跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 nemo-rl-session-memory

Nemo Rl Session Memory

为编码代理管理持久的工作会话内存. 当用户请求保存或恢复代理上下文时,使用VS代码重启,长期运行的工作,交接,或任何应当定期在repo会话目录下写入重要状态的会话. 切勿用于:简单的问题,短任务,一次性命令,林入,或代码审查.

2079 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

管理编码代理的持久工作会话内存

何时用

当 :

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Session Memory、When To Use、Session Directory、Start Or Resume、Checkpoint Rhythm、File Templates。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.

Session MemoryWhen To UseSession DirectoryStart Or ResumeCheckpoint RhythmFile Templates`session_state.md`Session StateGoalCurrent SubtaskLoaded SkillsCurrent Status

· 许可:Apache-2.0

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
nemo-rl-session-memory
description
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.
许可
Apache-2.0
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「nemo-rl-session-memory」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-f96d99317fe45e60-%E5%B0%BC%E8%8E%AB-Rl-%E4%BC%9A%E8%AF%9D%E5%86%85%E5%AD%98.html
请存为 .cursor/skills/nemo-rl-session-memory/SKILL.md 或 .claude/skills/nemo-rl-session-memory/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/nvidia/skills' --list

npx skills add 'https://github.com/nvidia/skills' --skill 'nemo-rl-session-memory'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: nemo-rl-session-memory license: Apache-2.0 description: "Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review." when_to_use: Preserving or recovering coding-agent context; creating checkpoints for long-running work, handoffs, disconnects, VS Code restarts, branch switches, or nontrivial edits. --- # Session Memory Keep a durable, human-readable record of the current working session so another agent can resume after a disconnect with minimal context loss. ## When To Use Use this skill when: - The user asks to preserve, recover, checkpoint, or manage agent memory. - Work is long-running, experimental, or likely to span disconnects. - You are about to make nontrivial edits, run long jobs, switch branches, or pause for user input. - You resume in a repo that already has `./session/` directories. ## Session Directory Create one directory per working session: ```bash mkdir -p session date +%Y%m%d_%H%M%S mkdir -p session/ ``` Use local time from the machine. Reuse the same session directory for all checkpoints in the same conversation unless the user explicitly starts a new session. Expected files: - `session_state.md` - overall goal, current subtask, loaded skills, status, plan, assumptions, blockers, and next actions. - `timeline.md` - append-only log of major actions, commands, results, and decisions. - `files.md` - files inspected, files changed, and why they matter. - `handoff.md` - concise resume instructions for the next agent. Add other files only when useful, such as `experiments.tsv`, `review_notes.md`, or copied command logs. ## Start Or Resume At the start of a session: 1. Check for existing session directories: ```bash ls -dt session/* 2>/dev/null | head ``` 2. If the user is resuming work, read the latest relevant `session_state.md`, `timeline.md`, and `handoff.md`. 3. If no relevant session exists, create a new timestamped directory. 4. Write an initial `session_state.md` with the user's overall goal, current subtask, loaded skills, repo path, branch, and known constraints. Do not treat session notes as the only source of truth. Verify important claims against git state, files, and command output before acting. ## Checkpoint Rhythm Write a checkpoint: - After gathering enough context to form a plan. - Before and after meaningful code edits. - Before long-running commands, experiments, branch switches, or anything hard to reconstruct from chat. - When the user changes direction. - Before final response if the session has meaningful state worth resuming. - At least every 30 minutes during active long-running work. Prefer updating the same files rather than creating many small checkpoint files. Keep the record compact and scannable. ## File Templates ### `session_state.md` ```markdown # Session State - Session: - Repo: - Branch: - Started: - Updated: ## Goal ## Current Subtask ## Loaded Skills - `` - ## Current Status ## Plan - [ ] - [ ] ## Assumptions - ## Blockers - ``` ### `timeline.md` ```markdown # Timeline ## - User asked: - Context gathered: - Decision: - Result: ``` ### `files.md` ```markdown # Files ## Inspected - `` - ## Changed - `` - ## Generated - `` - ``` ### `handoff.md` ```markdown # Handoff ## Resume From Here ## Next Actions - - ## Watch Outs - ``` ## Recovery Workflow When resuming after a disconnect: 1. Find the likely latest session directory. 2. Read `handoff.md` first, then `session_state.md`, then recent `timeline.md`. 3. Run lightweight verification such as `git status --short`, `git branch --show-current`, and targeted file reads. 4. Continue from the latest verified next action. 5. Append a timeline entry noting the recovery and any mismatches found. ## Quality Rules - Keep notes factual and terse. Future agents need state, not a transcript. - Record command outcomes that matter, especially failed tests or skipped verification. - Mention uncommitted changes and whether they were made by the current agent or pre-existing. - Do not store secrets, tokens, private credentials, or large logs in session files. - If a session file becomes large, summarize old details and keep the latest next actions near the top of `handoff.md`.

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…