Showing 32011–32040 of 77205 skills
Use when writing PlayCanvas Engine code touching transforms, cameras, lights, materials, meshes, bounds, or imports, to apply Engine conventions and avoid legacy APIs.
playcanvas/skills
Use when composing PlayCanvas entity hierarchies from models, colliders, rigid bodies, and scripts, so each object has one semantic root and clear lifecycle.
playcanvas/skills
Use when static PlayCanvas lighting, shadows, or ambient occlusion cost too much per frame and should be baked into lightmaps.
playcanvas/skills
Use when creating or restructuring a PlayCanvas app with the Engine API, @playcanvas/react, or @playcanvas/web-components, covering bootstrap, input, resize, physics, update loop, UI, and lifecycle.
playcanvas/skills
Use when lighting or rendering a PlayCanvas scene, covering lights, ambient and environment lighting, sky, shadows, tone mapping, exposure, fog, and post-processing.
playcanvas/skills
Use when a PlayCanvas StandardMaterial needs custom shading its properties cannot express, such as stylized looks or vertex displacement, before writing a ShaderMaterial.
playcanvas/skills
Use when a PlayCanvas app has too many draw calls or is CPU-bound, before hand-merging meshes or writing custom renderers.
playcanvas/skills
Use when a PlayCanvas rendering change is meant to leave the image unchanged, to prove it with deterministic captures and pixel comparison.
playcanvas/skills
Evidence-backed agentic image-prompt engineering skill for GPT Image 2. Converts plain-language visual requests and optional reference images into coherent production prompts using explicit locks, reference-role isolation, temporal-cultural evidence, art/craft/material reasoning, visual direction, compatibility audits, regression checks, evaluation, and surgical revision. Prompt generation is the primary output; image generation is optional.
PaladinKnightMaster/ai-image-prompt-factory
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
full-stack-skills/tauri-skills
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
full-stack-skills/tauri-skills
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
full-stack-skills/tauri-skills
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
full-stack-skills/tauri-skills
Use when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery.
MemTensor/skills-vote
Use when: 需要检查 super-pm 技能包安装完整性、元数据和体积 Do NOT use when: 正在执行具体 PM 任务且不需要安装诊断
konglong87/superPM
Launch planning workflow — chain risk assessment, cross-team coordination, agile delivery, and release planning Use when: Preparing for a product launch, release, or go-live
konglong87/superPM
Use whenever the user asks to "humanize", "make this sound more human", "rewrite to avoid AI detection", "make this less AI-sounding", "add a human voice", or "write like a person". Also use when the user pastes text and asks why it reads as robotic, generic, flat, or AI-like, or when generating new text in a register where AI tells (em dashes, semicolons, hedges, banned vocabulary like "delve", "leverage", "robust") would damage credibility.
harshaneel/humanize
Use when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by position; gating degraded results; and disclosing tool substitutions, in any language.
antonbabenko/agent-plugins
pedrohcgs/claude-code-my-workflow
Use when code needs a judgment about natural language that rules or regex cannot make (classify, route, triage, moderate, score, rank, match, dedupe, filter, extract, verify, or gate an action), when brainstorming where AI could fit in an app, when an LLM call exists only to pick a label, score, or yes/no, or when code uses TypeSafe AI, Jev, System One, typesafe-sdk, or @typesafe-ai/sdk.
aaddrick/building-with-typesafe-jev
审计自上次发版以来的提交,把遗漏的「用户可见变更」补进 CHANGELOG.md 的 [Unreleased];可选地把 [Unreleased] 收口成正式版本节
maotoumao/Cebian
Resume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md.
maotoumao/Cebian
Conventions for writing justfile recipes in Nix-based projects.
srid/drishti
Sets up a complete skill stack for the user's kind of work with one of Alyn's curated bundles (design, engineering, startup founder, writing, SEO and GEO, marketing, office documents, video, token saving). Use when the user asks which skills to install, wants to set up Claude Code, Cursor or Codex for a role, says "set me up for design" or similar, or is new to agent skills.
tammo1007/alyn
A relentless interview to sharpen a plan or design.
Authula/authula
<What it does and when to use it, in one or two sentences. This is what an agent matches on. At most 1,024 characters.>
gooseworks-ai/goose-skills
Inspect an application or project's latest Knowledge Graph existence, synthesize living Markdown architecture documentation and Mermaid FlowDiagram, and link them to the KGraph documentation package.
nddipiazza/robos
Remove a node from the Knowledge Graph and optionally prune cascading references across dependent nodes.
nddipiazza/robos
Insert or register a new architectural node (Microservice, Database, MessageBroker, App, etc.) into the Knowledge Graph with W3C SHACL shape validation gate.
nddipiazza/robos
Search Knowledge Graph nodes across all packages by text query, RDF type, owner team, or tags.
nddipiazza/robos