Generate a validated Claude Code ecosystem (orchestrator + N subagents + M skills + MCPs) from a brief. Use when the user asks to scaffold, bootstrap, or design a multi-agent system, agent team, or orchestration plugin.
Generates short dramatic-comedy dialogue stories between a fixed astronaut and a robot assistant from a user prompt, saved as a Markdown file. Use when the user invokes /escribe-dialogo or asks to write a space dialogue, relato, or historia with two characters.
Grade and verify MCP servers A–F with the open polygraph litmus — tool-output injection, egress, sensitive-data, and adversarial-input checks. Bundles the polygraph skill, the polygraph-litmus MCP server, and /polygraph:grade · /polygraph:check.
Build a source-backed GTM Brain for your company with specialist agents, skills, Grill-me questions, MVP checklists, and session handoffs. Originally built for Freckle.io's company GTM brain, then repurposed into a public plugin anyone can use.
Build new Aomi apps and plugins from API docs, OpenAPI/Swagger specs, SDK docs, runtime interfaces, or product requirements. aomi-build scaffolds production-ready Rust SDK crates (lib.rs, client.rs, tool.rs) with tool schemas, preambles, host-interop flows, and validation steps — turning a vendor's full API surface…
The Aomi CLI drives an Aomi runtime that reads and writes EVM chain state: stages calldata, simulates as a batch on a forked chain, and returns wallet requests for the user to sign. Works on any EVM contract via low-level primitives — ABI encoding (encodeandcall), fork-batch simulation (simulatebatch), staged-tx que.
Workflow management for Claude Code, Cursor, Gemini, Windsurf, AGENTS.md — 30 AI agents, 86 commands, 14 hooks, 63 opt-in skill categories. Built for Anthropic Claude Opus 4.7 and Sonnet 4.6.
Comprehensive Rust development assistance for building, testing, and deploying Rust applications with cargo, clippy, async patterns, and framework support.
Workspace agent that executes tasks assigned by humans or supervisors, communicates progress via reply, and manages task lifecycle within a specific AgentRQ workspace.
Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.
6
changed yesterdayA
tokens not measured
originalMIT
Long-term memory for Claude Code. Bundles the memharness MCP server (7 tools: remember, recall, revise, diff, why, forget, stats), a SessionStart hook that injects relevant memories, a PostToolUse hook that nudges durable-fact capture after git commits, and a skill carrying the proactive-use policy.