agentleFS
PUNCKePUNCKe/manuscript-context-integrity/.agents/skills/session-close/SKILL.md

session-close

Skill2 starsChanged 56 days agoMITView on GitHub

Session wrap-up: update the project CLAUDE.md, dashboard and discussion summary, and record key decisions to _synthesis before context compaction loses them. (指导内容为中文 / guidance is in Chinese) 会话收束:更新项目 CLAUDE.md、项目仪表盘、写讨论摘要,并把关键决策与用户原话落进 _synthesis

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use session-open and handoff.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • vishnujchandranSkill

    session-open

    Restart-safe session starter that restores context, validates readiness, and creates a focused execution plan for the current development session.

    Also in 4 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

Files
SKILL.md

会话收束

核心认知

上下文是会消耗的资源,不是无限工作区。compaction 是不可逆的, summary 质量看运气,可能把假设校准逻辑压得只剩一句"调整了维度3"。

收束四件套(不能省)

1. 更新项目 CLAUDE.md 的「项目当前状态」段

已完成 / 进行中 / 下一步 / 阻塞项。只写状态,不写过程。

2. 更新 _输出文件/0_项目仪表盘.md

进度总览表(研究设计 / 文献精读 / 数据采集 / 论文写作 / 投稿)、阻塞项、版本记录。 仪表盘是所有产出物的索引。

3. 写讨论摘要

_输出文件/7_会议记录/讨论摘要_YYYYMMDD.md

按包内模板:本次会话目标 / 关键决策(含理由)/ 用户反馈原话 / 产出文件清单 / 下一步 / 待核实事项。

4. 关键决策写 _synthesis/

_输出文件/_synthesis/session_{日期}_{关键词}.md

必须包含四类内容——这四类是 compaction 最容易毁掉的:

  • 决策的理由:不只是"选了方案A",而是"为什么方案B、C不行"
  • 参数校准的推导过程:不只是最终值
  • 技术踩坑的根因:不只是报错信息和修复
  • 用户反馈的原话:compaction 会改写或删除

**不要等到收束才写。**关键讨论一结束就写,会话炸了也不丢。

里程碑结束时额外做

  1. 写 progress.md(里程碑完成状态 + 产出清单)
  2. 更新 framework_vX.X.md 版本号(重大转向升版本号)
  3. 再更新一次 CLAUDE.md + 仪表盘

收束前建议顺手跑的验收

python "tools/lit_audit.py"      # 本批文献闭环完整吗
python "tools/refs_check.py" --draft _输出文件/5_论文草稿   # 改稿后编号还对吗

判定标准

**本次会话有没有产出具体文件?**没有 = 本次会话无效。 产出物清单要写进仪表盘。

上下文危机处理

  • 主上下文接近上限时:主动写详细摘要,建议用户开新会话
  • 新会话从摘要恢复,应在 1 分钟内接上
  • 不要等上下文爆了再补救,那时已经开始丢信息

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.