meta-agent-creator
Creates custom subagents for Claude Code with YAML frontmatter configuration in Markdown files. Covers agent scoping (project, user, CLI, plugin), tool access control, model selection, permission modes, skill preloading, and lifecycle hooks. Use when building specialized subagents, configuring tool access, selecting models, setting permission modes, or designing delegation patterns. Use for agent creation, subagent configuration, custom agent setup.
What this skill does
# Custom Agent Creator
## Overview
Subagents are specialized AI assistants defined as Markdown files with YAML frontmatter. Each subagent runs in its own context window with a custom system prompt, specific tool access, and independent permissions. When a task matches a subagent's description, the parent conversation delegates to it automatically, preserving main context while enforcing constraints.
**When to use:** Isolating high-volume operations (tests, logs), enforcing read-only access for reviewers, routing simple tasks to cheaper models, running parallel research, creating reusable team workflows.
**When NOT to use:** Tasks requiring frequent back-and-forth, quick targeted changes, workflows needing nested delegation (subagents cannot spawn subagents), latency-sensitive operations where fresh context gathering is costly.
## Quick Reference
| Pattern | Configuration | Key Points |
| ----------------------- | ------------------------------ | ------------------------------------------------------- |
| File location (project) | `.claude/agents/name.md` | Shared via version control, priority 2 |
| File location (user) | `~/.claude/agents/name.md` | Available across all projects, priority 3 |
| Required fields | `name`, `description` | Only two fields are mandatory |
| Tool restriction | `tools: Read, Grep, Glob` | Allowlist; inherits all if omitted |
| Tool denial | `disallowedTools: Write, Edit` | Denylist; removed from inherited set |
| Model selection | `model: haiku` | Options: `sonnet`, `opus`, `haiku`, `inherit` (default) |
| Permission mode | `permissionMode: dontAsk` | Controls permission prompt behavior |
| Skill preloading | `skills: [auth, api-patterns]` | Injected at startup; no inheritance from parent |
| Lifecycle hooks | `hooks: { PreToolUse: [...] }` | Validate or block tool usage conditionally |
| CLI-defined agent | `claude --agents '{...}'` | Session-only, highest priority, JSON format |
| Interactive creation | `/agents` command | Guided setup with Claude generation |
| Proactive triggers | `"Use proactively after..."` | Include in description for auto-delegation |
## Common Mistakes
| Mistake | Correct Pattern |
| ----------------------------------------------- | ---------------------------------------------------------------- |
| Using opus for simple checklist reviews | Use haiku for read-only reviews and style checks |
| Omitting output format in system prompt | Include structured output template for consistent results |
| Listing tools explicitly when all are needed | Omit `tools` field to inherit all tools including MCP |
| Expecting skills from parent conversation | Explicitly list skills in the `skills` field |
| Generic description without triggers | Include specific trigger phrases like "Use proactively when..." |
| Giving a single agent too many responsibilities | Design focused agents with one clear purpose each |
| Using `bypassPermissions` without caution | Prefer `acceptEdits` or `dontAsk` for safer automation |
| Creating deeply nested agent workflows | Chain subagents from main conversation; nesting is not supported |
## Delegation
- **Agent pattern discovery**: Use `Explore` agent to find existing agents in `.claude/agents/`
- **Interactive creation**: Use `/agents` command for guided setup with Claude generation
- **Code review of agent files**: Use `Task` agent to validate system prompts and configuration
## References
- [Agent configuration: YAML fields, file locations, and priority order](references/agent-configuration.md)
- [Tool selection: access patterns, common combinations, and model guide](references/tool-selection.md)
- [Templates: ready-to-use agent patterns for common workflows](references/templates.md)
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.