Use when deciding whether a completed AnthroClaw run should become durable memory or a reusable native skill update. Helps convert user corrections, repeated workflows, and recovered mistakes into safe learning proposals.
Traces failures from observed symptoms to the first incorrect state transition.
Experimental working-model protocol shipped with memesh v4.1. Status — protocol present + instrumented; effectiveness in real usage is being collected (see `memesh patterns`), not yet proven. Suggests a user-as-CTO / Claude-as-orchestrator / background-agents-as-engineers split. Claude routes work by verifiability, dispatches parallel background agents for high-verifiability technical work, and stays foreground only for strategic/understanding work that the user must own. Use as a default for non-trivial software tasks; report back when it helps or doesn't.
>-
Use token-efficient CLI patterns instead of verbose MCP output when direct shell tools are enough. Provides JSON or compact-output conventions for gh, mgrep, psql, and similar tools.
Compose an arrangement for a tape — plan which elements enter and exit over time, then generate a playable CCArrangement.
Perform a self-review of a PR before requesting human review. TRIGGER when user invokes /pr-selfcheck or when the git workflow reaches the self-review step after PR creation. Accepts a PR number as an argument.
>-
Dashboard-style snapshot of overall WP Umbrella fleet health in one call — totals of sites down, pending updates, vulnerabilities, outdated WordPress, unsupported PHP. Invoke as /umbrella:health.
Writes Python code following FiftyOne's official conventions. Use when contributing to FiftyOne, developing plugins, or writing code that integrates with FiftyOne's codebase.
Use when an agent needs the smallest useful eval pack to catch regressions or false confidence early.
Converts webpages, articles, or documents into study flashcards that you can review with spaced repetition
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:
