メニュー
Use the Agentic File System (AFS) context model for discovery, mounts, scratchpad memory, and file-based tool workflows. Use when a task involves .context operations, AFS CLI usage, or cross-agent context coordination.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | agentic-context |
| description | Use the Agentic File System (AFS) context model for discovery, mounts, scratchpad memory, and file-based tool workflows. Use when a task involves .context operations, AFS CLI usage, or cross-agent context coordination. |
~/src/lab/afs/scripts/afs context discover --path ~/src --json..context when working inside a repo.~/src/lab/afs/scripts/afs context ensure-all --path ~/src.context.read, context.write, context.list, context.move, and context.delete.fs.* MCP tool names as compatibility aliases.afs fs read scratchpad state.md --path ~/src.afs fs write scratchpad notes.md --path ~/src --content "...".afs fs list knowledge --path ~/src --glob "*.md".scratchpad unless explicitly asked.session pack as an explicit handoff/export step, not routine startup.ws list, ws find, and ws status for project discovery.AFS_CLI=~/src/lab/afs/scripts/afs and AFS_VENV=~/src/lab/afs/.venv when needed.references/sources.md for AFS context docs and contracts.Read and interpret the Link to the Past (ALTTP) disassembly with label/symbol context. Use when mapping ROM/CPU addresses to labels, searching usdasm/jpdasm sources, or cross-referencing routines with Hyrule Historian, z3dk label indexes, or z3ed output.
Train, evaluate, and maintain the scawful-echo persona and related avatar models (Echo/Memory/Muse). Use when working on persona voice, dataset prep, A/B testing, deployment, or tool-calling constraints for avatar models.
Autonomous navigation agent for Oracle of Secrets. Uses static map data and dynamic RAM state to localize Link and route him to destinations.
End-to-end Oracle of Secrets debugging using the Mesen2-OOS socket CLI, z3ed, and label/symbol tooling. Use for breakpoint/trace capture, memory inspection, savestate repro, overlays, or crash/regression triage (replaces mesen2-mcp and legacy Lua bridge workflows).
Expert guidance for LLM model training, synthetic data generation (SDE), Hierarchical MoE (H-MoE) management, and agentic evaluation. Use when setting up training runs (Vast.ai), generating datasets, or performing technical research PDF analysis for ROM hacking and general AI development.
Manage Zelda/ALTTP/Oracle model training, datasets, evals, registry updates, and deployment artifacts (Nayru/Din/Farore/Veran/Sahasrahla/IQuest). Use when planning or running training runs, curating ASM datasets, selecting base models, evaluating outputs, or converting/serving GGUF or MLX models.