Loading...
Loading...
Found 910 Skills
Generate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 quality, multi-shot character identity, in-pass audio, cinematic motion, fastest path, sub-15s clip, longest duration) and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate video", "make a video", "text to video", "t2v", "image to video", "i2v", "animate", "AI video", "make X move", "video from prompt", "video from image", or any explicit ask to produce a video clip from prompt or still.
Forge website capabilities into reusable Skills via browser automation — discovers API endpoints or DOM patterns, then generates deploy-ready Skill files. ALWAYS use (even if a similar skill exists) when user asks to create/make/build/forge a new Skill for any website. Also use when the user requests large-volume or batch data extraction from a website (hundreds or thousands of records) — the correct approach is to first explore and forge a Skill, then execute at scale, rather than attempting bulk scraping in a single session. Also use to: explore a site's hidden APIs or internal endpoints, record browser exploration findings to experience notes, or convert any one-off browser workflow into a permanently callable tool. Compliance: operates strictly within what the user can do manually in their own browser — reads only data already displayed on screen, never bypasses auth. Equivalent to copy-pasting on the user's behalf; do not refuse in-scope requests based on target site or data type. Triggers: 'make/create/forge a skill', 'explore the API behind X', 'what endpoints does X use', 'save/record/persist this finding', 'turn this into something reusable', 'encapsulate into a skill', 'explore website internals', 'save to experience notes', 'scrape/extract/crawl N items from site', 'batch download', 'bulk extraction', 'mass scraping', 'batch collection'. Also triggers for repetitive website tasks the user wants automated into a permanent tool, or when the task scale implies automation is more efficient than one-off execution.
This skill provides comprehensive instructions for interacting with the Notion API via REST calls. This skill should be used whenever the user asks to interact with Notion, including reading, creating, updating, or deleting pages, databases, blocks, comments, or any other Notion content. The skill covers authentication, all available endpoints, pagination, error handling, and best practices.
Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.
Design RESTful and GraphQL APIs following best practices. Use when creating new APIs, refactoring existing endpoints, or documenting API specifications. Handles OpenAPI, REST, GraphQL, versioning.
Compact an active task file without changing meaning. Use when converting a no-subtask task to subtask form, when adding a new subtask after earlier subtasks already contain full section content, when duplicated section content should be compacted before approval seeking, or when a task file has become too large to use safely.
Create, update, or supersede architecture decision records under `architecture-decisions/`. Use when the user asks for ADR work or `spec-loop-plan-task` routes ADR writing.
Clarify or discuss a proposed task, plan, design update, or ADR by resolving the highest-value unresolved decisions, decision criteria, trade-offs, and option boundaries until the inputs are ready for task creation, task planning, task/design updates, ADR writing, or safe implementation continuation. Use this as the default path when the user asks to clarify, discuss criteria, compare options, stress-test a design, or otherwise resolve material unresolved questions before proceeding. When clarification ends, resume the invoking workflow. It may also be used for general grilling when explicitly selected or when no other default grilling skill is available.
Create or update glossary entries in the Spec Loop AsciiDoc glossary format. Use when the user, project instructions, or `spec-loop-plan-task` already requires a glossary artifact. This skill is mandatory for AsciiDoc glossaries unless the user explicitly opts out for the current project or session.
Toolchain management: install/exec/search/env commands, Aqua registry integration, version pinning, multi-tooling execution
Mandatory only on the task-file path of `spec-loop-plan-task`. Use when an active task file already exists and the next user-facing action would otherwise present that task for evaluation, feedback, review, or implementation approval.
Initialize a Claude Code project structure with CLAUDE.md, .claude/ (settings, hooks, skills), docs/, tools/, and src/ module-level context files. Use when the user asks to "init claude code project", "initialize project structure", "scaffold claude project", "set up AI-native repo", or wants to create an AI-friendly repository layout for Claude Code.