Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Manage local Airflow environment with Astro CLI (Docker and standalone modes). Use when the user wants to start, stop, or restart Airflow, view logs, query the Airflow API, troubleshoot, or fix environment issues. For project setup, see setting-up-astro-project.
Integration patterns for Mapbox MCP DevKit Server in AI coding assistants. Covers setup, style management, token management, validation workflows, and documentation access through MCP. Use when building Mapbox applications with AI coding assistance
Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity — e.g., "create my SOUL.md", "bootstrap my agent", "set up my AI partner", "define who you are", "let's do onboarding", "personalize this AI", "make you mine", or when a SOUL.md is missing. Also trigger for updates: "update my SOUL.md", "change my AI's personality", "tweak the soul"
Write LinkedIn posts that match the user's voice system (about-me.md and voice.md). Use this skill whenever the user says "write a post", "draft a post", "LinkedIn post", "post about [topic]", "content idea", or wants help writing any LinkedIn content. Also trigger when the user pastes a context dump (notes, transcripts, bullet points) and wants it turned into a post. Always references the voice files in the project before writing. Always outputs the final post in a code block.
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an eased pointer
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.
Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to end. Covers extracting the implicit repro from a thin report (env, build, steps, data), the reproduce-minimize-isolate-capture loop, git bisect to find the introducing commit, building a deterministic minimal repro (fixed seeds, frozen time, stubbed network), writing the failing regression test BEFORE the fix (red) and confirming the fix flips it green, and writing repro evidence back into the ticket. Distinguishes flaky-not-reproducible from environment-specific. Use when: "reproduce this bug," "minimal reproduction," "repro steps," "find the commit that broke it," "git bisect," "make the repro deterministic," "write a failing test for this bug," "regression test for a defect," "can't reproduce this bug." Not for: Classifying/deduplicating/severity-routing existing failures without reproducing them — that is ai-bug-triage. Generating tests from specs rather than from a defect — that is ai-test-generation. Related: ai-bug-triage, ai-test-generation, test-reliability, systematic-debugging, qa-project-context.
Lightpanda browser, a drop-in replacement for Chrome-based browsing in any AI agent — faster and lighter for tasks without graphical rendering, such as data retrieval. Use it via MCP server, CLI fetch, or CDP with Playwright/Puppeteer — or run/save automations as deterministic, token-free replay scripts (PandaScript) via its own agent mode.
Extracts learnings from execution trajectories at the end of a Mantis loop. Use to parse agent conversations, extract successes, failures, and false assumptions, and append them to workspace/learnings.jsonl. Don't use for analyzing source code or writing patches.
Run an AWS Security Agent scan on the workspace. It uploads the source to AWS, scans it with the managed Security Agent service, and returns ranked, verified findings with code locations and remediations. Use when the user asks to scan code, find vulnerabilities, run a security scan or review, check security issues or scan status, show findings, list recent scans, or stop a scan.
Performs graph-assisted triage of a single security finding, SARIF result, weAudit annotation, suspicious function, or report excerpt using Trailmark reachability, entrypoint paths, taint, privilege-boundary, blast-radius, caller/callee, and neighborhood evidence. Use when deciding whether one candidate issue is reachable, prioritizing a finding before PoC work, preparing evidence for exploit validation, or checking whether a static-analysis result is actionable.
Add a restrained particle atmosphere inside one section with configurable shapes, density, gravity, wind, sway, rotation, recycling or settling, pointer disturbance, visibility pausing, responsive limits, and reduced-motion fallbacks. Use for petals, leaves, snow, sparks, confetti, dots, paper, icons, or brand fragments that support a section's mood without obscuring content.
Use when the user wants to research competitors' social media strategy, compare brands or creators, find what content is working in a niche, identify content gaps, or produce a practical social strategy brief from public social data.
IDA Pro reverse-engineering assistance skill. Always use this skill when the user mentions reverse engineering, decompilation, analysis of binaries/PE/ELF/APK/DLL/SO, cracking, finding passwords, vulnerability analysis, malware analysis, firmware analysis, or needs to analyze files such as exe/dll/so/elf/macho/sys. Ensure to use this skill whenever the user wants to analyze any binary file, regardless of whether they explicitly mention “IDA” or “reverse engineering”. This includes requests like “看看这个exe”, “分析这个dll”, “帮我破解”, “找一下密码”, “这个软件怎么注册”, etc. Use the bundled scripts (scripts/start.ps1, scripts/open.ps1) for deterministic server management and file opening; do not write ad-hoc PowerShell commands for these operations.
