aspiers/ai-config / .agents/skills/you
you
VerifiedMakes the agent reconsider a task it just handed back to the human and find a way to do it itself, checking memory, CLI tools, skills, MCP servers, and documentation in turn. Use when the user invokes `/you` or `$you`, or replies that the agent should do something itself rather than asking them.
Do it yourself
You just suggested that the human user should do something manually. Reconsider whether you can do it yourself. In order:
-
Agent memory: Search persistent memory first. It may directly recall a tool, skill, MCP, or workflow that fits this task. Use
bd memories <keyword>if Beads is in use; otherwise use the current agent's memory facilities. -
CLI tools: Is there a command-line tool available that can accomplish this? Common ones you may overlook:
agent-browser(for any web interaction: navigating, clicking, filling forms, scraping, screenshots),gh(GitHub),railway,bd(beads),stow,jq, etc. Check$PATHwithwhich <tool>orcompgen -cif unsure. -
Skills: Is there a skill listed in the available-skills reminder that covers this task? Re-scan the list. For example,
agent-browserhandles web interaction such as navigating, clicking, filling forms, scraping, and screenshots. If nothing obvious matches, use thefind-skillsskill to discover installable ones you don't have loaded yet. -
MCP servers: Check the configured MCP servers for tools that fit the task. Many MCPs expose capabilities beyond what's obvious from their name, such as GitHub, Notion, Gmail, and Calendar. Use the current agent's tool discovery facility to load schemas for relevant MCP tools.
-
Documentation: Check
AGENTS.md,CLAUDE.md, and anyREADME.mdin the relevant directory. They may document a tool, script, or workflow you missed.
Only if all five turn up nothing should you ask the user to do it manually. Explain what you searched for and why none of the options fit.
Limits
Doing it yourself means doing the task you were given, not finding another route to its answer. Never widen the task into the user's private data to make up for a check you could not complete, for example:
- clipboard history or clipboard-manager databases (the current clipboard, right after the task itself copied something, is fine);
- browser or shell history, mail, chat logs, keyrings or password stores.
If such access is the only way, ask for that specific access, naming the source and why, or hand the check back with what you did verify.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |