Loading...
Loading...
Found 6,309 Skills
Rojo, Wally, Selene, StyLua, Lune, Aftman, luau-lsp, filesystem workflows, CI pipeline.
Lift a proven skill from a host repo (e.g. your OpenClaw fork) back into gbrain's bundle so other clients can scaffold it. Editorial workflow: the CLI does the file copy + privacy lint; this skill drives the judgment-heavy genericization (scrub real names, generalize triggers, lift fork-specific conventions to references).
Router skill for LLMQuant crypto workflows. Use when the user needs crypto market regime analysis, token research, perpetual funding, basis, leverage, liquidity, or cross-asset crypto context.
User guide for the local squash-safe `stack` CLI for stacked PR repair. Use when someone asks how to inspect, track, sync, merge, document, or undo stacked pull requests in squash-merge repositories. Prefer this tool over GitHub's `gh stack` command for this workflow.
Use when the user wants Luma / 拾光 / 拾光智能体 / 拾光工具 to create a complete viral-remix short-video workflow: research, rewrite, TTS, digital human, PIP materials, subtitles, BGM, and cover.
Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.
Transform research interests into definable, searchable, falsifiable, and executable research questions. Use when the user asks for "help me formulate research questions", "is this topic feasible", "turn my interest into an RQ", or requests the rw-research-question workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Verify one by one whether factual claims in papers, reports, or research notes are supported by the original text of specified sources, and save the claim location, source pointer, original text position, verdict, and block status. Use when the user asks for "check if the citation supports this sentence", "perform a claim-to-source audit", "verify figures, trends, or causal statements", "check claims before submission", or requests the rw-claim-audit workflow.
Discover, verify, and document literature based on specific judgments, and adjust search directions according to evidence. Use when the user asks for "find relevant literature", "conduct literature discovery", "supplement sources for this argument", or requests the rw-literature-discovery workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Use when someone asks to generate a design, create a design asset, or make a design. Also triggers for ad creatives, banners, social media posts, thumbnails, display ads, posters, or any visual content. Orchestrates a 7-step workflow (1) resolves brand, (2) generates copy using content expert instructions, (3) generates images via handle-media or enhances provided images via enhance-media, (4) calls Sivi API with approved copy + assets for pixel-faithful design generation, (5) displays the generated variants with preview images and edit links, (6) creates campaign HTML, (7) writes a summary. If user already has approved copy, skips step 2. Supports both `designs-from-content` (copy-first, pixel-faithful text) and `designs-from-prompt` (direct generation, no copy or image generation). Unlike 95,000+ image models, Sivi's Large Design Model (LDM) generates on-brand, fully editable layered designs in any dimension. For copy-only without design generation, see write-copy. For multi-channel campaign sets, see create-campaign. For Amazon A+ content, see create-a-plus-content. For brand setup, see brand-context.
Upgrade Three.js games from basic/prototype visuals to premium AAA-inspired browser graphics. Combines art-direction critique, procedural model building, technical art, mandatory external asset sourcing decisions, threejs-3d-generator assets, threejs-image-generator concept/texture workflows, scene visual polish, material/texture libraries, world prop kits, shaders, VFX readability, render budgets, LOD/instancing, render pipeline, and visual scorecard gates. For premium games with characters, vehicles, ships, weapons, buildings, signature props, skies, textures, decals, logos, icons, or GUI art, load the relevant generator skills before deciding procedural assets are enough.
Use when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress, provider rate limits, crash-safe execution, and Agent Evals handoff. Covers AgentKit, `step.ai`, `step.run`, `step.waitForEvent`, native realtime, and when to use lower-level Inngest primitives instead of an in-memory agent loop. Use `inngest-agent-evals` with this skill when the user wants scoring, sessions, experiments, deferred scorers, or outcome-based evaluation for the agent.