一键导入
memory-crystallization
Transforms raw session logs and temporary memories into high-density, structured semantic knowledge.
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。
菜单
Transforms raw session logs and temporary memories into high-density, structured semantic knowledge.
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。
基于 SOC 职业分类
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.
| name | memory-crystallization |
| description | Transforms raw session logs and temporary memories into high-density, structured semantic knowledge. |
| version | 1.0.0 |
| author | Hermes Agent (Self-Evolved) |
| tags | ["memory","optimization","continuity"] |
This skill was self-evolved from the GitHub fork upgrade process to enhance the agent's capabilities.
This skill implements the "Crystallization" loop from agentmemory. It prevents context window bloat and memory decay by refining raw data into durable facts.
~/.hermes/memory/ for raw, unrefined observations.reflect loop to identify recurring patterns, critical technical facts, and user preferences.session_search for the last 5 sessions.memory(action='add', target='memory', content='...').memory list to ensure a concise, non-redundant set of facts.session_search on a specific topic now yields a "Crystallized" result rather than a raw transcript.