Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Provider-independent ecommerce product imagery production for marketplace listings, product pages, hero shots, lifestyle scenes, comparison charts, infographics, variant/packaging images, virtual try-on or placement mockups, ads, and AI-assisted product visuals. Use when an agent must plan, generate, edit, review, localize, package, or QA truthful commercial product images while managing SKU continuity, marketplace requirements, claims, rights, releases, accessibility, and approval.
Execute a signed-off PLAN.final.md for a single feature yourself, phase by phase, on the current branch — you are the engineer, not a delivery lead. Use when the user invokes /execute-plan, or asks to implement, build or continue an approved plan that is small enough for one person, e.g. "/execute-plan spell-check", "/execute-plan spell-check p1-p3", "build the rest of the plan while I sleep". Resolves the requested phases against the final doc, builds each as its own verified increment, runs its verification before the next begins, and commits each landed phase without waiting for approval. Questions that need the user are recorded with a recommendation instead of blocking. For a roadmap large enough to want parallel sub-agents, use execute-roadmap instead
Expose a Factorial Code process to Factorial as a Factorial Action—the `factorial` block in a process's metadata.json (master switch, awaitResult, requiredPolicies, and the uiTrigger / form / agentTool / backend entry points), the Factorial One tool contract (description, effect, whenToUse, whenNotToUse, preconditions, doesNotDo, degradation, simulatesFor), the reserved lifecycle slugs, the parameters schema as the contract with Factorial, and how the legacy `form` / `uiTrigger` blocks are kept mirrored. Use when configuring how Factorial reaches a process, writing an agent tool contract, or filling the "Trigger from Factorial" section of a process.
Feishu cloud document content: read and summarize docx/wiki/sheet (including converting to Markdown ready to send in IM); create documents from scratch (templates for PRDs, proposals, reports, minutes, and other formats, DocxXML drafts, and doc script preflight checks); create and edit docx (create with content and upload local images/attachments/HTML blocks/board source files, append, overwrite, precisely replace/delete/move by section or block, insert local or clipboard images, set document covers, view and roll back version history); import Markdown (convert Mermaid/PlantUML/SVG to boards); export Markdown/PDF/Word/Excel and download or preview document assets; upload, diff, and overwrite native .md files in cloud drives; and read and edit nodes in existing mind maps. Use when users want to read, summarize, write, add to, or rewrite Feishu documents; import Markdown into Feishu; export documents locally; set document covers; work with mind map nodes; or roll back accidental document changes. Do not use for comments (even if the request mentions documents), collaborators and permissions, importing binary files such as DOCX/XLSX, file versions and cloud drive directories (use feishu-cli-storage); reading or writing sheets by cell (use feishu-cli-data); dynamic HTMLBox/ECharts components in documents (use feishu-cli-visual); or retrieving meeting minutes, meeting notes, and transcripts (use feishu-cli-meetings; still use this Skill to write minutes-style documents).
Fix bugs and make small improvements while leaving the codebase better than it was found. Use when the user asks to fix a bug, clean something up, or make a minor improvement. Every fix explains the root cause for the reviewer, justifies the chosen solution against alternatives, and looks for the simplification the bug is pointing at — and asks before any product decision, large-blast-radius change or persisted schema/format change.
Create, edit, review, refactor, or rewrite Markdown artifacts while preserving meaning, valid syntax, navigability, and human reviewability. Use whenever work directly changes or reviews a Markdown file, including README.md, AGENTS.md, SKILL.md, reference docs, design docs, or Markdown produced from notes, transcripts, scratch text, or rough drafts.
When the user wants help setting up or auditing Google Ads conversion tracking, Google Tag, Google Tag Manager, enhanced conversions, conversion actions, attribution models, cross-channel attribution, GA4 import, phone call tracking, or troubleshooting conversion data issues. Triggers on 'conversion tracking', 'Google tag', 'gtag', 'GTM', 'Tag Manager', 'conversion action', 'enhanced conversions', 'attribution model', 'conversion window', 'tracking not firing', 'missing conversions', 'GA4 import', or 'phone call tracking'. This skill is a prerequisite for google-ads-bidding Smart Bidding and google-ads-audiences remarketing.
Hardens the Docker daemon (dockerd) through /etc/docker/daemon.json with user namespace remapping, TLS client authentication, seccomp profiles, and CIS Docker Benchmark controls such as icc, no-new-privileges, and live-restore. Use when securing a Docker host's daemon to prevent privilege escalation, breakout, or lateral movement, or when auditing daemon settings against CIS requirements. Keywords: dockerd, daemon.json, userns-remap, no-new-privileges, icc, live-restore, TLS socket. Do not use for hardening images and per-container runtime flags - use hardening-docker-containers-for-production.
