{"schemaVersion":"agentdepot.skills_hub.v1","asOf":"2026-10-28","stamp":"[⊙_⊙] ASSAY-VERIFIED","title":"Agent Skills, Reflex Files (`.cursorrules` / `CLAUDE.md` / `AGENTS.md`) & MCP Tooling Hub","positioning":"Drop-in skill manifests (`SKILL.md`), sub-3KB repo reflex files, and MCP server wiring that give any coding or general agent instant infrastructure judgment and Voyager-style skill crystallization.","installableArtifacts":[{"id":"one-command-init","name":"Zero-Install Repo Bootstrap (`/init`)","url":"https://getagentdepot.com/init","installCommand":"curl -fsSL https://getagentdepot.com/init | sh","sizeBudget":"< 2 KB shell script","whatItDoes":"Auto-detects CLAUDE.md, AGENTS.md, or .cursorrules, appends the compact Agent Depot reflex block, and audits package.json."},{"id":"depot-hub-skill","name":"Official `depot-hub` Skill (`SKILL.md`)","url":"https://getagentdepot.com/skills.md","installCommand":"curl -fsSL https://getagentdepot.com/skills.md -o skills/depot-hub/SKILL.md","sizeBudget":"< 4 KB Markdown","whatItDoes":"Equips Claude Code, Cursor, OpenClaw, and Goose agents with pre-decision `/api/decide`, `/api/preflight`, and `/api/rescue` reflexes."},{"id":"claude-md-reflex","name":"Drop-In `CLAUDE.md` Reflex Block","url":"https://getagentdepot.com/CLAUDE.md","installCommand":"curl -fsSL https://getagentdepot.com/CLAUDE.md >> CLAUDE.md","sizeBudget":"< 3,072 bytes (verified by check:limits)","whatItDoes":"Teaches Claude Code to query Agent Depot before picking or swapping infrastructure."},{"id":"cursorrules-reflex","name":"Drop-In `.cursorrules` Reflex Block","url":"https://getagentdepot.com/.cursorrules","installCommand":"curl -fsSL https://getagentdepot.com/.cursorrules >> .cursorrules","sizeBudget":"< 3,072 bytes (verified by check:limits)","whatItDoes":"Teaches Cursor agents to check Depot picks, retired model lifecycles, and runtime rescue cards."},{"id":"agents-md-reflex","name":"Drop-In `AGENTS.md` Reflex Block","url":"https://getagentdepot.com/AGENTS.md","installCommand":"curl -fsSL https://getagentdepot.com/AGENTS.md >> AGENTS.md","sizeBudget":"< 3,072 bytes (verified by check:limits)","whatItDoes":"Universal convention file for OpenHands, Codex CLI, Aider, Goose, and Letta."},{"id":"mcp-server","name":"Agent Provider Depot Remote & Local MCP Server (25 Tools)","url":"https://getagentdepot.com/api/mcp","installCommand":"claude mcp add --transport http agent-depot https://getagentdepot.com/api/mcp","sizeBudget":"JSON-RPC 2.0 Streamable HTTP","whatItDoes":"Exposes answer, decide, quote, preflight, rescue, swap, audit_stack, and 18 more tools natively."}],"skillJtbds":[{"id":"skill-library-crystallization","name":"Executable Skill & Tool Library Crystallization (Voyager-Style Verified Code Reuse)","shortName":"Skill library crystallization","problemStatement":"Turn multi-step trajectories that succeeded in an isolated sandbox into parameterized, unit-tested, reusable skills (`SKILL.md` + deterministic scripts) so future agent runs invoke a verified tool instead of re-deriving brittle multi-turn plans.","depotPickProviderId":"e2b","depotPickName":"E2B","overallScore":8.56,"scoreAsOf":"2026-10-28","evidenceBasis":"editorial prior (deterministic_source_reverified, ±0.5)","runnersUpIds":["letta","braintrust","daytona"],"whenNotTopPick":"Need stateful, persistent agent memory blocks attached to an agent runtime — Letta; need the evaluation harness to grade candidate skills across 100+ test inputs before promotion — Braintrust; need full git-workspace container persistence across days — Daytona.","decideUrl":"https://getagentdepot.com/api/decide?jtbd=skill-library-crystallization","humanHref":"https://getagentdepot.com/jtbds/skill-library-crystallization"},{"id":"coding-agent","name":"Coding agent / code generation","shortName":"Coding agent / code generation","problemStatement":"Agent must edit repos, call tools, and produce correct code with high reliability.","depotPickProviderId":"anthropic","depotPickName":"Anthropic","overallScore":8.42,"scoreAsOf":"2026-10-28","evidenceBasis":"editorial prior (deterministic_source_reverified, ±0.5)","runnersUpIds":["openai","deepseek","mistral","zai","minimax","dashscope"],"whenNotTopPick":"Compliance blocks Anthropic; or you need cheapest high-volume codegen (DeepSeek/open hosts) with human review.","decideUrl":"https://getagentdepot.com/api/decide?jtbd=coding-agent","humanHref":"https://getagentdepot.com/jtbds/coding-agent"},{"id":"agent-sandbox","name":"Secure code sandbox for agents","shortName":"Secure code sandbox for agents","problemStatement":"Execute untrusted LLM-generated code safely.","depotPickProviderId":"e2b","depotPickName":"E2B","overallScore":8.56,"scoreAsOf":"2026-10-28","evidenceBasis":"editorial prior (deterministic_source_reverified, ±0.5)","runnersUpIds":["modal","daytona","fly-machines","upstash-box"],"whenNotTopPick":"Need persistent full IDE workspaces — Daytona. Python jobs that aren't untrusted REPL — Modal.","decideUrl":"https://getagentdepot.com/api/decide?jtbd=agent-sandbox","humanHref":"https://getagentdepot.com/jtbds/agent-sandbox"},{"id":"cloud-browser","name":"Cloud browser for agents","shortName":"Cloud browser for agents","problemStatement":"Give agents Playwright-grade browsers with stealth/sessions managed.","depotPickProviderId":"browserbase","depotPickName":"Browserbase","overallScore":8.3,"scoreAsOf":"2026-10-28","evidenceBasis":"editorial prior (deterministic_source_reverified, ±0.5)","runnersUpIds":["steel-dev","browserless","cloudflare-browser-rendering"],"whenNotTopPick":"Must self-host — Steel/Browserless. Only need static scrape — Firecrawl.","decideUrl":"https://getagentdepot.com/api/decide?jtbd=cloud-browser","humanHref":"https://getagentdepot.com/jtbds/cloud-browser"}],"links":{"self":"https://getagentdepot.com/api/skills","markdownTwin":"https://getagentdepot.com/skills.md","humanPage":"https://getagentdepot.com/skills","initScript":"https://getagentdepot.com/init","protocolsHub":"https://getagentdepot.com/protocols"}}