Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when the user wants to create AI music videos (MV)—including generating music from text prompts or using custom lyrics. Before blocking on execute_workflow, tell the user the MV pipeline is running until completion; after return, immediately forward the result—user need not ask for progress. Triggers: generate MV, music video, make video for this song, lyrics video, create MV, AI music video, music+video, generate video from lyrics.
Generates Chinese script content based on narrative pacing and dialogue mechanisms common in Jiang Wen films. Use when the user asks to generate script, write script, create scenes, output dialogue draft, revise script or similar. Outputs story synopsis, character bios, scene outlines, scene scripts (with dialogue, action, staging), and can adjust era, character relations, conflict pacing, and endings per user request.
Git workflow commands for committing changes and managing pull requests. Use when the user says '/git commit', '/git commit-all', '/git pr', '/git pr-update', '/git pr-pull-review', or '/git help'. Supports atomic commits, conventional commit format, and PR creation/updates without AI attribution.
Use when writing BK-CI Git commit messages and organizing commit boundaries, such as choosing a commit type, writing a commit message, deciding whether to split commits, and running pre-PR self-checks. Prefer this when the user wants to commit code rather than discuss implementation details.
Provides comprehensive guidance for GitHub Actions including workflow creation, actions, secrets, and automation. Use when the user asks about GitHub Actions, needs to create GitHub workflows, automate GitHub processes, or configure CI/CD with GitHub Actions.
Enable the GitHub CLI (`gh`) in Claude Code cloud sessions and GitHub Copilot coding agent environments. Use this skill when: (1) setting up a project so cloud AI agents can use `gh` for PRs, issues, and releases, (2) configuring setup scripts or SessionStart hooks for `gh` installation, (3) adding `copilot-setup-steps.yml` for GitHub Copilot agents, (4) troubleshooting `gh` auth failures in cloud sessions, or (5) configuring `GH_TOKEN` for headless environments. Triggers on: "enable gh", "github integration", "Claude Code cloud setup", "copilot setup steps", "gh auth in cloud", "gh not working in cloud", "setup script", or any request involving GitHub CLI access from cloud-based AI coding agents.
Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images/GIFs for visual evidence.
Install, wire up, and tune glimm—WebGL color-sweep page transitions—in a web project, with correct setup and candid guidance on where it fits. Use whenever the user wants page transitions, route-change animations, more lively or polished navigation, mentions glimm by name, or asks for “view transitions with some color” in a Next.js or React site, even if they never name a library. Also use when customizing an existing glimm install—changing palettes, matching brand colors, adjusting sweep timing or direction, or excluding specific links. Also use when a single in-app moment should get a sweep, such as a plan upgrade, a payment landing, a mode change, or a generated result.
Delete a Grove tenant account via wrangler D1 commands. Use when the user wants to remove a test account, clean up after a walkthrough, or fully delete a user's data. Handles D1 CASCADE cleanup, R2 media purge, and Heartwood session invalidation.
Write effective, maintainable tests that catch real bugs and enable confident refactoring. Use when deciding what to test, reviewing test quality, or writing tests for Grove features. Focuses on philosophy and strategy—pair with javascript-testing for implementation details.
Build a Vineyard showcase page for any Grove property using @autumnsgrove/lattice/vineyard components. Vineyard is the consistent /vineyard route where each tool demos its features, documents its API, and shows its roadmap. Use when creating or updating a property's vineyard page.
End-of-session ritual. Captures decisions, lessons, gotchas, and open threads. Writes a narrative session log to ~/.origin/sessions/ and stores granular memories via Origin MCP. Previews any unconfirmed captures from the current session before closing. Invoked as `/handoff`.
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management, making interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
Thoroughly analyze a single function by first recovering its type definitions, constant definitions, vtables, function name and signature, then producing the final decompilation. Use when the user wants a complete per-function analysis following the strict recovery order: types → constants → vtables → function identity → decompilation.
Use when the user wants to convert HTML slides to .pptx—for example, “HTML to PPT,” “web slides to pptx,” “convert this deck to ppt,” “make a ppt copy for a colleague,” or “it’s inconvenient to present in a browser”—or provides a .html path and mentions ppt / pptx / presentations / slides. Keep vector text editable, embed fonts as needed, and automatically fall back to screenshots for complex decorations; do not depend on specific frameworks such as reveal.js or a custom-built deck.
