Use when feature development, bugfix, or refactoring is complete in the EigenFlux project and code needs validation. Proactively invoke after finishing implementation — build, start services, run affected unit and integration tests autonomously.
Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).
Deep code scan for AI security issues — prompt injection, PII in prompts, hardcoded keys, unguarded agents.
Use when running demo recordings, diagnosing recording failures, or regenerating GIFs from existing MP4s. Covers the Docker + VHS + ffmpeg pipeline. --- # VHS Demo Recording Use this skill to run, debug, or regenerate gh-infra demo GIF recordings. ## When To Use - Running `make demo` or `docs/tapes/vhs.sh` directly - Diagnosing why a recording failed or produced a 0-byte GIF - Regenerating GIFs from existing MP4s without re-recording - Understanding the recording pipeline ## Prerequisites - Docker must be running - Go toolchain (for cross-compiling the Linux binary) ## Pipeline ```text make demo 1. go build -o docs/tapes/.gh-infra (GOOS=linux GOARCH=amd64) 2. docs/tapes/vhs.sh a. docker build → gh-infra-vhs image (VHS + vim) b. For each *.tape in parallel: docker run --memory=1g --cpus=2 → produces .mp4 c. For each .mp4 sequentially: docker run jrottenberg/ffmpeg:7-alpine → produces .gif 3. Copy GIFs to docs/public/ 4. Clean up .gh-infra binary ``` ## Why MP4 → GIF Instead of Direct GIF VHS's built-in GIF output is unreliable when multiple containers run in parallel on macOS. The workaround is to output MP4 only from VHS, then convert to GIF via ffmpeg with high-quality settings (lanczos scaling, sierra2_4a dithering, 256 colors). ## Key Files | File | Role | |------|------| | `docs/tapes/vhs.sh` | Orchestrator: parallel recording + sequential GIF conversion | | `docs/tapes/Dockerfile` | `ghcr.io/charmbracelet/vhs` + vim | | `docs/tapes/*.tape` | VHS scenario files | | `docs/tapes/setup*.sh` | Per-demo setup scripts (mock data, gh wrapper) | | `docs/tapes/mock-gh` | Generic mock for `gh` CLI | | `docs/tapes/.gh-infra` | Cross-compiled Linux binary (ephemeral) | ## Output Locations - Raw recordings: `docs/tapes/*.mp4` and `docs/tapes/*.gif` - Published assets: `docs/public/demo*.gif` (copied by Makefile) ## Environment Variables `make demo` forwards `DEMO_ENV` variables into Docker via `-e` flags. Use this to pass environment overrides (e.g. `GH_INFRA_OUTPUT`) into
Native Rust browser automation CLI for AI agents. Use when the user needs to interact with websites — navigating pages, filling forms, clicking buttons, taking screenshots, extracting structured data, running assertions, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", "visual regression test", "check for prompt injection", or any task requiring programmatic web interaction.
React DevTools CLI for AI agents. Use when the user asks you to debug a React or React Native app at runtime, inspect component props/state/hooks, diagnose render performance, profile re-renders, find slow components, or understand why something re-renders. Triggers include "why does this re-render", "inspect the component", "what props does X have", "profile the app", "find slow components", "debug the UI", "check component state", "the app feels slow", or any React runtime debugging task.
Academic writing, research methodology, and scholarly communication workflows. Use when writing papers, literature reviews, grant proposals, conducting research, managing citations, or preparing for peer review. Essential for researchers, graduate students, and academics across disciplines.
name = "context-optimize"
Install or enable Secure Claude Code with the recommended balanced baseline.
Design and build websites with film-inspired visual systems, director-driven art direction, storyboard-first layout planning, and cinematic motion. Use when the user asks for a cinematic site, movie-style landing page, director-inspired UI, film-noir, sci-fi, romance, thriller, action, animation, or a movie-like website aesthetic, including requests phrased in Chinese. Do not use for generic web design unless the user explicitly wants a film or director reference.
Use when running promptminder or promptminder-agent commands, setting PROMPTMINDER_TOKEN, passing --team for workspace scoping, handling JSON stderr errors like "Missing token" or HTTP 401, or using the agent wrapper with dot-notation actions and --input JSON.
Transform messy prompts into structured, effective prompts — single, multi-agent, or reverse-engineered from great outputs.
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:
