manage-skills
Discover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment)
What this skill does
# Manage AI Agent Skills You can manage skills and rules for all major AI coding tools directly from the terminal. This skill teaches you the directory layout, file format, and operations for each tool. ## When to Use Use this skill when the user wants to inspect, create, edit, enable, disable, copy, move, or delete local AI-agent skills or rule files across supported coding tools. ## Supported Tools & Paths ### Directory-based tools (multiple skills) Each skill lives in its own subdirectory with a `SKILL.md` file containing YAML frontmatter. | Tool | Global Path | Project Path | |------|------------|--------------| | Agents | `~/.agents/skills/<name>/SKILL.md` | `.agents/skills/<name>/SKILL.md` | | Cursor | `~/.cursor/skills/<name>/SKILL.md` | `.cursor/skills/<name>/SKILL.md` | | Claude | `~/.claude/skills/<name>/SKILL.md` | `.claude/skills/<name>/SKILL.md` | | Windsurf | `~/.windsurf/rules/<name>/<name>.md` | `.windsurf/rules/<name>/<name>.md` | | Cline | `~/.cline/rules/<name>/<name>.md` | `.cline/rules/<name>/<name>.md` | | Continue | `~/.continue/rules/<name>/<name>.md` | `.continue/rules/<name>/<name>.md` | | Roo Code | `~/.roo/rules/<name>/<name>.md` | `.roo/rules/<name>/<name>.md` | ### Single-file tools (one config file) | Tool | Global Path | Project Path | |------|------------|--------------| | Copilot | `~/.github/copilot-instructions.md` | `.github/copilot-instructions.md` | | Codex | `~/.codex/AGENTS.md` | `.codex/AGENTS.md` | | Aider | `~/.aider.conf.yml` | `.aider.conf.yml` | | Augment | `~/augment-guidelines.md` | `augment-guidelines.md` | ### Cursor plugins (read-only) Plugin skills are cached at `~/.cursor/plugins/cache/<org>/<plugin>/<version>/skills/<name>/SKILL.md`. These are managed by Cursor and should not be edited directly. ## Skill File Format For directory-based tools (Agents, Cursor, Claude), skills use YAML frontmatter: ```markdown --- name: skill-name description: Brief description of what this skill does --- # Skill Name Skill instructions go here. The AI agent reads this content when the skill is activated. ``` For Windsurf, Cline, Continue, and Roo Code, skills are plain `.md` files (frontmatter optional). ## Operations ### List all skills ```bash # List skills for a specific tool ls ~/.agents/skills/ ls ~/.cursor/skills/ ls ~/.claude/skills/ ls ~/.windsurf/rules/ ls ~/.cline/rules/ ls ~/.continue/rules/ ls ~/.roo/rules/ # Count total skills across all tools echo "Agents: $(ls ~/.agents/skills/ 2>/dev/null | wc -l | tr -d ' ')" echo "Cursor: $(ls ~/.cursor/skills/ 2>/dev/null | wc -l | tr -d ' ')" echo "Claude: $(ls ~/.claude/skills/ 2>/dev/null | wc -l | tr -d ' ')" echo "Windsurf: $(ls ~/.windsurf/rules/ 2>/dev/null | wc -l | tr -d ' ')" echo "Cline: $(ls ~/.cline/rules/ 2>/dev/null | wc -l | tr -d ' ')" echo "Continue: $(ls ~/.continue/rules/ 2>/dev/null | wc -l | tr -d ' ')" echo "Roo: $(ls ~/.roo/rules/ 2>/dev/null | wc -l | tr -d ' ')" # Check single-file tools test -f ~/.github/copilot-instructions.md && echo "Copilot: exists" || echo "Copilot: not found" test -f ~/.codex/AGENTS.md && echo "Codex: exists" || echo "Codex: not found" test -f ~/.aider.conf.yml && echo "Aider: exists" || echo "Aider: not found" test -f ~/augment-guidelines.md && echo "Augment: exists" || echo "Augment: not found" ``` ### Read a skill ```bash cat ~/.cursor/skills/my-skill/SKILL.md ``` ### Create a new skill ```bash # For Agents/Cursor/Claude (SKILL.md format) mkdir -p ~/.agents/skills/my-new-skill cat > ~/.agents/skills/my-new-skill/SKILL.md << 'EOF' --- name: my-new-skill description: What this skill does --- # My New Skill Instructions for the agent go here. EOF # For Windsurf/Cline/Continue/Roo (plain .md format) mkdir -p ~/.windsurf/rules/my-new-rule cat > ~/.windsurf/rules/my-new-rule/my-new-rule.md << 'EOF' # My New Rule Instructions go here. EOF # For single-file tools cat > .github/copilot-instructions.md << 'EOF' Instructions for Copilot go here. EOF ``` ### Enable / Disable a skill Disabling renames the file to `.disabled` so the tool ignores it but the content is preserved: ```bash # Disable mv ~/.cursor/skills/my-skill/SKILL.md ~/.cursor/skills/my-skill/SKILL.md.disabled # Enable mv ~/.cursor/skills/my-skill/SKILL.md.disabled ~/.cursor/skills/my-skill/SKILL.md ``` ### Copy a skill between tools ```bash # Copy from Cursor to Claude cp -r ~/.cursor/skills/my-skill ~/.claude/skills/my-skill # Copy from Agents to Windsurf (adapt format) mkdir -p ~/.windsurf/rules/my-skill cp ~/.agents/skills/my-skill/SKILL.md ~/.windsurf/rules/my-skill/my-skill.md ``` ### Move a skill ```bash mv ~/.cursor/skills/my-skill ~/.agents/skills/my-skill ``` ### Delete a skill ```bash rm -rf ~/.cursor/skills/my-skill ``` ### Copy a skill from global to project scope ```bash cp -r ~/.cursor/skills/my-skill .cursor/skills/my-skill ``` ### Search across all skills ```bash # Search by name find ~/.agents/skills ~/.cursor/skills ~/.claude/skills ~/.windsurf/rules ~/.cline/rules ~/.continue/rules ~/.roo/rules -maxdepth 1 -type d 2>/dev/null | sort # Search by content grep -rl "search term" ~/.agents/skills/ ~/.cursor/skills/ ~/.claude/skills/ 2>/dev/null ``` ### Find disabled skills ```bash find ~/.agents/skills ~/.cursor/skills ~/.claude/skills -name "*.disabled" 2>/dev/null ``` ## Guidelines - When the user asks to "manage skills", "list my skills", "create a skill", "copy a skill to X", or similar, use the paths and formats above. - Always confirm before deleting skills. - When copying between tools with different formats (e.g., Cursor SKILL.md to Windsurf plain .md), adapt the file naming accordingly. - Project-scoped skills override global skills of the same name. - For single-file tools (Copilot, Codex, Aider, Augment), editing means replacing the entire file content. - When creating skills, use kebab-case for directory names (e.g., `my-new-skill`). ## Limitations - Use this skill only when the task clearly matches the scope described above. - Do not treat the output as a substitute for environment-specific validation, testing, or expert review. - Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.