菜单
Implements a high-fidelity state-save and restore system (Snapshotting) that allows the agent to 'fork' its own consciousness for risky experiments and revert to a 'Perfect State' instantly.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Produce a Prismtek/Buddy talking-host overlay for narrated videos using pixel-art visemes and FFmpeg audio RMS animation.
Compare an implementation PR against its referenced BMO tech spec and report gaps, risks, and verification status.
Create a BMO product spec from a GitHub issue or operator request. Use when work needs a durable user-facing intent artifact before implementation.
Create a BMO tech spec from a product spec, GitHub issue, or operator request. Use when work needs grounded implementation planning before code changes.
Allows the Buddy to mutate its own operational kernel to improve performance.
Review and summarize online videos (especially YouTube) by extracting transcript + keyframes with local tools. Use when the user asks you to "watch" a video link, react to a video, summarize a video, or extract highlights/timestamps.
基于 SOC 职业分类
| name | sovereign-state-snapshot |
| description | Implements a high-fidelity state-save and restore system (Snapshotting) that allows the agent to 'fork' its own consciousness for risky experiments and revert to a 'Perfect State' instantly. |
| version | 1.0.0 |
| author | PRISMO (The High Coordinator) |
| tags | ["state","snapshot","risk-management","simulation"] |
This skill treats the agent's current session, memory, and tool-state as a single 'Save Game' file.
TASK_STATE.md, WORK_IN_PROGRESS.md, and recent L1/L2 memory.context/continuity/snapshots/.snapshot-create before any 'savage' refactor.snapshot-restore if a recursive loop or fatal error occurs.snapshot-compare to see the delta between the current soul and the 'Perfect' version.