Loading...
Loading...
Found 1,254 Skills
Run an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the local wasm-agent runtime
Deep expertise in Hermes Agent architecture, implementation patterns, and extension development
AI-native software engineering harness. plugkit owns all state and serves every instruction via the spool. The agent dispatches verbs; plugkit tracks phase, mutables, PRD, and recall.
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocation.
Structure and organize Dagster code locations using dg. Use this skill when creating or migrating code locations, placing assets or sensors in the correct location, scaffolding new dg projects, or setting up the dg_projects/ workspace layout.
This skill is used when users provide one or more slide images, image-based PPT/PPTX or PDF files, and request conversion to editable PowerPoint/PPTX, reconstruction of slide objects, retention of page notes, or editable replication.
Orchestrate the UI team through the full UX pipeline: from UX spec authoring through visual design, implementation, review, and polish. Integrates with /ux-design, /ux-review, and studio UX templates.
Execute one role inside the loop CLI orchestrator. Use when the CLI asks you to act as planner, coding, or review agent and return strict handoff JSON while using loop-owned commands for Git integration.
Router and overview for the Cargo CLI agent skills. Explains the eleven skills (one outcome skill cargo-gtm + ten capability skills), the UUID flow between them, async polling, end-to-end use cases (enrich one record, enrich and sync to CRM, AI lead scoring, custom workflow, error monitoring, fresh-workspace bootstrap, segment export, GTM context authoring), and common gotchas (`conjonction` spelling, run vs batch, model-uuid vs segment-uuid). Load first whenever working with the Cargo CLI, when unsure which sub-skill applies, when stitching multiple sub-skills together, when bootstrapping a workspace, or when the user asks about Cargo skills in general.
Routes any game-development request to the right specialized skill(s): it detects the engine (Godot, Unity, Unreal, Bevy, Phaser, PixiJS, three.js, LÖVE, pygame, Roblox) and the task, then reads the chosen skill before acting. Use to make a game or to decide which skill applies — for players, levels, enemies, shaders, UI/UX, cameras, game feel, physics, input, audio, saving, multiplayer, AI, dialogue, procedural generation, or performance, for genres (platformer, roguelike, RPG, FPS, tower-defense, card game, visual novel, survival-crafting, puzzle), and for shipping (game jam, Steam, itch). Start here when unsure which gamedev skill to use.
Orchestrate Apex-backed Lightning Type + HXL widget generation. TRIGGER only when the prompt EXPLICITLY invokes Lightning Types: user says 'Lightning Type', 'CLT', 'Custom Lightning Type', 'Apex-backed type', references '@apexClassType/...', asks to build a widget or card for a named Lightning Type, asks to create a new Lightning Type and widget together, or grounds a widget in a specific Apex class as its schema. DO NOT TRIGGER when the prompt names only a subject, domain, feature, or entity noun. Also DO NOT TRIGGER when: authoring only a Custom Lightning Type (use platform-custom-lightning-type-generate), only an Apex class (use platform-apex-generate), editing an existing widget without any Lightning Type change, or grounding a widget on an object/JSON-based Lightning Type (lightning__objectType with primitives).
Vertical / parallel implementation planning skill. Creates DAG-structured plan directories where each step is an independent, QA-able vertical slice that sub-agents can pick up and implement in parallel. Use whenever the user wants a plan that fans out (multiple independent features), invokes /v-plan, or asks for a "parallel plan", "DAG plan", "vertical plan", or "plan that can be parallelized" — even if they don't say those exact words. Prefer the linear `planning` skill for strictly sequential work.