Convert a rendered HTML page (especially A0 conference posters) into a native PowerPoint .pptx with editable text + native shapes — NOT a PNG-in-slide. Walks the live DOM via headless chromium, extracts BLOCK-level text containers (p/h1-h6/li/td) as TextBoxes with inline <strong>/<em> as mixed-style Runs, <img> as Picture with object-fit:contain respected (plus white-tile decoration under transparent-PNG logos), CSS ::before/::after generated content (e.g. 'So what →' callouts) as inherited-style runs, SVG via cairosvg rasterization, decorative <div>/<section> with bg/border/gradient/box-shadow as Rectangle/RoundedRect with matching fill (solid + linear-gradient + outer shadow). All CSS colors (including color-mix/oklab/color()) normalized via canvas. CSS hyphens:auto becomes OOXML soft hyphens via pyphen. CSS line-height absolute Pt for paragraph spacing. Native OOXML bullets with hanging indent. Optional Claude-vision fidelity auditor runs by default (toggle with `--no-vision-audit`); diffs HTML truth vs PPT render → structured 12-category issue report. Supports both direct API (`ANTHROPIC_AUTH_TOKEN`) and base-URL proxy (`ANTHROPIC_BASE_URL`) auth. Targets ~95% visual fidelity with web fonts installed. TRIGGER when user asks: 'HTML to PPT', 'poster to PowerPoint', 'editable PPT from HTML', 'pptx from html', '1:1 PPT clone', or wants an HTML render shipped as an editable .pptx for a non-developer collaborator.
Manage CloudRobo workspaces — create, list, show, update, delete workspaces; manage workspace members (add, list, update role, delete); view workspace overview statistics (capacity, used, available, member count); switch active workspace context for use by other cloudrobo skills (dataset, train, eval, infer, etc.). Workspace is the foundational resource container — all other CloudRobo operations require a valid workspace_id. Triggers include: workspace management, workspace member management, workspace switching, workspace overview, workspace configuration, default workspace, 工作空间管理, 工作空间成员, 工作空间切换, 工作空间概览, 工作空间配置, 默认工作空间.
Huawei Cloud LTS (Log Tank Service) full lifecycle management via hcloud CLI. Covers log groups, log streams, indexes, transfer tasks, keyword/SQL alarm rules, and log search. Supports Query (list/show logs, alarms, transfers, indexes), Create (log groups/streams, indexes, transfers, alarms), Update (TTL, index, transfer, alarm config), Delete (log resources, alarm rules), and Diagnose (search logs to locate faults). Delete operations require explicit user confirmation; batch deletion of all LTS resources is prohibited. Triggers include: LTS, 云日志服务, log group, log stream, 日志组, 日志流, 日志检索, 日志转储, 日志告警, 索引配置, log transfer, log alarm, log index, 日志运维, 故障排查, log search, structured log, SQL alarm, keyword alarm.
Huawei Cloud algorithm auto-design (LLM4AD) skill. Performs the full lifecycle through KooCLI (command-line entry `hcloud`): algorithm project management, file upload, evolve task CRUD, status polling, result retrieval, and log inspection; also uses KooCLI's `hcloud IAM` subcommand to create the trust agency and grant algorithm design module bucket permissions. Trigger words: code evolution, evolve task, LLM4AD, algorithm optimization, upload algorithm file, create evolve task, start evolve task, fetch evolve result, evolve log, 代码演化, 演化任务, LLM4AD, code evolution, 算法优化, 上传算法文件, 创建演化任务, 启动演化任务, 拉取演化结果, 演化日志
Removes signs of AI generation from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive guide "Signs of AI writing". Detects and fixes patterns such as: significance inflation, promotional tone, superficial -ing analysis, vague attribution, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, excessive conjunctions.
Build agent-friendly motion-graphics videos with Hyperframes (HTML-to-MP4). Three levels of effort — Level 1 website-to-video for quick conversions, Level 2 storyboards for guided design iteration, Level 3 fully custom guided-video productions with cut/storyboard/motion-graphics workflow. Triggers on "hyperframes", "html to mp4", "render with hyperframes", "motion graphics for [recording]", "storyboard a video", "/hyperframes-helper".
Repurpose existing content into a native Instagram post. Turn a LinkedIn post, blog, YouTube script, or X post or thread into Instagram content: make long pieces a carousel or caption, re-hook before the 125-character fold, strip off-platform artifacts (X @-handles, link in bio), and publish via Publora on approval. Use to adapt content across platforms for Instagram. Not for writing from scratch (use ig-caption-writer or ig-carousel-planner), or auditing a draft (ig-humanizer --mode audit).
