agent-registry
MANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill instead of loading agents directly from ~/.claude/agents/ or .claude/agents/. Provides lazy loading via search_agents and get_agent tools. Use when: (1) user task may benefit from specialized agent expertise, (2) user asks about available agents, (3) starting complex workflows that historically used agents. This skill reduces context window usage by ~95% compared to loading all agents upfront.
What this skill does
# Agent Registry Lazy-loading system for Claude Code agents. Eliminates the "~16k tokens" warning by loading agents on-demand. ## CRITICAL RULE **NEVER assume agents are pre-loaded.** Always use this registry to discover and load agents. ## Workflow ``` User Request → search_agents(intent) → select best match → get_agent(name) → execute with agent ``` ## Available Commands | Command | When to Use | Example | |---------|-------------|---------| | `list_agents.py` | User asks "what agents do I have" or needs overview | `python scripts/list_agents.py` | | `search_agents.py` | Find agents matching user intent (ALWAYS do this first) | `python scripts/search_agents.py "code review security"` | | `search_agents_paged.py` | Paged search for large registries (300+ agents) | `python scripts/search_agents_paged.py "query" --page 1 --page-size 10` | | `get_agent.py` | Load a specific agent's full instructions | `python scripts/get_agent.py code-reviewer` | ## Search First Pattern 1. **Extract intent keywords** from user request 2. **Run search**: `python scripts/search_agents.py "<keywords>"` 3. **Review results**: Check relevance scores (0.0-1.0) 4. **Load if needed**: `python scripts/get_agent.py <agent-name>` 5. **Execute**: Follow the loaded agent's instructions ## Example User: "Can you review my authentication code for security issues?" ```bash # Step 1: Search for relevant agents python scripts/search_agents.py "code review security authentication" # Output: # Found 2 matching agents: # 1. security-auditor (score: 0.89) - Analyzes code for security vulnerabilities # 2. code-reviewer (score: 0.71) - General code review and best practices # Step 2: Load the best match python scripts/get_agent.py security-auditor # Step 3: Follow loaded agent instructions for the task ``` ## Installation ### Step 1: Install the Skill **Quick Install (Recommended):** ```bash # NPX with add-skill (recommended) npx add-skill MaTriXy/Agent-Registry # OR npm directly npm install -g @claude-code/agent-registry ``` **Traditional Install:** ```bash # User-level installation ./install.sh # OR project-level installation ./install.sh --project ``` **What install.sh does:** 1. ✓ Copies skill files to `~/.claude/skills/agent-registry/` 2. ✓ Creates empty registry structure 3. ✓ Automatically installs `questionary` Python package (for interactive UI) 4. ✓ Falls back gracefully if `pip3` not available **Note:** All installation methods support Python-based migration and CLI tools ### Step 2: Migrate Your Agents Run the interactive migration script: ```bash cd ~/.claude/skills/agent-registry python scripts/init_registry.py ``` **Interactive selection modes:** - **With questionary** (recommended): Checkbox UI with category grouping, token indicators, and paging - ↑↓ navigate, Space toggle, Enter confirm - Visual indicators: 🟢 <1k tokens, 🟡 1-3k, 🔴 >3k - Grouped by subdirectory - **Without questionary** (fallback): Text-based number input - Enter comma-separated numbers (e.g., `1,3,5`) - Type `all` to migrate everything **What init_registry.py does:** 1. Scans `~/.claude/agents/` and `.claude/agents/` for agent files 2. Displays available agents with metadata 3. Lets you interactively select which to migrate 4. Moves selected agents to the registry 5. Builds search index (`registry.json`) ## Dependencies - **Python**: 3.7 or higher - **questionary**: Interactive checkbox selection UI with Separator support The installer automatically installs questionary. If installation fails or pip3 is unavailable, the migration script falls back to text-based input mode. **Manual installation:** ```bash pip3 install questionary ``` ## Registry Location - **Global**: `~/.claude/skills/agent-registry/` - **Project**: `.claude/skills/agent-registry/` (optional override) Agents not migrated remain in their original locations and load normally (contributing to token overhead).
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.