- 📄 SKILL.md
follow-manager
Manage your follow list — add/remove X users, YouTube channels, keywords to track for knowledge building.
Manage your follow list — add/remove X users, YouTube channels, keywords to track for knowledge building.
Build and maintain a project-serving knowledge base inside the current project's `.project-knowledge/` directory. Use when Codex should initialize a project knowledge base, inspect current project knowledge status, rebuild the project knowledge graph, or crystallize stable knowledge from the current task into project-local Markdown.
Core ComfyUI knowledge — workflow format, node types, pipeline patterns, and MCP tool usage
Save a URL with an auto-generated summary to the knowledge base
Authoring discipline for Spandrel knowledge graphs — surfaces /patterns/authorship, /hypothesis, and the audit heuristics when editing graph content (nodes, descriptions, link descriptions). References canonical knowledge in the graph rather than hardcoding it. Auto-load when editing markdown with Spandrel frontmatter, or when authoring/auditing any Spandrel knowledge graph content.
Converts documents and knowledge gathered from Microsoft Copilot into well-structured, SharePoint-compatible markdown files. Use when a user has content from Copilot (summaries, research, meeting notes, process steps) and wants to produce a formatted page for a SharePoint site, wiki, or knowledge base. Triggers include "create a markdown file from this", "format this for SharePoint", "write this up as a knowledge base article", "turn this Copilot output into a page", or when a user pastes Copilot-generated content and asks for it to be documented.
Search the Claude knowledge graph vault for past Q&A sessions, concepts, and developer knowledge. Use when you need to find information from previous conversations, recall how something was done before, or look up stored technical knowledge. Supports Korean and English queries.
xiReactor Brilliant Knowledge Base assistant — manages sessions, daily notes, content routing, search, browsing, governance, and meeting intelligence via MCP. Use when the user asks about organizational knowledge, needs to look something up, wants to create or update KB content, says "resume", "compress", "daily", "search", or when you need institutional context.
Capture a specific piece of knowledge, constraint, or decision to the Kindex knowledge graph. Use when the user says "remember this", "add this to kindex", or "this is important".
Query, store, or inspect cross-project knowledge in the Shared Brain (Notion + local SQLite mirror). Use when user says '/brain', 'brain query', 'brain store', 'brain show', 'check the brain', or wants to search/save knowledge across projects.
Use when Claude makes repeated mistakes, users correct behavior, tool failures indicate missing knowledge, or managing learning via /coach commands.
Use when user says "update/refresh knowledge graph", "graph status", "blind spots", "CLAUDE.md coverage", or "init knowledge graph". Also use when receiving a "[kg auto-trigger]" message injected by hooks. Do not use for regular coding tasks.
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: