop, prompt, all), regex pattern writing, condition operators, and rule organization. Activates when the user asks to create a hookify rule, write a hook rule, configure hookify, or add pattern-based automation rules.

Use when writing any plan document — project plans, PRDs, proposals, implementation plans, or design docs. Applies as a writing style layer alongside other planning skills like superpowers:writing-plans.

Draft lean, executable, and verifiable plans before non-trivial work. Use when the user asks for a plan, implementation plan, roadmap, design plan, migration plan, refactor plan, PR split, plan checklist, or completion checklist for a plan; or when the task needs sequencing, tradeoffs, assumptions, unknowns, risk control, or completion criteria. Do not use for small, obvious tasks that can be completed directly.

Internal skill used by writing-setup at exit gate. Dispatches a reviewer subagent to verify PRECIS.md quality before outlining. NOT user-facing.

When a user wants to grow an X (Twitter) account from zero before a product launch, or asks how to get first followers, warm up the algorithm, hit ~500-1,000 followers, or prepare an account to make a launch video land. Also use when the user mentions "new X account", "warm up my Twitter", "first 1000 followers", "building in public strategy", "X growth", or "engagement before launch".

Read and post to X/Twitter via API. Check mentions, post tweets, search. Use app bearer tokens for read-only fetches and OAuth 1.0a user context for account actions.

When the user is planning, scripting, or editing a product launch video for X (Twitter) and needs the structure. Also use when the user mentions "launch video", "demo video", "product launch on X", "60 second demo", "how to structure a launch", or "my launch video isn't working". Produces a beat-by-beat timing sheet, not copy.

When the user wants to find proven-to-travel post templates in their niche and adapt them to their own product. Also use when the user mentions "what's going viral in my space", "what are competitors posting", "copy a viral post", "trending on X", "post ideas", "template mining", or "what to post this week". This is trend hunting, not plagiarism — the output is a template the user fills with their own assets.

Interactively explore a user's idea through structured questioning until all dimensions are covered. Produces a context summary and optionally detailed specifications. Use when the user has an idea they want to flesh out.

This skill should be used when the user asks to "get stock prices", "check stock quotes", "look up earnings", "get financial data", "find trending stocks", or needs stock market data from Yahoo Finance.

Get stock prices, quotes, fundamentals, earnings, options, dividends, and analyst ratings using Yahoo Finance. Uses yfinance library - no API key required.

Design yoga sequences — class structures, pose progressions, and balanced practices. Use when building a yoga class sequence or evaluating pose flow.

Audit ZIA SSL inspection rules to identify which applications, URL categories, users, or groups are subject to INSPECT, DO_NOT_INSPECT, or DO_NOT_DECRYPT actions. This skill focuses exclusively on SSL inspection rules and their configuration. Use when a security administrator asks: 'What SSL rules are in decryption mode?', 'What is bypassing SSL inspection?', 'Are there SSL bypass exceptions?', or 'Audit our SSL inspection policy.'

Investigate where a specific URL or URL category is referenced across all ZIA policy rules. Searches URL filtering rules, DLP web rules, SSL inspection rules, and cloud firewall rules to provide a comprehensive view of how a category is used. Use when an administrator asks: 'Where is this URL category used?', 'What rules apply to this URL?', or 'Show me the policy impact of this category.'

Guide for Zig and C interoperability. Use when importing C headers with @cImport, exporting Zig functions to C, mapping C types, using translate-c, or linking C libraries.

Analyze web traffic patterns using Zscaler Analytics (Z-Insights). Examines traffic distribution by location, protocol breakdown (HTTP vs HTTPS), threat categories, DLP violations, and volume trends over time. Use when an administrator asks: 'Show me web traffic by location', 'What protocols are in use?', 'Are there any DLP violations?', 'What does our traffic look like?', or 'Show traffic trends.'

Go up a layer of abstraction and map the surrounding architecture. Use when the user is unfamiliar with an area of code, asks "how does this fit in", "what calls this", "give me the big picture", "where am I", "map this out", "I'm lost", "explain this area", or needs to understand how a file, module, or function connects to the rest of the system. Also use when the user says /zoom-out or "zoom out" mid-conversation — even without a specific file reference, orient them based on whatever code is currently in context.

Create a ZPA server group with all required dependencies. Server groups require app connector groups to exist first. This skill walks through the dependency chain: (1) Check for existing app connector groups, (2) Create an app connector group if none exist, (3) Create the server group referencing the connector group IDs, (4) Verify the server group was created correctly. Use when an administrator needs to set up a new server group for application access.

Zustand 5 state management patterns for React: stores, persistence, selectors, slices. Trigger: When managing global state in React, using Zustand, or implementing state slices.

# Product Manager Agent

# QA Test Specifications Agent

401/403 bypass playbook. Use when encountering access-denied responses on admin panels, API endpoints, or restricted paths. Covers path manipulation, HTTP method tampering, header injection, protocol downgrade, and automated bypass tools.

Set up the 42Crunch environment so that audit and scan skills can run without friction. Use this skill whenever the user wants to configure 42Crunch for the first time, install or update the 42c-ast binary, configure an API key, or troubleshoot missing credentials or binary errors. Triggers on phrases like "setup 42crunch", "configure 42crunch", "install 42c-ast", "update 42c-ast", "set api key", "42crunch not working", "binary not found", or any request to prepare the environment before running an audit or scan.

