Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Write or fix ad copy using the classic copywriting formulas (PAS, AIDA, Before-After-Bridge, 4Ps, SCQA, Star-Story-Solution and friends), choosing the right formula for the placement. Use to draft primary text or to diagnose copy that reads fine but does not convert.
Side-route skill for explicit backtracking when an upstream artifact becomes untrustworthy. Use when research, PRD, or slice decomposition has been invalidated by new information and you need to clean up stale artifacts before re-running an earlier pipeline step. Not for forward progress, fresh shaping, or routine bug fixes.
Create, list, inspect, and delete Bolna knowledge bases from PDF files or URLs, including multilingual retrieval settings, chunking, overlap, similarity top k, processing status, rag_id and vector_id usage. Use when a voice agent needs RAG over FAQs, policies, product docs, or web pages.
Creating high-quality agent skills following Claude's official best practices. Use when designing, implementing, or improving agent skills, including naming conventions, progressive disclosure patterns, description writing, and appropriate freedom levels. Helps ensure skills are concise, well-structured, and optimized for context efficiency.
When every option on the table is a variation of one route or waits on the same sign-in, approval, person or dependency, list the options that frame already gives, then map working mechanisms from five or more distant domains onto the problem and report the ones the first list lacked, each with where it breaks. Use when work is stuck inside one frame, when the user asks how another field or industry would solve it, or asks for an analogy that actually transfers. Not for re-reading a decision at a larger scale (macrothink), listing options when no single frame is stuck, or checking claims (factchk).
An all-in-one Skill for automated data analysis and ad campaign optimization. Trigger it when the user uploads an Excel/CSV file or mentions any of the following: ① general data analysis (reading reports, data trends, visualization); ② account diagnosis (which campaigns perform poorly, which to pause, delivery diagnosis, account health check); ③ A/B test analysis (comparing two datasets, which version is better, whether results are significant, confidence); ④ daily report generation (delivery daily report, daily briefing, DingTalk/Feishu weekly report, comparison with yesterday). Suitable for feed ad optimizers, operations staff, and data analysts. Supports exported data from Juliang Engine, Tencent Ads, Meta Ads, Google Ads, Kuaishou and other platforms, and also any structured table from sales, finance, operations, etc. Even if the user only says "analyze this", "look at the report", "which campaigns need adjustment", "which of these two is better", or "generate a daily report", this Skill should be triggered.
Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset collection. Triggers on phrases like \"dataset bias\"、\"stratified sample\"、\"class imbalance\"、\"data distribution\"、\"fairness analysis\", or \"ethical review\".
WeChat Official Account article pipeline · use it when the end state is **formatted WeChat Official Account HTML** or **the article placed into your own WeChat Official Account drafts** (saves drafts only, never mass-sends). The input is **already-written** Markdown/HTML; this pipeline does not write the body text, only the deterministic operations that follow: render → pre-upload images → cover → save draft. ⚠️ It **writes to the user's own WeChat Official Account backend**; do not run it on your own initiative just because a draft is ready. Saving a draft requires an bound account + DOUBAOYA_API_KEY; not needed for local rendering / theme switching only. Trigger words: 正文写好了怎么发 / 要排版好的公众号 HTML / 接着排版发草稿 / 写公众号 / 转公众号排版 / 推公众号草稿 / 重新推草稿 / 带封面发布到草稿箱 / 把文章存进公众号草稿箱 / 公众号图文流水线 / dby-publish / 存公众号草稿 / 公众号草稿箱 / 代发公众号草稿箱 / addDraft / draft/add / 图文推进公众号 / 稿子发到公众号后台。
Diagnose Bolna voice-agent issues: robotic / laggy responses, agent interrupting users or never interrupting, long silences, premature hangups, webhook misses, wrong caller context, batch failures, SIP/SRTP no-audio, agent restricted by content policy, balance-low queueing, and provider connection latency. Maps symptoms to the exact field on the agent (`task_config`, `endpointing`, `incremental_delay`, `number_of_words_for_interruption`), and uses `latency_data` from `GET /executions/{id}` + raw logs to pinpoint which pipeline component (transcriber, LLM, synthesizer) is slow.
Finds out why a data quality check failed or errored, looks at the rows it matched, and recommends the fix. Also covers a materialized view refresh that the data quality gate did not publish. Use when asked why a check is red, what rows failed, why a view shows "Not published", why a view's data is stale after a refresh, or how to get a blocked refresh published. Trigger terms: failed check, failing rows, errored check, data quality failure, not published, blocked materialization, unpublished refresh, check keeps failing.
Deconstruct viral web novels on benchmark platforms: learn the structure, don't copy the words. Use when the user wants to deconstruct a book, analyze why a hit novel went viral, benchmark against a popular title, extract the opening/hook/power-up/pacing formulas of a hit, or asks to "write my own following this hit's approach". Outputs reusable structural templates and strictly upholds the no-plagiarism line.