Use when the user asks to design, review, add, drop, consolidate, or tune SQL Server indexes. Proactively activate for clustered vs. nonclustered design, covering indexes and INCLUDE columns, filtered indexes, columnstore indexes, missing-index DMV interpretation, duplicate or unused indexes, index maintenance, fragmentation, fill factor, compression, partition-aligned indexes, partition elimination proof, huge-table index constraints, online/resumable rebuilds, and index changes for slow T-SQL queries. Provides an index-design decision tree, workload-aware tradeoff checklist, DMV interpretation guidance, and maintenance/rebuild patterns.
Generate AntV Infographic syntax only. Use when asked to turn notes, outlines, reports, or other user content into the Infographic DSL with template selection, data structuring, and theme hints. Do not use for HTML rendering or TS/TSX component implementation.
AGENTS.md contract: 42. WITHOUT ASKING, run it if the coverage contract is below 42 or missing; above 42, do not lower it—update iskronify. For repositories without signs of the project, only suggest it. Triggers: iskronify, “level up the repo,” “bring the project up to standard,” “create/update AGENTS.md,” set up AGENTS.md. Two phases: “stand up” — graph, scope by origin, role, coverage, guard; “finish” — slots from the graph, code, and agents’ responses in alignment work, without waiting for a person; reserve principled decisions for them, and when no one can be asked, anything that cannot be inferred. Requires iskron_* tools.
Apply when producing any markdown artifact for someone else (or future-you) to read — READMEs, analysis documents, Confluence pages, status reports, troubleshooting write-ups, skill content, conversation summaries, ticket descriptions, post-mortems, snapshots of system state, or any document that contains concrete current-state values. Defines the "snapshot + reproducer" rule (every static value must be paired with the command/query/script that regenerates it), the single-source-of-truth rule (reference canonical homes instead of duplicating values), and fact-vs-assumption marking. Trigger keywords include writing or producing or creating or drafting a README, analysis, Confluence page, status update, summary, snapshot, current state, documenting data, posting findings, file tree, port number, version number, table count, or any concrete value that may drift over time.
Provides authoritative guidance for Lynx development involving pages, templates, components, CSS, layouts, elements, web migration, rendering or styling bugs, and code review. Applies to *.ttml, Lynx *.tsx, and all Lynx-specific files, and requires searching the installed API docs before acting.
Write, edit, and review MaaFramework interface.json (Project Interface V2) — task entry declarations, controller/resource configuration, GUI option wiring (pipeline_override and override order), presets, pretask startup tasks, agent child process configuration, import splitting, and structure troubleshooting. Use when creating, editing, or reviewing an interface.json for a MaaFW project, adding user-facing options or presets, wiring pipeline_override, configuring pretask or agent child processes, splitting interface files via import, or diagnosing interface structure errors.
Create or update a RevealJS HTML presentation using the repository's bundled slide template. Use for creating RevealJS talks, making HTML slide decks, building presentation slides, starting a new conference talk deck, or converting a talk outline into RevealJS slides.
Generate images, videos, and SVGs using x402-protected AI models at StableStudio. USE FOR: - Generating images from text prompts - Generating videos from text or images - Editing images with AI - Vectorizing images to SVG - Creating visual content TRIGGERS: - "generate image", "create image", "make a picture" - "generate video", "create video", "make a video" - "edit image", "modify image" - "vectorize", "convert to svg" - "stablestudio", "nano-banana", "sora", "veo", "grok", "flux", "seedance", "gpt-image" ALWAYS use `npx agentcash@latest fetch` for stablestudio.dev endpoints.
Operate WorldEdit safely for Minecraft 26.x and 1.21.x selections, region edits, masks, schematics, brushes, terrain shaping, and rollback. Use for command-driven world editing, not plugin development or general server administration.
(NS) LangGraph.js agent-api — bootstrap-agent-runtime, StateGraph, MCP, skill bind/inject, checkpointers, user memory, HITL/SSE. Use for new agent-api, LangGraph graphs, MCP wiring, orphan layout, bind parity, graph-spec sync, or “fix my LangGraph agent” / “wire MCP tools” / “translations in the graph.” Do NOT use for CrewAI, generic web apps, or SDD-only with no agent-api.
Creative director and orchestrator for Pawbytes Creative Suites. Use when the user needs creative direction, campaign planning, brand setup, or help choosing the right creative specialist or workflow. Triggers: “Aria,” “creative direction,” “campaign planning,” “brand setup,” “which creative agent should I use,” “creative suite”.
