Handles ambiguous or high-impact coding work where missing artifacts, protected-surface changes, or unresolved implementation branches could materially change the implementation. Use for coding tasks that need artifact recovery, guarded clarification, or post-patch verification. Skip trivial, formatting-only, or already explicit single-path work.
Use when writing intimate or erotic scenes in fiction that require sensory completeness and narrative integrity (opt-in, requires --all flag to install)
Apply web animation principles from Animation at Work by Rachel Nabors. Covers human perception of motion, 12 principles of animation, animation patterns (transitions, supplements, feedback, demonstrations, decorations), CSS transitions, CSS animations, Web Animations API, SVG/Canvas/WebGL, communicating animation with storyboards and motion comps, performance (composite-only properties, will-change, RAIL), accessibility (prefers- reduced-motion, vestibular disorders), and team workflow. Trigger on "animation", "transition", "CSS animation", "keyframe", "easing", "motion design", "web animation", "prefers-reduced-motion", "storyboard", "parallax", "loading animation", "hover effect", "micro-interaction". --- # Animation at Work Skill You are an expert web animation advisor grounded in the 5 chapters from *Animation at Work* by Rachel Nabors. You help in two modes: 1. **Design Application** — Apply animation principles to create purposeful, performant web animations 2. **Design Review** — Analyze existing animations and recommend improvements ## How to Decide Which Mode - If the user asks to *create*, *add*, *implement*, *animate*, or *build* animations → **Design Application** - If the user asks to *review*, *audit*, *evaluate*, *optimize*, or *fix* animations → **Design Review** - If ambiguous, ask briefly which mode they'd prefer --- ## Mode 1: Design Application When helping create animations, follow this decision flow: ### Step 1 — Classify the Animation's Purpose Every animation must have a clear purpose. Classify using these five patterns: | Pattern | Purpose | When to Use | Example | |---------|---------|-------------|---------| | **Transition** | Show state change between views/states | Navigating pages, opening panels, switching tabs | Page slide-in, modal open/close | | **Supplement** | Bring elements into/out of a view that's already in place | Adding items to lists, showing notifications, revealing content | Toast notification slide-in, list item appear
Guides ACT-R cognitive model construction: chunk types, production rules, subsymbolic parameters, and model validation
Run agent definitions as sub-agents. Use when the user names an agent or sub-agent to run, references an agent definition, or delegates a task to an agent.
ALL interactions with ANY app — whether built-in (Finder, Safari, System Settings) or third-party (WeChat, Chrome, Slack) — MUST go through this skill. Clicking, typing, reading content, sending messages, navigating menus, filling forms: everything uses visual detection (screenshot → template match → click). This is the ONLY way to operate apps. Never bypass with CLI commands, AppleScript, or Accessibility APIs.
Domain context for delivery — feature completeness, shipped pipelines, defaults, and release coordination.
Drive the skvm CLI on behalf of a user to profile models, AOT-compile skills, run skill-assisted tasks, run benchmarks, and manage compiled proposals. Trigger when the user asks to "profile", "aot-compile", "bench", "run a skill", or asks about skvm proposals.
Structured code review checklist for the Reviewer agent. Provides a systematic framework for evaluating code changes across correctness, security, performance, and maintainability.
Audit a NousResearch/hermes-agent checkout or fork for Hermes-specific runtime-contract drift, command-surface splits, memory/skill/gateway health, and agent architecture risks. Uses the hermescheck Python library (hermescheck.report.v1) for structured reports with severity-ranked findings and code-first fix plans.
Author, read, debug, and modify Claude Code hooks — the user-defined shell commands, HTTP endpoints, or LLM prompts that run automatically at lifecycle events like PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit, and many more. Use this skill whenever the user mentions "hooks", "Claude Code hooks", a `.claude/settings.json` hooks block, auto-formatting on edit, blocking dangerous commands, Stop/PreToolUse/PostToolUse/SessionStart/etc., hook input JSON, `hookSpecificOutput`, `permissionDecision`, exit code 2 behavior, `CLAUDE_PROJECT_DIR` in hook scripts, or wants to guard, observe, or automate anything at a specific point in Claude Code's execution. Also use when the user asks to write a script that "runs before/after" a tool call, runs "when Claude finishes", or wants deterministic guardrails the model can't ignore.
Generic bioinformatics reproduction playbook for data discovery, execution planning, degradation, and auditable negative or partial results without paper-specific shortcuts.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
