Enable, disable, and manage Claude Code skills. Use when the user asks to enable/disable/toggle/manage skills, check skill status, list skills, manage skill collections, or clean up the skills directory.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Manage personal skills and plugin skills from one CLI.
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py <command> [args]
| Command | Action |
|---|---|
list | Show all skills with status (enabled/disabled), source, description |
list --enabled | Only enabled skills |
list --disabled | Only disabled skills |
list --plugins | Only plugin skills |
disable <name> [name...] | Disable one or more skills (personal: moves to disabled/, plugin: flips settings.json) |
enable <name> [name...] | Enable one or more skills (reverse of disable) |
status <name> | Show details for a specific skill |
search <query> | Fuzzy match across all skill names and descriptions |
clean | Move orphan directories (no SKILL.md), zip files, and stale .sh scripts to disabled/orphans/ |
collection list | Show all collections with skill/plugin counts |
collection create <name> <skills...> | Define a new collection from explicit skill list |
collection save <name> | Snapshot all currently-enabled skills as a collection |
collection show <name> | List skills in a collection with current enabled/disabled status |
collection on <name> | Enable all skills in the collection |
collection off <name> | Disable all skills in the collection |
collection delete <name> | Remove a collection definition |
collection add <name> <skills...> | Add skills to existing collection |
collection remove <name> <skills...> | Remove skills from existing collection |
Personal skills: Moved between ~/.claude/skills/<name>/ (enabled) and ~/.claude/skills/disabled/<name>/ (disabled). The disabled/INDEX.md is auto-regenerated after every operation.
Plugin skills: The enabledPlugins object in ~/.claude/settings.json is toggled. Accepts both plugin names (compound-engineering) and namespaced skill names (compound-engineering:deepen-plan)—the skill suffix is stripped and the entire plugin is toggled either way.
Collections: Named groups of skills stored as JSON in ~/.claude/skills/skill-toggle/collections/. Each collection lists personal skills and/or plugins that can be toggled as a unit. collection on research enables everything in the research collection; collection off research disables them. Collections are additive—turning one on only enables its skills, it doesn't disable anything outside the collection. Use collection save to snapshot your current enabled set.
# Disable two personal skills
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py disable smolvlm llama-cpp
# Enable a previously disabled skill
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py enable webflow-migrate
# Disable a plugin (all its skills go with it)
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py disable agent-evaluation
# List only what's currently disabled
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py list --disabled
# Clean orphan dirs and zip files
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py clean
# Create a named collection of skills
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py collection create research academic-research ancient-near-east-research rlama exa-search linear-a-decipherment
# Snapshot all currently-enabled skills as a collection
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py collection save baseline
# Disable all skills in a collection at once
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py collection off research
# Re-enable a collection
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py collection on research
# Show what's in a collection with current status
python3 ~/.claude/skills/skill-toggle/scripts/skill_toggle.py collection show research
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Search academic papers, build literature reviews, and synthesize research findings — combines Exa MCP (research_paper category, arxiv filtering) with arxiv-mcp-server for paper discovery, download, and deep analysis. Triggers on academic paper, literature review, research synthesis, arxiv, find papers, scholarly search.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
This skill should be used when creating, auditing, or maintaining AGENTS.md files and Codex CLI configuration for any project—including initializing AGENTS.md for cross-agent compatibility (Codex, Cursor, Copilot, Devin, Jules, Amp, Gemini CLI), generating config.toml or .rules files, scaffolding .agents/skills/, converting CLAUDE.md to AGENTS.md, or auditing existing agent configs for bloat and staleness. Complementary to codex-orchestrator (which executes subagents; this skill creates the config files they consume).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Academic research skill for Biblical Hebrew, Semitic linguistics, cuneiform studies, and comparative Ancient Near Eastern research. Provides Sefaria API for Hebrew Bible, CDLI/ORACC for cuneiform databases, and web discovery via Omnisearch, Exa, Firecrawl, and Obscura for finding scholarly sources across JSTOR, Perseus, Persée, Google Scholar, and academia.edu. Triggers on Hebrew quotes, cuneiform, Sefaria, ANE research, Minoan, search for scholarship, find papers, literature review, scholarly search, academic search, Genesis/Tehom, Ugaritic, Talmudic sources, extract from PDF, OCR academic.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build comprehensive ARCHITECTURE.md files following matklad's canonical guidelines — bird's-eye views, ASCII/Mermaid diagrams, codemaps, invariants, and layer boundaries. Triggers on document the architecture, create ARCHITECTURE.md, map this codebase, architectural overview.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generate physically-based atmospheric scattering shaders — sky domes, planetary atmospheres, LUT-optimized pipelines, depth-aware post-processing. Four modes — sky-dome, atmosphere-post, planet, lut. Triggers on atmospheric scattering, sky shader, sunset rendering, planet atmosphere, Rayleigh scattering, Mie scattering, volumetric sky, sky dome, atmosphere post-processing, aerial perspective, transmittance LUT, sky rendering, realistic sky, planetary rendering.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.