Find one person's or one organization's data leaked into a shared repository, folder or artifact, using needles built from that owner's own records (names in every script, handles, emails, phone numbers, addresses, account and client ids), replace each hit with a role or placeholder that keeps the artifact working, and scan git history read-only for the commits that still carry them. Use when a public or shared repository, a template, a fixture set, docs or a deliverable may hold an operator's, a client's or a teammate's personal or business data, when someone asks to de-identify, anonymize, scrub or depersonalize an artifact, before publishing or open-sourcing a repository, or when a person's data must leave a codebase every operator runs.
Opinionated product-design skill for building, reviewing, polishing, and iterating on landing pages, apps, dashboards, AI products, design systems, and brand touchpoints. UX and comprehension first, then restraint (three type sizes, delete decoration), then foundations, then tactical craft — hierarchy, spacing systems, type scales, HSL palettes, shadows, finishing touches. Distilled from 20 YC Design Review videos (Linear, Stripe, Cursor, Framer) plus the Refactoring UI book. Use whenever the user asks to design, redesign, critique, or polish anything user-facing: "make it look better/more professional/trustworthy", de-slop the AI/vibe-coded look, fix a landing or pricing page, improve conversion, design an AI feature or agent UI, set up tokens or a design system, review a URL/screenshot/mockup. Also trigger for tactical UI questions — spacing feels off, visual hierarchy, choosing colors, typography, empty states, Tailwind/CSS styling — even without the word "design". Not for pure backend/DevOps work.
Critique UI visual quality with observable design criteria. Use this skill whenever the user asks for visual critique, design review, polish, hierarchy, spacing, typography, contrast risk, consistency, brand fit, anti-slop review, screenshot critique, Figma frame critique, or a fix brief for a weak interface. Keep findings actionable and evidence-labeled. Do not require Attention Insight, Khroma, or external screenshot upload for normal local critique.
Designs modular high-level architectures from functional requirements and produces design documents for each module. Use when designing a new system, creating architecture documentation, or producing module-level design specs with integration contracts and test specifications.
Build, plan, review, and document pyRevit extensions. Use when Codex needs the pyRevit development workflow, templates, prompts, checklists, or scripts for creating or updating pyRevit commands in this repo. Pair with a version-specific Revit skill (e.g., 2023/2024/2025) for API constraints.
Automatically illustrate Markdown documents by turning image markers into browser screenshots or AI-generated images, then writing an image-enriched Markdown output. Use when a document needs screenshots, generated visuals, semantic image placement, or end-to-end document illustration automation.
Convert Docker Compose files or installation docs into production-grade Sealos templates. Use when user has a docker-compose.yml and wants a Sealos or Kubernetes template, wants to migrate from Docker Compose to Sealos, needs to convert container orchestration configs to Sealos format, or mentions compose-to-template conversion. Also triggers on "/docker-to-sealos".
Generate production-ready Dockerfiles for any GitHub project. Supports monorepos, multi-stage builds, workspace detection, and iterative build-fix cycles. Use when the user asks to create, generate, write, fix, or improve a Dockerfile; containerize an application; mentions Docker build issues; needs a .dockerignore; or wants to package an app as a Docker image. Also triggers on “/dockerfile”.
Review legal documents as an experienced attorney. Analyzes contracts, ToS, privacy policies, NDAs, and corporate docs section-by-section. Identifies risks, gaps, and unfavorable terms with specific replacement text for problematic clauses.
Find the perfect available domain name for a product idea. Researches competitors, generates name theses, checks availability in parallel, and ranks the best options. Use when the user wants to find, brainstorm, or research domain names.
Writes, edits, and debugs Mermaid diagrams (flowchart, sequence, class, state, ER, Gantt, pie, mindmap, timeline, quadrant, git graph, XY, Sankey, architecture, journey, kanban, block). Use when the user says "draw a diagram", or when the user asks for a diagram, flowchart, ERD, or Mermaid code, or when a Mermaid diagram fails to parse or render.
Extracts and analyses empirical results from primary research papers, summarising each result, explaining its importance, and decomposing the discussion into supporting or contrasting citations. Use this skill whenever the user pastes a paper, uploads a PDF, or shares a results/discussion section and wants to understand what was found and how it fits the literature. Trigger on phrases like "analyse this paper's results", "what did this paper find", "extract the results", "break down the discussion", "what papers support or contrast this result", "help me ground this paper in the literature", "summarise the findings", or "what's the discourse around these results". Also trigger when the user is building a literature review and needs to understand what a specific study found and how its discussion situates the results in prior work. Do NOT use for review papers, detect these early and refuse gracefully (see below).
Optimize multilingual product listings for international e-commerce including SEO localization, machine translation workflows, and cultural adaptation. Use this skill when the user needs to create product listings in multiple languages, optimize for local search, or adapt marketing content for different markets — even if they say 'translate our listings', 'optimize for local SEO', 'adapt for the Japanese market', or 'our translated listings don't convert'.
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.