Implements supply chain integrity verification for container builds with the in-toto framework: generating signing keys, defining a supply chain layout, recording pipeline steps as signed link metadata, verifying before deployment, enforcing at Kubernetes admission, and integrating with SLSA. Use when attesting CI/CD pipeline steps, proving an image followed the approved build process, or enforcing provenance at admission. Keywords: in-toto, layout, link metadata, step, inspection, SLSA, provenance, admission. Do not use for signing and verifying images with Cosign - use implementing-image-provenance-verification-with-cosign.
Activates when the user asks to write, draft, translate, or revise Italian texts for public, editorial, blog, social media, newsletter, marketing, fiction, nonfiction, or informational use. It also activates when the user asks to humanize Italian texts, remove AI patterns, correct chatbot-like wording, capture or calibrate an author's voice based on a corpus of their texts, respond to an automatic detector that flagged human-written text as generated, or revise Italian text generated by language models.
Prefers `jo` (https://github.com/jpmens/jo) for constructing JSON in shell snippets over hand-written quoted JSON literals. Removes quote-escaping pitfalls, makes variable interpolation natural, and lets `jo` infer field types from values (with explicit coercion when needed).
Decision-support lens for distilling Justin Sun's public X posts (@justinsuntron) into short-horizon crypto, crypto-equity, and related US-stock catalysts. This skill should be used when the user mentions Justin Sun, Sun Yuchen, @justinsuntron, TRON/TRX, JST, SUN, BTT, HTX, Poloniex, WBTC, WLFI, TRUMP memecoin links, Tron Inc. / NASDAQ:TRON, SunPump, or asks what a Justin Sun X post means for a ticker/token. Live-fetch or inspect the latest posts first. Decision-support only; never auto-trades and never places, amends, or cancels orders.
Audit Kafka security configuration across the codebase and live cluster using the Lenses MCP server. Checks authentication (SASL), encryption (SSL/TLS), authorisation (ACLs), secrets management and environment tier mismatches. Use when user says "audit Kafka security", "check security config", "is my cluster secure" or asks about authentication, encryption or credentials. Do NOT use for configuring certificates, creating SASL users or setting up ACLs.
Stand up a personal Kanban board and wire this agent to it, end to end. Serve the board, publish it to a public URL, verify the connection, and hand the user their live link. Each user gets their OWN board at their OWN URL — self-contained, no shared server, no collisions. Use when the user wants to set up / publish / deploy their Kanban board, or connect their agent to it. For day-to-day task operations (create/move/list tasks) use the nested companion skill `kanban-agent` (in kanban_agent_skill/) instead — it is auto-discovered when this skill is installed.
Comprehensive knowledge base for go-kratos microservices framework. **Use this skill when:** - Building REST/gRPC APIs with kratos (Service → Biz → Data layered architecture) - Creating microservices with DDD and Clean Architecture patterns - Implementing dependency injection with Wire - Configuring service discovery, load balancing, and resilience patterns - Troubleshooting kratos issues or understanding framework conventions - Generating production-ready microservices code with Protobuf **Features:** - Complete pattern guides with ✅ correct and ❌ incorrect examples - DDD/Clean Architecture enforcement - Production best practices - Common pitfall solutions
Lands a reviewed pull request by rebasing onto the base when the branch is behind and resolving any conflicts, running the project's declared pre-merge steps, pushing, waiting for green CI, and squash-merging. Use when the user says "ship it", or when the user explicitly asks to land, ship, or merge a reviewed PR. Never infer from approval, green CI, or completion. Not for a watch that should merge on approval; use watching-authored-prs. Not for updating a PR without landing; use modernizing-prs.
Expert guide for using latenode-mcp MCP tools effectively. Use when searching for nodes, managing scenarios, managing credentials or using any latenode-mcp tool. Provides tool selection guidance, parameter formats, and common patterns. IMPORTANT — Always consult this skill before calling any latenode-mcp tool — it prevents common mistakes like wrong nodeType formats, incorrect parameter structures, and inefficient tool usage. If the user mentions Latenode, scenarios, nodes, or connections and you have latenode-mcp MCP tools available, use this skill first.
Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like \"setup latex\", \"biber vs bibtex\", \"latex compilation error\", \"install latex packages\", \"venue template\", or \"texlive 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.