Loading...
Loading...
Found 2,021 Skills
Analyze project briefs to resolve architectural ambiguity before tech stack selection. Determines greenfield vs brownfield, platform constraints, integration requirements, scale expectations, and team context. Produces architecture-context.json for downstream skills.
Audits and auto-fixes a project's CLAUDE.md against Anthropic best practices. Activates during ship phase — checks conciseness, enforces @import structure for detailed docs, auto-excludes bloat, identifies hook candidates, and auto-fixes structural issues. Flags content questions for developer review.
Socratic discovery and design exploration before planning. Activates when starting non-trivial work — asks clarifying questions, explores alternatives and tradeoffs, produces a design document for approval. Pulls context from Linear issue description, linked docs, and existing CLAUDE.md learnings. Simple bugs and fixes skip this automatically.
Use when developing outgoing webhooks for applications and services.
Structured interactive learning assistant, used when users want to learn project-related knowledge, specific code files or underlying technologies. It records the learning process as persistent Markdown logs.
Use for high-stakes technical decisions, system design (Microservices/Monolith), cloud infrastructure, or generating ADRs/RFCs.
Generates a cross-referenced U.S. nonprofit annual filing package for state charity-bureau registration. Produces Full Compliance Package, Form-Field Mode, or Executive Briefing with source citations, disclosure cross-checks, and filing instructions. Trigger when the user drafts annual report submissions, renewal packets, penalty-of-perjury certifications, or charity bureau filings. Also trigger on Form RRF-1, CHAR500, BCO-10, nonprofit annual report, charity registration renewal, or fundraiser disclosure attachments.
Drafts the appellant's opening brief challenging a lower court decision in federal or state appellate courts. Covers issue selection, standard of review framing, record citation, argument structure, and procedural compliance under FRAP 28/32 or state equivalents. Use when preparing an appellant's opening brief, selecting appellate issues, structuring appellate arguments, or demonstrating reversible error on appeal.
Answer questions about OpenClaw's deployment, permissions, operation restrictions and troubleshooting across different platforms. It is applicable when users mention environment differences on macOS, Linux, Windows, iOS, Android or cloud platforms.
Generate videos from text and image prompts via Together AI. 15+ models including Veo 2/3, Sora 2, Kling 2.1, Hailuo 02, Seedance, PixVerse, Vidu. Supports text-to-video, image-to-video, keyframe control, and reference images. Use when users want to generate videos, create video content, animate images, or work with any video generation task.
Open a new context session at the start of a leader agent workflow. Records agentName, storyId, and phase in wint.contextSessions, emitting a structured SESSION CREATED block for downstream workers to inherit.
Guidance on **generation** and **implementation** of TinyVue component library code, used when analyzing, planning or generating components. This skill provides strict API constraints, search processes for documents and examples, as well as code specifications.