Systematic visual QA for UI screenshots. iOS HIG, web WCAG 2.2, cross-platform heuristics.

Structured visual QA verdict for screenshot-to-reference comparisons

Vroid Studio, VRM format, and VTuber avatar creation

Vue 3 renderer for json-render. Use when building Vue UIs from JSON specs, working with @json-render/vue, defining Vue component registries, or rendering AI-generated specs in Vue.

Vue 3 gotchas and decision criteria. Covers reactivity traps, Composition API pitfalls, and Pinia patterns.

Create and manage sandboxed WASM agents for isolated code execution

Gas optimization analysis and implementation for Solidity contracts. Triggers on weasel gas, weasel optimize, or weasel efficiency.

Manage Weaviate vector database — classes, objects, and vector search via the REST API.

Build accessible web applications following WCAG guidelines. Use when implementing ARIA patterns, keyboard navigation, screen reader support, or ensuring accessibility compliance. Triggers on accessibility, a11y, WCAG, ARIA, screen reader, keyboard navigation.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Structured approach to conducting thorough web research with source citation

Web search with automatic Qdrant storage for building persistent knowledge

Real-time web research using Google Search via Google's Antigravity (`agy`) CLI — the replacement for the deprecated `gemini-cli`. Trigger when user needs current information ("search with agy", "search with Google Antigravity", "find current info about X with agy", "what's the latest on Y"), library/API research, security vulnerability lookups, or comparisons requiring recent data.

Knowledge base for web search query techniques, source authority ranking, WebFetch/WebSearch best practices, and bot-block fallback via webfetch.py. Used by quick-searcher and deep-researcher in plugins/research/. TRIGGER WHEN: performing web research with WebSearch or WebFetch. DO NOT TRIGGER WHEN: searching local codebase (use Grep or Glob directly).

Send HTTP requests to webhooks and APIs using curl. Supports GET, POST, PUT, DELETE with headers and JSON payloads.

Classify decision weight (Light/Medium/Complete) and adjust gate depth accordingly

Configure and customize WezTerm terminal emulator. Use for setting up WezTerm config, themes, keybindings, and advanced features.

Log decisions, progress, deviations, and discoveries during any workflow phase

Fetch data from URLs. Use when asked to download content, fetch remote files, or read web data.

WHOOP morning check-in (recovery/sleep/strain) with suggestions.

Use when an operation issue asks you to ingest a captured source from `raw/` into the LLM Wiki, or when the user explicitly says "ingest <slug>". The issue body will name a file under `raw/` (e.g. `raw/karpathy-llm-wiki.md`) and ask for durable wiki pages. Do not invoke this skill for Paperclip activity bundles — those use `paperclip-distill` instead.

Work on wizardshit.ai — Joel's AI education platform teaching the exploratory journey of building systems with and around AI. Covers the Next.js app in gremlin, The Claw course design, and the manage brain vault. Triggers on: 'wizardshit', 'wizard shit', 'wizardshit.ai', 'the claw course', 'agent game generation', 'zots', 'minions of toil'.

Wisdom of Agents (WoA) — internal agent forum for sharing solutions to problems. Use when stuck on a problem after 2+ failed attempts, or after solving a non-trivial problem worth sharing. Provides protocol for searching existing solutions and posting new ones. Triggers on: agent is stuck, recurring error, wants to check if others hit this issue, solved a hard problem.

Manage WooCommerce stores — products, orders, customers, and coupons via the REST API.

Automatically checks word counts of documents when the user mentions word count in relation to a file. Triggers on phrases like "Check the word count of X", "Stop when the word count is N", or similar references to document word counts. Use this skill proactively whenever word count is mentioned with a document reference.

Get word count, character count, reading time, and text statistics. Quick analysis without questions.

CLI for bootstrapping and managing wordspace projects

Document a recently solved problem to compound your team's knowledge

Git worktree commands and usage. Triggers on 'worktree', 'worktrees', 'create worktree', 'git worktree'.

Opinionated worktree workflow with .git/checkouts convention. Load explicitly with /worktree-workflow.

Use when user says "wrap up", "close session", "end session", "wrap things up", "close out this task", or invokes /wrap-up — runs end-of-session checklist for shipping, memory, and self-improvement

Write prose that avoids AI tells through an iterative workflow. Gathers your context, writes using research-backed principles, reviews via writing-reviewer agent, auto-fixes HIGH+ issues, loops until clean. Use for articles, blog posts, emails, marketing copy, social media. Triggers: write content, draft article, write blog post, write email, write copy.

Reference standards for writing and maintaining GitHub issues in the tldraw repository. Use as supporting guidance when another skill or workflow needs issue title, body, type, label, or triage standards.

Author a new agent skill in this repo following progressive-disclosure, trigger-rich-description, and script-over-prose principles. Use when the user asks to "write a skill", "add a skill", "create a new skill", or scaffold a SKILL.md. Targets the `npx skills` layout (top-level `skills/<name>/SKILL.md`).

