Loading...
Loading...
Found 2,392 Skills
Single source of truth for linting/formatting across workspaces. Apply when setting up or modifying ESLint/Prettier configuration in multi-workspace projects.
Surgically updates a specific section of .marrow.md without re-running the full extraction. Accepts a new value, color, image, or description and patches only the relevant section — leaving everything else intact. Use this skill when the user wants to update one part of the extracted soul, change the brand accent color, update spacing rules, replace a typeface, refine the brand personality, or extract color from a new reference image. Triggers on: /marrow-update, or prompts like "update the accent color to X", "change the brand color", "update spacing in marrow", "the font changed to X", "update marrow with this new color", "patch marrow", "update just the accent", "marrow-update accent #FF6B6B", "update the palette from this image". Requires .marrow.md to exist. If not found, instructs user to run /marrow first.
Apply when building or debugging a VTEX IO session transform app (vtex.session integration). Covers namespace ownership, input-vs-output fields, transform ordering (DAG), public-as-input vs private-as-read model, cross-namespace propagation, configuration.json contracts, caching inside transforms, and frontend session consumption. Use when designing session-derived state for B2B, pricing, regionalization, or custom storefront context.
Create part assembly animations for SVG vector graphics with a strong sense of power and speed, and support one-click export of 30fps sequence frames with transparent background. It is suitable for scenarios where static SVG needs to be converted into transparent assets for video editing (such as AE/PR).
Review custom components and layouts against shadcn design patterns, theme styles (Maia, Vega, Lyra, Nova, Mira), component structure, composability, and Radix UI best practices. Use when planning new components, reviewing existing components, auditing spacing, checking component structure, or verifying shadcn best practices alignment.
Set up new project structure with seed file for research workspace. Use when the user wants to start a new project, create a project structure, initialize a new idea, or mentions starting something new.
Analyze the current workspace codebase and produce a single-file interactive C4 architecture diagram as HTML (L1 System Context → L2 Containers → L3 Components), with drill-down, breadcrumb, side panel, and light theme. Use when the user asks for C4 diagrams, interactive architecture HTML, system context/container/component views, or 可交互 C4 架构图. 分析当前项目代码结构，生成交互式 C4 架构图（单文件 HTML）：系统上下文、容器、组件三级下钻、面包屑、侧栏详情、浅色主题。触发词：C4 架构图、交互式架构、系统上下文、容器图、组件图、架构可视化、可下钻、architecture diagram、interactive C4。
Generate a resumable handoff document from an in-progress conversation, review, debugging session, or investigation. Dispatches co-located subagents to extract original instructions and Q&A context, capture evidence-backed insights, optionally validate claims from tracking files, and assemble a cold-start-ready handoff file plus structured working artifacts. Use when the user says "create a handoff doc", "save this for later", "document what we found", "update the resumption file", or wants a fresh agent to resume later without relying on chat history.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
Root-cause-driven solution decision framework for the hardest problems across any domain. This is the nuclear option — it consumes significant tokens through exhaustive multi-branch root cause analysis, MECE solution enumeration, and domain-adaptive external validation. Use ONLY for genuinely difficult problems: recurring failures that resist repeated fix attempts, complex systemic issues with no clear solution path, decisions where multiple approaches exist and the wrong choice has high cost, problems with multiple interacting causes spanning components or teams. Trigger when: the user says 'what's the best way to fix X', 'why does this keep happening', 'how should we approach this', 'find the root cause', 'what are my options for fixing X', 'analyze this problem systematically', 'evaluate our options for X', 'what's the right approach and why', or expresses frustration that previous solutions didn't stick. Do NOT use for: problems where the answer is already obvious or requires no analysis, straightforward issues with clear solutions, or routine investigation. If the problem can be solved in 5 minutes of investigation, this skill is overkill.
Claude Code skill that designs and builds high-converting questionnaire-style app onboarding flows modelled on proven conversion patterns from top subscription apps like Noom, Headspace, and Duolingo.
Unified wiki-history-ingest entrypoint for conversation/session sources. Use this when the user says "/wiki-history-ingest claude" or "/wiki-history-ingest codex", or asks to ingest agent history without naming the underlying skill. This router dispatches to the specialized history skill.