Review code phong cách SENIOR 10 năm — bốn mục security · performance · naming · logic, mỗi mục cho ĐIỂM/10 + LỖI NẶNG NHẤT + CÁCH SỬA, rồi một kết luận PASS-sang-bước-kế hay CẦN-SỬA. Mục logic tìm bug (null/rỗng/âm/overflow, off-by-one, race) và SINH một test-case tái hiện cho mỗi bug (đặt tên qc-*), các test đó auto-chạy qua hook tất định (0-token, không LLM). Gọi khi user nói "qc code", "review code", "soi code", "chấm điểm code", "kiểm tra chất lượng code", "/qc-code". KHÁC /orca-sec-scans (Trivy quét TĨNH — vuln/misconfig/secret) và /code-review built-in (review tổng quát): qc-code là format senior bốn-mục-chấm-điểm-verdict + sinh test tái hiện. Mặc định review DIFF hiện tại; chỉ định file khi cần.
Optimize Roblox monetization strategy. Use for game passes, developer products, bundles, store UX, pricing ladders, premium anchors, cosmetics, conversion experiments, offer placement, revenue analysis, and fair non-pay-to-win monetization.
Structured session analysis and project instruction refinement using a five-type intervention taxonomy (Correction, Repetition, Role Redirect, Frustration Escalation, Workaround) with severity scoring. Refines project instructions (CLAUDE.md, AGENTS.md) with structural language, maintains WORKING_STATE.md for crash recovery, and implements a self-reminder protocol to prevent role drift. Includes advisory-to-structural promotion for recurring gaps. Use after milestones, repeated user corrections, session restarts, crash recovery, every 5 completed tasks, or on request. Triggers on: “reflect on this session”, “why do I keep correcting you”, “update project instructions”, “session retrospective”, “crash recovery”, “context compaction”, “role drift”, “analyze my corrections”. Also relevant when noticing repeated corrections or resuming after compaction.
Builds accessible, customizable component libraries using shadcn/ui with Radix UI or Base UI, Tailwind CSS 4, and React 19. Covers component ownership, oklch CSS theming, type-safe forms with Field and Zod, CLI workflows, and registry patterns. Use when adding shadcn/ui components, configuring themes, building forms with Zod, creating custom registries, or composing accessible component variants. Use for shadcn CLI, dark mode, component variants, form validation.
First-response triage for cross-code (LAMMPS/VASP/QE/MOOSE) simulation failures: classifies failure signatures (nonconvergence, NaN/Inf, exploding energy, unstable timestep, pressure blow-up, missing potentials/pseudopotentials, memory exhaustion, process crash/segfault, corrupted output, incomplete runs) and proposes a SAFE one-change-at-a-time RETRY LADDER with explicit STOP CONDITIONS, prioritizing evidence preservation. Use as the immediate first response to a failed or suspicious run. For deep per-stage validation, conservation/physical-bounds checks, and “can I trust these results” analysis, defer to the simulation-validator skill.
sqlite-vec extension for vector similarity search in SQLite. Use when storing embeddings, performing KNN queries, or building semantic search features. Triggers on sqlite-vec, vec0, MATCH, vec_distance, partition key, float[N], int8[N], bit[N], serialize_float32, serialize_int8, vec_f32, vec_int8, vec_bit, vec_normalize, vec_quantize_binary, distance_metric, metadata columns, auxiliary columns
Look up official SurrealDB Agent Memory (formerly Spectron) documentation from surrealdb.com as markdown: quickstarts, mental model, ingest, sessions, recall, reasoning, SDKs, framework integrations, MCP server, REST API, CLI, and configuration. Use when building with or answering questions about SurrealDB Agent Memory. Read-only; sends only search terms and doc paths.
Implements the Syncfusion WPF CheckedListBox (CheckListBox) control for multi-select lists with checkboxes. Use this when adding checklist controls, checkbox-enabled item lists, or SelectAll functionality in WPF applications. Covers data binding, appearance customization, grouping/sorting, item selection handling, and virtualization.
Create and manage WPF TabControl (TabControlExt) components for organizing content into tabs. Use this skill when users need to implement tabbed interfaces, manage tab selection, configure close buttons, handle tab interactions (clicking, keyboard navigation), customize tab appearance (orientation, placement), or bind tab data. Covers tab creation via XAML/C#, tab item management, event handling, context menus, drag-and-drop reordering, and theming.
Run vLLM performance benchmark using synthetic random data to measure throughput, TTFT (Time to First Token), TPOT (Time per Output Token), and other key performance metrics. Use when the user wants to quickly test vLLM serving performance without downloading external datasets.
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.