Challenges requirements, removes unnecessary work, and simplifies design before writing code. Activates when asked to build, implement, automate, add a feature, create a service, migrate, or replace a process. Does not activate for general code writing, bug fixes, or simple edits.

Analyze the gap between current state and specification to identify all required changes. Use when: (1) After SPEC phase in 5D-SDD workflow, (2) Spec exists and implementation is about to begin, (3) User asks 'what needs to change' or 'what's the delta,' (4) Assessing scope of work. This phase prevents surprise discoveries during implementation.

Pre-development orientation and assumption mapping for spec-driven development. Use when: (1) Starting a new feature or project, (2) User says 'let's build X' without prior analysis, (3) Beginning any 5D-SDD workflow, (4) User wants to 'think through' an idea before planning. This phase prevents wasted effort by surfacing hidden assumptions and identifying all relevant domains before committing to a direction.

Convert expanded thinking into a concrete, multi-perspective plan. Use when: (1) After SPAR phase in 5D-SDD workflow, (2) User is ready to define what will be built, (3) User asks to 'write up the plan' or 'document what we're building,' (4) Transitioning from exploration to commitment. This phase creates the authoritative description of intent before technical specification.

Stress-test the plan through adversarial review and edge case analysis. Use when: (1) After PLAN phase in 5D-SDD workflow, (2) User wants to 'validate,' 'review,' or 'check' a plan, (3) Before committing significant resources to implementation, (4) Plan exists but hasn't been challenged. This phase catches plan-level errors before they become code-level errors.

Structured sparring to challenge and expand thinking before planning. Use when: (1) User has an idea but hasn't stress-tested it, (2) After ORIENT phase in 5D-SDD workflow, (3) User asks to 'think through,' 'challenge,' or 'poke holes' in an idea, (4) User seems certain too early—needs perspective expansion. This phase prevents building the wrong thing by forcing multi-perspective examination.

Multi-layer verification of implementation against spec and intent. Use when: (1) After BUILD phase in 5D-SDD workflow, (2) Implementation is complete and needs validation, (3) User asks to 'test,' 'verify,' or 'check' the implementation, (4) Before considering a feature done. This phase catches errors at multiple levels and routes fixes appropriately.

MANDATORY verification system that prevents Claude Code instances from making false claims or fabricating evidence. Enforces cryptographic verification, real testing evidence, and automatic claim validation before any success statements can be made.

This skill should be used when the user asks "what is agent-runtime", "why use agent-runtime", "what does this repo do", "agent runtime architecture", "how does agent-runtime work", or needs to understand the purpose, value proposition, and high-level architecture of the @hhopkins/agent-runtime monorepo.

Screen job applications against requirements and score candidates

This skill should be used when the user asks to "sign a message", "sign typed data", "sign a transaction", "submit a transaction", "submit raw transaction", "personal_sign", "EIP-712", "eth_signTypedData", "eth_signTransaction", or any direct signing or transaction submission operation. Covers the synchronous /agent/sign and /agent/submit endpoints.

This skill should be used when the user asks "what can the SDK do", "what prompts does Bankr support", "SDK features", "supported operations", "what can I build with Bankr", "Bankr SDK capabilities", "what chains are supported", "what tokens can I trade", "SDK supported commands", or wants to understand the full range of operations available through the Bankr SDK.

This skill should be used when the user asks about "job status", "check if request completed", "cancel request", "why is my request taking so long", "poll for result", "batch requests", "retry failed request", "request timeout", "async operations", "job lifecycle", "manual polling", or needs advanced control over SDK async operations, manual job polling, batch processing, retry logic, or job cancellation.

This skill should be used when the user asks to "swap tokens", "exchange ETH for USDC", "buy DEGEN", "sell tokens", "swap on Base", "trade crypto", "convert ETH to WETH", "exchange tokens", "token swap code", "0x routing", or any token swap operation. Also use for questions about ERC20 approvals, allowanceTarget, swap transaction execution, or building swap transactions with the Bankr SDK.

This skill should be used when the user asks to "send tokens", "transfer ETH", "send USDC to", "transfer NFT", "wrap ETH", "unwrap WETH", "bridge tokens", "mint NFT", "buy NFT", "approve token", "build transaction", "DeFi transaction", or needs to build transactions for transfers, approvals, NFT operations, cross-chain bridges, ETH/WETH conversions, or DeFi interactions beyond simple swaps using the Bankr SDK.

Create and maintain brand style guides for consistent visual identity

Generate release notes from git commits, updates, or feature lists

Receive and act on code review feedback with technical rigor, not performative agreement or blind implementation

Establish workflow boundary checklists with clear pass/fail criteria and escalation procedures

Use this skill when working with TypeScript/JavaScript files (.ts, .tsx, .js, .jsx, .mts, .cts, .mjs, .cjs) in Deno projects, or when the user asks about Deno-specific patterns, imports, configuration, testing, or tooling.

Automatically categorize emails by type, priority, and required action

This skill should be used when the user asks about "FastAPI", "FastAPI routes", "FastAPI dependencies", "Pydantic models", "FastAPI middleware", "API endpoints", "OpenAPI", or mentions FastAPI development.

Organize and rename files based on content analysis

Automate invoice generation, sending, tracking, and payment reconciliation across accounting platforms

Score and qualify leads based on criteria and fit

Research company and contact information for sales outreach

Create formal employment offer letters with compensation and terms

Set up or reorganize project documentation using intent-based structure (BUILD/FIX/UNDERSTAND/LOOKUP)

Convert PDF files to and from Word, Excel, Image, and other formats