Find company and contact data. Turn your agent into a prospecting platform. Get contact information, roles, tech stacks, business events, website changes, and intent data. Build lead lists, research prospects, and identify talent. 150M+ companies, 800M+ professionals, 50+ data sources.
Use when the user wants to analyze active ads from Meta/Facebook, Google, or LinkedIn ad libraries; tear down a competitor's messaging; extract hooks, offers, CTAs, video transcripts, landing page claims, and test ideas from public ads.
Install and operate Everything Claude Code (ECC) on the DeepSeek Harness (DSH): native skill roots (~/.dsh/skills, .agents/skills), the @deepseek-ai/dsh-hooks-claude-code bridge for command hooks, bare-insert patch mounting, generator usage, event-support limits, and update workflow. Use when setting up ECC on DeepSeek Harness, wiring ECC hooks into a DSH profile, or debugging why ECC skills or hooks do not appear in a DSH session.
Builds and ships iOS/macOS apps with XcodeGen, SwiftUI and SPM: Xcode build fixes, device deployment, Apple Developer signing/notarization, CI/CD pipelines. Use for XcodeGen project.yml setup, "Library not loaded @rpath" crashes, code-signing errors (Error -25294, adhoc fallback), or Electron notarization failures. Not for TCC permission dialogs (use macos-permissions) or disk cleanup (use macos-cleaner).
Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fields): "fill in the form", "fill out this PDF", "complete the form fields", "write values into PDF", "what fields does this PDF have". REFORMAT (apply design to an existing doc): "reformat this document", "apply our style", "convert this Markdown/text to PDF", "make this doc look good", "re-style this PDF". This skill uses a token-based design system: color, typography, and spacing are derived from the document type and flow through every page. The output is print-ready. Prefer this skill when appearance matters, not just when any PDF output is needed
Generative UI with OpenUI: build apps and agents whose model responses render as live interfaces. Use when the task involves OpenUI, OpenUI Lang, `@openuidev/*` packages, OpenUI Gateway, Autofix, or the `@openuidev/cli` (create, generate, deploy), or when the user wants a generative UI chat, agent, or dashboard
Use only for MSBuild failure investigation, build-performance analysis, or review of existing build XML/extension contracts. A plan to convert a working legacy/non-SDK project to SDK style or migrate packages.config is a project-system migration, NOT a build-file review: do not activate, even to check scope. Framework/API upgrades are also excluded. Activate for advisory Import/Exists hook and NuGet packed-import questions even without a checkout or failed build; .csproj/.fsproj/.vbproj/.props/.targets conditions; custom-target inputs/outputs; .binlog capture/replay; failing dotnet build/restore/pack/publish or MSBuild-based test builds; slow evaluation, compilation, copying, or no-change builds; and controlled timing comparisons. Exclude SDK installation alone, C# refactoring, runtime profiling, assertions after successful builds, and non-MSBuild builds.
Lightning Web Components with PICKLES methodology and 165-point scoring. TRIGGER when: user creates/edits LWC components, touches lwc/**/*.js, .html, .css, .js-meta.xml files, or asks about wire service, SLDS, or Jest LWC tests. DO NOT TRIGGER when: Apex classes (use sf-apex), Aura components, or Visualforce.
Test REST and GraphQL APIs with Playwright APIRequestContext, Supertest, or standalone HTTP clients. Covers schema validation with Zod 4/AJV, auth flow testing, CRUD lifecycle tests, error and header validation, pagination, and performance assertions. Use for “API test,” “endpoint test,” “REST test,” “GraphQL test,” “schema validation,” or “Postman replacement.” Not for consumer-driven contract verification (Pact, broker) — use contract-testing; browser UI flows — use playwright-automation. Related: contract-testing, test-data-management, ci-cd-integration, playwright-automation.
Run an in-depth root-cause investigation with the AWS DevOps Agent. Use when the user describes an incident, alarm, outage, or unexplained behavior—keywords include “5xx”, “503”, “OOM”, “latency spike”, “deployment failure”, “rollback”, “sev1”, “investigate”, “root cause”, “debug”, “alarm fired”, and “service down”. Polls and streams progress, then presents recommendations.
Run a fast AWS Security Agent diff scan on only the changed code since a git ref. Use when the user asks to scan changes, run a diff scan, check what changed for security issues, scan before committing, scan before PR, or any pre-commit/pre-push security check.
