Set up and operate abi through opencode — how opencode discovers abi skills, slash-commands, and MCP servers. Use when the user asks about opencode config, why an abi skill is not loading in opencode, or how to add a skill to the opencode allowlist.
日本語の概要は準備中です。原文の説明を表示しています。
Build, launch, and drive the abi stable-Rust project — the `abi` CLI and the `abi-mcp` JSON-RPC server. Use when asked to run, start, build, smoke-test, or screenshot abi, drive its CLI subcommands, exercise the MCP server over stdio, or confirm a change works in the real binaries (not just the test suite).
日本語の概要は準備中です。原文の説明を表示しています。
Show or reset abi agent context: report history, file mentions and session data (`/context` in abi agent tui), or clear history, file mentions and transient state (`/reset`).
日本語の概要は準備中です。原文の説明を表示しています。
Local multi-agent orchestration superpower. Fixed trio, custom workers, browser planning — all scheduler-backed, no distributed agents, no embedded browser.
日本語の概要は準備中です。原文の説明を表示しています。
AI completion and SEA learning guide. Maps completion, streaming, training, and learning requests to real ABI CLI paths.
日本語の概要は準備中です。原文の説明を表示しています。
GPU and Metal backend superpower. Reports backend status, vector ops, hardware capabilities.
日本語の概要は準備中です。原文の説明を表示しています。
ABI MCP JSON-RPC server skill for the frozen 12-tool stdio surface and custom loopback HTTP compatibility listener.
日本語の概要は準備中です。原文の説明を表示しています。
SEA (Sparse Evidence Attention) learning superpower. Evidence-augmented completion with task-aware scoring and adaptive modulation.
日本語の概要は準備中です。原文の説明を表示しています。
WDBX compute superpower. Cycle-free accelerator contracts, deterministic CPU SIMD fallback, scoped Metal execution, output-checked CoreML inference, and honest CUDA/Vulkan boundaries.
日本語の概要は準備中です。原文の説明を表示しています。
WDBX secure/compression demos. Deterministic persisted PQ/autoencoder artifacts, additive/DGHV references, educational refresh, and optional pinned TFHE-rs execution with strict claim boundaries.
日本語の概要は準備中です。原文の説明を表示しています。
Plan and execute ABI repo work from current TODOs, roadmap/spec docs, stable Rust 1.99.1 constraints, and validation gates. Use when user asks to find all ABI todos/roadmaps, compile ABI goals/specs, organize a large ABI implementation goal, or decide the next safe work slice in the abi repository.
日本語の概要は準備中です。原文の説明を表示しています。
Execute ABI repo work from current TODOs, roadmap/spec docs, stable Rust 1.99.1 constraints, and validation gates. Use when user asks to find all ABI todos/roadmaps, compile ABI goals/specs, organize a large ABI implementation goal, or decide the next safe work slice in the abi repository.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a macOS user asks to free substantial storage, delete caches or duplicates, empty Trash, manage Time Machine snapshots, consolidate repositories, or reorganize files across the home directory.
日本語の概要は準備中です。原文の説明を表示しています。
Run the propose-then-apply self-improvement loops in abi (`abi improve`) and abbey (`abbey learn improve`). Use when asked to "self-improve", "auto-improve", or preview/apply what abi or abbey would learn from recent activity. Both default to a dry run; applying is an explicit, gated step. Not a trainer, not LoRA, and not skill-loop.
日本語の概要は準備中です。原文の説明を表示しています。
Build the abi CLI and report GPU / accelerator / shader / MLIR backend status and the compute-backend matrix (CPU/GPU/NPU/TPU detection + dynamic selection). Use when asked about backend capabilities, why a backend shows accelerated=false, or to capture a hardware/dispatch report.
日本語の概要は準備中です。原文の説明を表示しています。
Build the abi CLI and drive the base completion path — `abi complete "<input>"` with no flags — routing to the local model, running the constitution audit, and optionally recording the completion in WDBX. Use to smoke-test the core local-completion path after touching crates/abi-ai or the model catalog. Fully local: no --live (remote) and no --learn (SEA).
日本語の概要は準備中です。原文の説明を表示しています。
Show all build-time feature flags and their current state. Maps to `/features` slash command in abi agent tui.
日本語の概要は準備中です。原文の説明を表示しています。
WDBX vector store operations superpower. Includes insert, query, stats, compaction, secure demos, and REST API.
日本語の概要は準備中です。原文の説明を表示しています。
Drive ABI's loopback multimodal browser studio — camera/image/video frames, microphone PCM, client-side Web Speech STT/TTS, and deterministic local analysis via `abi agent browser --studio`. Use for vision, voice, image, video, getUserMedia, or browser-studio work. Not a neural vision/STT/TTS model.
日本語の概要は準備中です。原文の説明を表示しています。
Donald Filimon's agent style for ABI and multi-CLI work: terse path-anchored status, claim-honest verification, cursor/ branches with draft PRs, skill-loop path hygiene, sync-clis discipline, mid-task skill routing, Cell/Browserbase orientation, and CoreAI skill lanes. Use for Donald, /donald-mode, or requests to work in this style.
日本語の概要は準備中です。原文の説明を表示しています。
Build the abi CLI and run the miniature character-level neural-net demo — `nn train` (real manual-backprop char-LM) and `nn sample` (train-then-generate). Use to train, sample, or smoke-test the nn demo trainer, or verify nn after touching crates/abi-nn/. This is a demo trainer, NOT a production/LLM/distributed trainer.
日本語の概要は準備中です。原文の説明を表示しています。
Build the abi CLI and exercise the OS-control policy in dry-run (planning) mode only, and verify the execute path refuses without --confirm. Use when working on OS-control handlers or the `abi agent os` handler, or to safely demo OS-command planning. Never executes a command.
日本語の概要は準備中です。原文の説明を表示しています。
Create reviewed conventional Git commits through the agent workflow. This is not an `abi agent tui` slash command.
日本語の概要は準備中です。原文の説明を表示しています。
Review Git diffs through the agent workflow. This is not an `abi agent tui` slash command.
日本語の概要は準備中です。原文の説明を表示しています。