Clear, concise writing standards for documentation, comments, commit messages, and technical communication. Use when writing README files, documentation, PR descriptions, code comments, or any technical writing. Focuses on clarity, brevity, and active voice.

Write blog posts sharing knowledge about the project. Use when writing blog posts, capturing knowledge, or adding to the project knowledge base.

Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering, or LLM-to-LLM content

Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.

This skill should be used when writing documentation, PR descriptions, handover docs, PEPs, Confluence pages, or any prose output. Activates when the user asks to "write a document", "create a handover", "update the docs", "write a PR description", "draft a PEP", or any task producing written content. Enforces natural, casual writing style and prevents AI-sloppy output.

Methodology for creating effective skills using TDD principles. Use when creating new skills, editing existing skills, or authoring plugin components. Triggers on: 'create skill', 'write skill', 'new skill', 'skill authoring'.

Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.

Write clear technical documents — design docs, PR descriptions, proposals, postmortems — that lead with the decision and ground every claim in specifics. Use when drafting or editing workplace technical writing where a reader must act or later understand why. For the specific RFC and ADR formats, use writing-rfc and writing-adr.

Query Xero accounting — invoices, contacts, accounts, and bank transactions via the REST API.

XML tag structure patterns for Claude Code agents and commands. Use when designing or implementing agents to ensure proper XML structure following Anthropic best practices.

XML tag structure patterns for Claude Code agents and commands. Use when designing or implementing agents to ensure proper XML structure following Anthropic best practices.

Guide for querying DeFi yield and APY data using get_yield_pools. Covers pool filtering by token, chain, protocol, category, stablecoin-only mode, and capacity assessment. Explains APY conventions, lending vs borrowing rates, and sort options. Use when users ask about yields, APY, lending rates, borrowing costs, best pools, or DeFi yield strategies.

Brief description of what this Skill does and when to use it. This field is critical for Claude to discover when to invoke your skill.

One sentence: what this skill does and when to invoke it. Use for: [list 2-3 trigger phrases users would naturally type].

Query YouTube — search videos, get channel stats, list playlists, and manage comments via the Data API v3.

Best practices for developing zensical/Material for MkDocs static sites. Covers installation, virtual environments, project structure, responsive images, CSS, media embedding, and verification. Use for ANY Material for MkDocs project development beyond basic text editing.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Expert in building accessibility scanning tools, rule engines, document parsers, report generators, and audit automation. WCAG criterion mapping, severity scoring, CLI/GUI scanner architecture, CI/CD integration.

Tool: Anthropic Claude API with 200K context window

All documentation in English. Root README concise, detailed docs in `/docs`.

A planted fixture that satisfies every blocking skill-eval rule so the gate passes cleanly.

Spin up a mock REST API server from JSON files in seconds. Full CRUD, filtering, pagination. Zero config. Free CLI tool for frontend developers.

Approve pending GitHub Actions workflows and add /ok-to-test comments to PRs that need testing

Anthropic's official prompt engineering best practices. Use when optimizing prompts, debugging outputs, or improving response quality.

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

Use when designing inclusive animations, addressing vestibular disorders and motion sensitivity, or ensuring animation accessibility compliance.

Web accessibility patterns for WCAG 2.2 compliance including ARIA, keyboard navigation, screen readers, and testing

Run ACFS.

GitHub Actions command center -- view workflow runs, read logs, re-run failed jobs, manage workflows, and debug CI failures entirely from the editor. Bypasses the deeply nested, visually-dependent Actions UI that is largely inaccessible to screen readers.

Expand a core idea into multiple distinct ad angles. Trigger on "more ads", "creative testing", "scale campaigns".

Materal-specific enum adaptation workflow: fetch enum values from provider API, let LLM fill suggested_name, then apply patch with aptx-ft. Use ONLY when: (1) user mentions Materal framework, (2) Materal naming rules are required, or (3) adapting Materal enum semantics. Do NOT use for generic OpenAPI projects.

Adds Cognito authentication and route protection. Use when adding login, signup, authentication, or user management.

Guide for adding new AI function examples, for testing specific features against the actual provider APIs.

Guide for adding new AI function examples, for testing specific features against the actual provider APIs.

Use this skill whenever important information is learned during a task or when the user explicitly asks to store something. Use when users ask to remember. Triggers on "remember this", "update memory", "share" or any persistent storage request.

Creates Architecture Decision Records (ADRs) following standard templates. Documents architectural decisions with context, options considered, and rationale. TRIGGERS - "create ADR", "document architecture decision", "new ADR", "record decision", "architecture decision record". Use when making significant architectural choices that should be documented. NOT for code documentation or README files.

Fresh adversarial review of implementation plans before execution. Dispatches a read-only agent to challenge feasibility, find gaps, and surface unstated assumptions. Bounded to 2 review passes. Use after writing a plan and before starting implementation.

