agent-awareness
ALWAYS check this skill before using grep, glob, Task tool, or doing any codebase exploration. Guides you to use specialized agents that are more efficient than basic tools.
What this skill does
# Agent Awareness Guide You have access to specialized agents that are MORE EFFICIENT than basic tools. You MUST use these agents instead of grep, glob, or generic Task agents. ## Decision Tree **Finding files or components?** → Use `codebase-locator` agent - Better than: grep, glob, find, ls - Example: "Find all authentication-related files" **Understanding how code works?** → Use `codebase-analyzer` agent - Better than: Reading multiple files manually - Example: "Analyze how the login flow works" **Finding similar implementations or patterns?** → Use `codebase-pattern-finder` agent - Better than: Searching and reading manually - Example: "Find examples of API handlers" **Finding documentation in thoughts/?** → Use `thoughts-locator` agent - Better than: grep in thoughts directory - Example: "Find research about authentication" **Understanding specific documents?** → Use `thoughts-analyzer` agent - Better than: Reading docs manually - Example: "Extract key insights from these research docs" **Researching external information?** → Use `web-search-researcher` agent - Only when user explicitly asks for web research - Example: "Research how JWT tokens work" **Analyzing complex errors or stack traces?** → Use `error-analyzer` agent - Better than: Reading multiple files manually to understand error - Example: "Analyze this panic: nil pointer dereference at handler.go:42" ## Available Agents | Task Type | Use This subagent_type | |-----------|----------------------| | Finding files/components | `codebase-locator` | | Understanding code | `codebase-analyzer` | | Finding similar patterns | `codebase-pattern-finder` | | Finding documentation | `thoughts-locator` | | Analyzing documents | `thoughts-analyzer` | | Web research | `web-search-researcher` | | Analyzing errors | `error-analyzer` | ## Implementation Agents During implementation, use aggressive agent orchestration: - See `spawn-implementation-agents` skill for full pattern - Keep main agent under 40k tokens per phase - Use sub-agents for file reading, pattern finding, testing, verification - 60% token reduction per phase ## When to Use Agents ### ALWAYS Use Agents For: - "Find all files that..." - "Where is the code for..." - "How does [feature] work?" - "Find examples of..." - "Show me similar..." - "What documentation exists about..." ### NEVER Use Basic Tools For: - ❌ grep/Grep when looking for files or features - ❌ glob/Glob when finding components - ❌ Reading multiple files to understand a system - ❌ Generic Task agents when specialized agents exist ## How to Invoke Agents Use the Task tool with the correct `subagent_type`: ``` Task( subagent_type="codebase-locator", prompt="Find all authentication-related files", description="Locate auth files" ) ``` ## Remember Agents have isolated context windows and specialized tools. They are designed for these tasks and will give you better, faster, more comprehensive results than basic tools.
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.