技能 人工智能 管理思虑流程帧队列

管理思虑流程帧队列

v20260701
accint-frames
该技能用于管理和处理ACC系统的思虑队列(brain_frames)。它允许用户列出待处理的、已检查点的工作帧,获取上下文,进行推理,并通过特定命令提交持续的解决方案。适用于需要迭代、持续处理AI工作流的场景,确保工作流的连续性和准确性。
获取技能
460 次下载
概览

frames

When to Use

Use this skill when you need drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue").

Routing sugar over the two MCP verbs — no logic lives here.

  1. List the queue: acc frames (CLI, read-only observation).
  2. For each open/waiting frame: read its typed hole + retrieved context, deliberate, then submit via acc_act(runtime="continue", input={"frame_id": ..., "submit_token": ..., "proposal_text": ...}).
  3. End proposal_text with PREDICT: <0.00-1.00> <why>; acc strips that line before the owner sees it and uses it to calibrate the Work Model against later outcomes.
  4. An identical duplicate submit replays the cached result — resubmitting is safe.
  5. Surface each resolution's commitment id and cited [ids]; drain the queue fully before taking new work — checkpointed frames are work headless runs saved for you.

Limitations

  • Use this skill only when the task clearly matches its upstream source and local project context.
  • Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.
  • Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.
信息
Category 人工智能
Name accint-frames
版本 v20260701
大小 1.75KB
更新时间 2026-07-02
语言