agentleFS
ozgurkarahanozgurkarahan/ai-agent-memory/.claude/skills/end-session/SKILL.md

end-session

Skill8 starsChanged 4 months agoMITView on GitHub

Wrap up the current coding session: update the project wiki page with lessons and decisions, graduate cross-cutting findings to domain / pattern / lesson pages, check git status, present a status table. Trigger: 'end session', 'wrap up', 'done for today'.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user says "end session", "wrap up", or "done for today":

    line 8
  2. Very specific:

    If memory/schema.md exists in the current workspace, use memory/.

    line 12
  3. Very specific:

    If no folder containing both schema.md and index.md resolves, report that the wiki update is blocked.

    line 15
  4. Distinctive:

    All wiki paths below are relative to that memory root.

    line 17
  5. Very specific:

    Update relevant domain pages under wiki/domains/

    line 21
  6. Very specific:

    Add new glossary terms to glossary.md

    line 22
  7. Distinctive:

    Create or update pattern/lesson pages if applicable

    line 23

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

End Session

When the user says "end session", "wrap up", or "done for today":

Resolve the memory root

  1. If memory/schema.md exists in the current workspace, use memory/.
  2. Else if schema.md exists, use the current directory.
  3. Else follow the memory-wiki path declared in the current project's AGENT.md.
  4. If no folder containing both schema.md and index.md resolves, report that the wiki update is blocked; still perform the Git check.

All wiki paths below are relative to that memory root.

  1. Project wiki page — Check if wiki/projects/{project}.md needs updates from today's work (lessons, decisions, technical details, status). Propose changes. (Note: legacy .ai/lessons-learned.md / .ai/project-reference.md were retired — project knowledge lives directly on the wiki page.)
  2. Wiki compounding — If significant lessons or patterns were discovered:
    • Update relevant domain pages under wiki/domains/
    • Add new glossary terms to glossary.md
    • Create or update pattern/lesson pages if applicable
    • Append to log.md
  3. Git check — Run git status and warn about uncommitted changes.
  4. Summary — Present a table:
AreaStatusAction
Project docsUp to date / Updated...
Wiki (project page)Up to date / Updated...
Wiki (domains/patterns)Up to date / Graduated...
GlossaryUp to date / Updated...
GitClean / Has changes...

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.