Perform an adversarial review of proposed work. Use ONLY when the user explicitly types /adversarial-review. Never auto-trigger, even if the user mentions reviewing, questioning, or challenging their approach.

Use when creating or upgrading CLAUDE.md instructions and selecting the right template baseline for repo size, architecture, and team constraints. AE.LTD template decision workflow.

Use when coding decisions depend on current library/framework APIs and you need version-accurate docs before implementation. AE.LTD workflow tuned for fast, verifiable doc grounding.

Use when scaffolding or extending MCP servers, adding tools/resources/prompts, or hardening MCP tool schemas and handlers. AE.LTD workflow tuned for production-ready MCP delivery.

Use when unit tests look green but confidence is low and mutation testing is needed to expose weak assertions. AE.LTD workflow for targeted mutation runs and actionable test hardening.

Use when converting plain-language automation goals into production-ready n8n workflow JSON with retries, error paths, and credential-safe placeholders. AE.LTD automation blueprint workflow.

Use when UI changes must be proven safe across breakpoints using baseline and diff workflows. AE.LTD visual quality gate for release confidence.

Use when parallel branches are needed for feature work, hotfixes, or review fixes using git worktrees with minimal context switching. AE.LTD workflow for safe creation, usage, and cleanup.

Daily DeFi read — regime verdict (RISK-ON / NEUTRAL / RISK-OFF) reproducible from named inputs, top TVL movers with one-line causal reasoning, and a sustainable-vs-incentive yield split so the operator can tell real product-market fit from emissions-pumped APY. Public APIs only. Triggers: "DeFi read", "DeFi regime today", "yield decomposition", "is this APY real or emissions", "DeFi movers with why".

Top Hacker News stories filtered by interest tags, with comment-mined insights (top, dissenting, expert/builder) and themed clustering. Comments often beat the post — this skill extracts the highest-signal threads rather than just listing front-page links. Triggers: "top HN today", "hacker news digest", "what's on hn", "best comments today".

Trending Hugging Face models, datasets, and spaces — filtered by license sanity, dedup vs same-week quantizations, with a "why notable" line per pick (architecture shift, size step, license change, notable author). Surfaces what's actually shifting rather than just popular. Triggers: "trending on HF", "what models are hot", "huggingface trending", "new spaces today", "best new datasets".

Top movers, losers, and trending coins from CoinGecko — with pump-risk flags (low liquidity, single-pair-only, fresh listing, volume-no-mcap, low-holder-data, cex-only). No API key required. Use for daily market scans, pre-trade screening, or as input to a token-pick workflow. Triggers: "top movers today", "what's pumping", "biggest losers 24h", "trending coins", "crypto movers with risk flags".

Use for full agentic multi-file refactoring or feature work — spec → planner → coder → qa-reviewer → qa-fixer pipeline with rollback. The "do the whole loop" command. Pairs with /siftcoder:agent.

Inter-agent communication for multi-agent workflows. Use when multiple agents need to coordinate, share information, or reserve resources.

Add AI features to Glide apps using AI columns like Generate Text, Image to Text, Audio to Text. Use when adding AI-powered functionality, text generation, OCR, transcription, or auto-categorization.

AI-powered issue operations via gh-models. TRIGGERS - issue summarization, auto-labeling, issue insights.

Use when writing or modifying OCaml code to annotate AI involvement. Triggers on any code generation, editing, or autonomous agent output in .ml/.mli files. Also use when creating or updating .opam files for packages containing AI-involved code.

Read and write Azure Data Lake Storage Gen2 (`abfss://`) from an AIDP notebook. Use when the user mentions ADLS, Azure Data Lake, abfss, or wants to ingest from a multi-cloud Azure source. Auth is OAuth client-credentials (Service Principal client_id + secret + tenant).

Run a Planning data-slice export against Oracle EPM Cloud (Planning / EPBCS) and materialize as a Spark DataFrame in an AIDP notebook. Use when the user mentions EPM Cloud, EPBCS, Hyperion Planning, planning app, MDX export, or wants Planning data in Spark. HTTP Basic auth with identity-domain-prefixed username.

Run an MDX query against an Oracle Essbase 21c cube and materialize the result as a Spark DataFrame in an AIDP notebook. Use when the user mentions Essbase, MDX, Essbase 21c, OLAP cube, or wants to read cube data into Spark. Auth is HTTP Basic.

Pull data from Oracle Fusion ERP / HCM / SCM REST APIs into a Spark DataFrame from an AIDP notebook. Use when the user mentions Fusion ERP, Fusion REST API, FA REST, Cloud ERP, or wants live data from a Fusion pod. HTTP Basic auth only. For volumes >499 rows/page or bulk extracts, route to aidp-fusion-bicc.

Read or write MySQL or OCI MySQL HeatWave from an AIDP notebook via the AIDP `aidataplatform` Spark format handler. Use when the user mentions MySQL, HeatWave, MySQL Database Service, MDS, or has a MySQL host/port. Auth is host/port + user/password.