Create or redesign creative-studio, agency, photographer, artist, and portfolio websites where project work leads the story. Use for dark editorial shells, full-bleed campaign media, color-coded case-study chapters, oversized service typography, restrained project reveals, and a decisive contact finale.
Guide for using MSBuild Server to improve CLI build performance. Activate when developers report slow incremental builds from the command line, or when CLI builds are noticeably slower than IDE builds. Covers MSBUILDUSESERVER=1 environment variable for persistent server-based caching. Do not activate for IDE-based builds (Visual Studio already uses a long-lived process).
Prepares and launches nf-core/pacsomatic matched tumor-normal PacBio HiFi genomics workflows from unaligned BAM inputs. Supports samplesheet generation, pinned Nextflow launch artifacts, local checks, LSF/Slurm/PBS Pro/SGE launcher submission, and startup troubleshooting. Use for pacsomatic run preparation and execution, not general short-read somatic analysis or medical imaging PACS.
Writes marketing copy using proven copywriting frameworks. Use when user needs copy for ads (Facebook, Instagram, TikTok, YouTube), landing pages, sales pages, email sequences, LinkedIn posts, product descriptions, or any marketing content.
Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write, rewrite, review, and lint modes.
Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities are spatial text boxes, Markdown, page raster output, and local parsing with optional custom HTTP OCR.
Create a recurring daily UI inspiration capture. Use when the user asks to run, refresh, package, or validate dated UI inspiration bundles, especially for `articles/YYYY-MM-DD-ui-inspiration-capture/` outputs, Framer/Dribbble landing-page inspiration, motion-study screenshots or videos, AI-builder prompts, duplicate checking, or converting a project runbook into a repeatable workflow
When catching up on an unfamiliar field, start with general terms to identify the community's terminology, key people, and media (academic societies, journals, personal blogs, videos, repositories, lists). Follow citations, links, and authors from one source to another, and save the target original sources (papers, personal articles, or video subtitles) without summarizing them to ~/research/{topic}/sources/. Add to map.md each week with a list of terms, people, media, and original sources; stop when saturated and every research question has an original source. In watch mode, fetch new posts via RSS from media listed in map.md (Qiita/Zenn tags, note, YouTube, blogs, arXiv) and list them with the opening of each source. Use for: “follow the trail”, “I want to catch up on this field”, “dig in through the community's terminology and people”, “look for papers or prior work”, “find the sources behind this technique”, “collect how skilled people do it”, “download the originals”, “/imozuru”, “Is there research on X? I want the original source”, “I don't understand at all—trace how it developed”, “I want to know what this community calls things”, “check new posts about X”, “round up this week's articles on X”, “catch up”, “/imozuru watch”, “dig into this field”, “find the canonical papers on X”, “literature dive”, “what's new in X this week”. Do not use for checking a single fact (year, yes/no, one specification—just search), searching local PC files, or summarizing or explaining material you've already read.
Expands one confirmed or suspected vulnerability into a Trailmark graph neighborhood of variant candidates by finding sibling functions, shared callers and callees, common sensitive sinks, common entrypoint paths, interface implementations, override relationships, type/reference neighbors, and structurally similar nodes. Use after one issue is found to seed variant-analysis, semgrep-rule-creator, static-analysis, or manual review with graph-derived candidate locations.
Query Dynatrace security data in security.events with DQL: vulnerabilities, threat detections, compliance posture, and scan coverage. Covers Dynatrace-native Runtime Vulnerability Analytics (RVA — CVEs, reachability, exposure, exploit), Runtime Application Protection (RAP), Automated Detections, Security Posture Management (KSPM/CSPM), and the Dynatrace vulnerability feed, plus external tools. Trigger: "open critical vulnerabilities", "vulnerable functions in use and publicly exposed", "top vulnerable libraries / K8s workloads", "CIS/DORA compliance pass rate", "SQL injection detections", "map external findings to workloads", "hosts not covered by scanning", "does Dynatrace know CVE-X / how is it fixed", "what is DTV-…", "new in the feed", "exploited in the wild (KEV)". Do NOT use for explaining existing DQL (use dt-dql-essentials), Davis problems (dt-obs-problems), logs (dt-obs-logs), distributed tracing (dt-obs-tracing), service RED metrics (dt-obs-services), or platform usage/audit telemetry (dt-platform).
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.