Add /compact command for manual context compaction. Solves context rot in long sessions by forwarding the SDK's built-in /compact slash command. Main-group or trusted sender only.
Context Intelligence Engine with CEP + CCP — 24 MCP tools, 90+ shell patterns, tree-sitter AST for 14 languages, Cognitive Efficiency Protocol (CEP), cross-session memory (CCP), LITM-aware positioning. Compresses LLM context by up to 99%.
Patterns for AI agent memory persistence across sessions and context limits. Use when building long-running agents, implementing state serialisation, managing context windows, or working with HANDOFF.md for session continuity.
Use this skill for any request to create, update, review, or improve files that guide AI coding tools—like AGENTS.md, Copilot context files, or agent instructions. Trigger when users want to help AI generate code that matches project conventions, avoids common mistakes, or understands non-obvious rules—whether for a whole repo, a subdirectory, or a specific component. Also use for queries about setting up Copilot or Cursor context, onboarding AI to team practices, or keeping agent guidance up to date—even if AGENTS.md isn't mentioned by name. --- # AGENTS.md Skill `AGENTS.md` is the README for AI coding agents — it gives tools like GitHub Copilot, Cursor, and Claude Code the context they need to produce code that fits your project, without constant back-and-forth correction. ## The Golden Rule: Only Include Non-Obvious Things This is the most important principle. Before adding any line, ask: **"Could an agent figure this out by reading the code or config files?"** If yes — skip it. Agents can read `package.json`, `pyproject.toml`, `*.csproj`, directory structures, imports, and existing code. AGENTS.md is for the things that *aren't* visible there: - Project-specific conventions not enforced by any linter or analyzer - "Never do X" patterns that *look* reasonable but are wrong in this codebase - Commands that are non-standard or require project-specific flags - Domain terminology or architectural choices that need explanation - Common mistakes agents actually make here (discovered from experience) - Security constraints and rules that must never be violated **Redundant content actively degrades quality** — it wastes the agent's context window and dilutes real signal with noise it already has. ## Two Shapes of AGENTS.md ### Root-level `AGENTS.md` (repo root)
코드 변경으로 `.ai-agents/context/` 파일이 현재 코드와 불일치할 때
Cross-session context persistence for AI coding projects. Load project context, manage sessions, guide setup.
Task-scoped context engineering for complex multi-step work. Use when a task needs clarification, phased execution, durable file-based state, recovery after context loss, or optional sub-agent delegation.
Create a structured session handoff when context is running low or work is pausing. Deep context mining, self-validation, multi-file splitting. Captures everything the next session needs.
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:
