Skills
100,696 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Audit a live page for accessibility issues and locate each violation precisely — pass a URL, a config target name (e.g. `accesslint:scan dev`), or nothing to use the default target from accesslint.config.json. Ensures a debuggable Chrome, runs the @accesslint/core engine via CDP, and returns a worklist of live-DOM WCAG violations grounded to each violation's DOM selector and source file:line. Locates; doesn't edit — output drives fixes by Claude. Use it for “is this page accessible,” or to verify a UI change. For diffing against uncommitted changes or a branch, use the `diff` skill.
Use when sculpting a realistic head, face, portrait, body or creature in ZBrush (anatomy, landmarks, proportions, "the face looks off", eyes, lips, jaw), adding skin, pores, wrinkles or reptile and dragon scales with alphas, Surface Noise, layers or morph targets, planning subdivision or HD Geometry for a film close-up, reprojecting detail, sculpting cloth folds or running Dynamics cloth, growing FiberMesh fur or hair, making horns, or judging a character sculpt the way a senior character artist would.
Use when an agent sculpts organic forms in ZBrush 2026 (sculpt a head, bust or creature in ZBrush from a sphere, ZSpheres or primitives); when blocking primary and secondary forms, choosing DynaMesh, Sculptris Pro or subdivision levels, or setting ClayBuildup, Dam_Standard, Move or TrimDynamic; when using masks, polygroups, Morph Targets or layers; or when scripted strokes miss, do nothing, come out too strong or leave marks, or a re-DynaMesh does nothing or loses polygroups.
SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length, use clean-code instead
Analyze tender and procurement documents (PDF, Word, images) to extract qualification requirements, scoring criteria, key deadlines, prohibited clauses, and submission checklists. Uses SoMark for accurate parsing of complex government and enterprise procurement documents. Requires SoMark API Key (SOMARK_API_KEY).
Connect design decisions to business outcomes through competitive analysis, opportunity mapping, Jobs to Be Done, outcome-driven discovery, value proposition design, and UX metrics. Shape product direction with strategic frameworks grounded in evidence.
Develop independent competing solutions to a defined brief, compare them, and synthesize a winning approach. Use when choosing well requires developing alternatives beyond their current form. Use ce-pov to judge developed material and ce-ideate to discover opportunities.
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful directions) and Experimentation Memory M_E (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after research-ideation), IVE (after experiment failure — classifies failures as implementation vs fundamental), ESE (after experiment success — extracts reusable strategies). Use when: updating memory after completing research-ideation cycles or experiment pipelines, classifying why a method failed (implementation vs fundamental failure), starting a new research cycle needing prior knowledge, user mentions 'update memory', 'classify failure', 'what worked before', 'research history', 'evolution'. Do NOT use for running experiments (use experiment-pipeline), debugging experiment code (use experiment-craft), or generating ideas (use research-ideation)
Automatically generate Excel reports from data sources including CSV, databases, or Python data structures. Supports data analysis reports, business reports, data export, and template-based report generation using pandas and openpyxl. Activate when users mention Excel, spreadsheet, report generation, data export, or business reporting.
Build consistent Frappe-style user interfaces using the frappe-ui Vue 3 component library and its design tokens. Use when scaffolding pages, forms, dialogs, lists, or any UI inside a Frappe-based app, when the user mentions frappe-ui, Frappe Cloud / Gameplan / Desk / Drive / Insights styling, or asks to "use frappe-ui components"
When the user wants to audit a Google Ads account, take over a new account, assess overall account health, do a first-30-days review, identify the highest-impact problems in an account, or build a prioritized optimization roadmap. Triggers on 'account audit', 'audit my Google Ads', 'taking over an account', 'account health check', 'what should I fix first', 'account review', 'new account onboarding', 'account score', 'where to start optimizing', or 'Google Ads diagnostic'. For specific area audits see individual skills (google-ads-quality-score, google-ads-negative-keywords, etc.).
Expert in building portfolios that actually land jobs and clients—not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities. Use when: portfolio, personal website, showcase work, developer portfolio, designer portfolio.
Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic, with formulas and derivations, from-scratch PyTorch code, comparison tables, and 25 frequently asked interview questions (L1 essential / L2 advanced / L3 top labs). Use when the user asks for an interview cheat sheet, an X tutorial, help preparing for Y interview questions, an X quick reference, or a 600–1,000-line Chinese tutorial on a specific ML topic.
Turn a novel into a five-part short drama outline package: an adaptation brief, character list, highlight moments list, episode-by-episode summaries, and an asset inventory. Produce outline.json + Markdown + a one-page review report (KPI band, key decisions, highlight timeline, scheduling matrix, scene overview, quality gates). All 14 quality gates are checked deterministically by scripts (character tier limits, main-scene limits that vary dynamically with episode count, no more than 3 episodes between highlight moments, required suspense hooks for every episode, etc.); they don’t rely on the model to remember. Supports a checkup mode: provide an existing outline to run only the quality gates and get a diagnosis. Zero dependencies, no API key; uses the current session quota. Use when asked for an adaptation outline, short drama outline, outline breakdown, novel-to-short-drama adaptation, or adaptation outline.
Create storyboards for AI short dramas: a three-level structure—segment (one video generation, ≤15 seconds) → shot (2–5-second cuts within a segment, each assigned a screenplay beat) → storyboard frame (one keyframe per cut: the main frame is pinned at 0.00 seconds, and child frames are pinned at their respective cut points). Each segment comes with a MiniMax H3 video prompt (official guidance defaults to English, one line per shot; promptLang can switch to Chinese): alignment instructions and [Shot k] cut timestamps are derived from the storyboard structure and checked character by character; dialogue is included verbatim in <d> blocks (conventions are embedded in references/h3-prompt.md, with no external skill dependency). Outputs storyboard.json + Markdown + a single-page review report (shot pacing track / episode shot list / generation batch sheet / voiceover alignment sheet, including JSON export). Does not generate images—the deliverables are each frame’s visual prompt and the reference images it should link to. All 18 quality gates are checked deterministically by scripts (gate 18, shot-recipe, is optional: it is checked only if the shot-recipes card library is attached; otherwise the skip is stated explicitly); one-click export creates an H3 production package (prompts per segment + storyboard image list ordered by Picture). Zero dependencies, zero API keys; uses the current session quota. Use when asked to create a storyboard, shot list, or cuts for an AI short drama
This skill should be used when the user asks about "observability" or "monitoring", what "metrics, logs, and traces" to collect, "health checks" (liveness/readiness), "alerting" or "on-call", "SLO/SLI" or "error budgets", the "RED" or "USE" method, "dashboards", or names a tool like "Prometheus", "Grafana", or "Datadog". Use it whenever a design has no answer to "how would we know this is broken?" or "what do we alert on?" — i.e. any time failure would be invisible until users complain, even if the user doesn't say "observability".
Review and improve tldraw SDK documentation against the voice and docs guides, scoring each article and iterating until it passes. Use when asked to review docs, audit an article in apps/docs/content, check whether documentation follows the style guide, or improve existing documentation.
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted stroke does not sculpt or a dialog blocks a script, or when a ZBrush result has to be judged the way a professional artist would.
Use when sculpting a stylized or cartoon character, bust, collectible or toy in ZBrush (Overwatch, Fortnite, Disney look), judging shape language (S and C curves, parallel lines, 70/30, silhouette read at a distance), exaggerating proportions on purpose, keeping stylized planes crisp through subdivision, sculpting stylized hair (chunky clumps, curve tube strands, ClayPolish), or designing a figure for toy production (articulation, wall thickness, scale).
When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/ (AI-compiled interlinked topic pages), outputs/ (generated artifacts). Vault defaults to ${SECOND_BRAIN_VAULT:-$HOME/Documents/SecondBrain}/. Six modes — capture (drop something into raw/), compile (process unprocessed raw files into wiki pages, update INDEX.md), query (answer a question from the wiki, save to outputs/), lint (orphans / contradictions / stale / unprocessed raw / topic gaps), connect (suggest new wikilinks between pages), search (quick lookup). Triggers on "/second-brain," "/sb," "capture this," "save this to my brain," "compile the wiki," "process raw notes," "query my wiki," "ask my brain," "lint the wiki," "find connections," "search my notes." Complements deep-research (external corpus) — this is the internal corpus. Team knowledge goes to company-brain, not here.
Translate technical security work into language for non-security audiences—boards, executives, engineering, customer success, customers, legal, procurement, and sales. Covers incident communication, post-mortem narratives, audit findings for stakeholders, risk justification, security-spend justification, and customer-facing breach disclosures. Use when the user mentions 'security comms,' 'communicate this finding,' 'explain to my boss,' 'board update,' 'executive summary,' 'incident communication,' 'breach notification letter,' 'customer disclosure,' 'security memo,' 'post-mortem narrative,' 'why this matters to the business,' 'translate this finding,' 'stakeholder update,' or has technical security work that needs to reach a non-security audience.
Guide the user through connecting a new data warehouse source, including databases, SaaS tools, and bucket files. Use when the user wants to "connect Stripe", "import data from Postgres", "import files from a bucket", "upload a file", "add a new data source", or pick sync methods for each table. This skill covers source-type discovery, credential validation, table discovery, per-table sync_type selection, and the final create call. Also covers picking a good prefix, what to do right after creation, and sending a source's tables to the user's own warehouse (Snowflake, BigQuery, Postgres, S3 and other destinations).
OpenClaw Token Optimizer v3.2.0 — practical cost-control toolkit for OpenClaw agents. Lazy context loading, Sonnet/Opus-aware routing, heartbeat scheduling, local token budgets, cache-TTL guidance, and security-audit-safe command behavior for current OpenClaw 2026.6.x installs.
Discover novel small-molecule binders for protein targets using structure-based and ligand-based screening. Covers druggability assessment, known-ligand mining (ChEMBL, BindingDB), similarity expansion, ADMET filtering, and synthesis feasibility. Use for hit identification, virtual screening, target-to-compounds workflows, and lead-finding before commit-to-medchem
An end-to-end content creation tool for WeChat Official Accounts, supporting Markdown theme formatting, Dan Koe-style writing, AI trace removal, image uploads, article drafts, and Xiaolvshu publishing. Use this skill when the user asks about WeChat Official Account publishing, converting Markdown to WeChat HTML, uploading images to WeChat, creating drafts, writing in Dan Koe style, or removing AI writing traces (humanizing). Also trigger it when the user mentions WeChat formatting, Official Account publishing, Official Account formatting, formatting an article for WeChat, WeChat articles and images, Xiaolvshu, or any WeChat content workflow—even if they don't explicitly say “wechat-studio”.
Create and manipulate Excel XLSX files programmatically. Use when the user needs to generate spreadsheets, modify XLSX templates, extract spreadsheet content, or automate Excel workflows. Supports both template-based generation (for branding compliance) and from-scratch creation. Keywords: Excel, XLSX, spreadsheet, workbook, worksheet, data, report, template, financial, analysis.
Apidog import/export and quality gates: import OpenAPI, Postman, Swagger, and Apidog native formats; export OpenAPI, HTML, Markdown, Postman, and Apidog native formats; validate spec completeness, tag grouping, schema/body coverage, counts, modules, and resource visibility.
Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document UI changes. Accepts two URLs (file://, http://, https://) or two image paths.
Runs Cantera homogeneous chemical reactors and evaluates ignition delay with mechanism provenance, conservation checks, and numerical refinement. Use for combustion kinetics, closed adiabatic ideal-gas constant-volume or constant-pressure ignition, temperature histories, or mechanism-specific ignition-delay comparisons.
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf. Team-scope sibling to second-brain — personal notes go there, not here. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/), review (verify / deprecate / supersede stale captures), lint, connect, search. Structured raw dirs (people/, companies/, meetings/, sops/, decisions/, customer-language/, sales-objections/). Every capture stamps author, timestamp, and trust status. Optional sync from call transcripts, Slack/email exports, CRM. Vault at ${COMPANY_BRAIN_VAULT:-$HOME/Documents/CompanyBrain}/. Triggers on "/company-brain," "/cb," "capture this into the team brain," "log this meeting," "save this SOP," "compile the company wiki," "query the team brain," "what does the team know about X," "review the company brain," "lint the company brain," "who's the internal expert on X."
Review Java concurrency code for thread safety, race conditions, deadlocks, and modern patterns (Virtual Threads, CompletableFuture, @Async). Use when user asks “check thread safety”, “concurrency review”, “async code review”, or when reviewing multi-threaded code.
Compare two versions of an AEM Edge Delivery Services page to identify what changed. Fetches preview vs live, or two different URLs, and produces a detailed content diff showing added, removed, and modified content, metadata, and blocks. Use when reviewing changes before publishing, auditing content modifications, or tracking content evolution.
Rewrite AEM Edge Delivery Services page content for AI search discoverability (GEO — Generative Engine Optimization). Analyzes content structure, semantic clarity, and factual density, then produces optimized rewrites that rank in both traditional search and AI-powered search engines. Use when optimizing pages for search visibility, AI discoverability, or content clarity.
Scans and removes sensitive data (secrets, API keys, private domains/IPs, PII) from GitHub repository history, then verifies and force-pushes safely. Use for 清理敏感数据 / 历史重写 / 泄露, "scan sensitive data", "clean git history", "remove secrets from repo", or before any force push to a public repo. Not for local-only Git recovery (use git-safety-net) or ordinary repository setup (use auto-repo-setup).
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.