agentleFS
usernameisthebestofthebestusernameisthebestofthebest/claude-recap/skills/save-topic/SKILL.md

save-topic

Skill2 starsChanged 9 months agoMITView on GitHub

Use when the user wants to save or checkpoint topic progress, persist current discussion state, or save all topics before ending a session.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write a structured summary using the format below (section headings in English, content in user's language, skip empty sections):

    line 31
  2. Distinctive:

    If an existing file for this slug exists, it will be overwritten with the new summary.

    line 74
  3. Distinctive:

    Do NOT copy or build upon any previous summary in your context.

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

save-topic

Overview

Saves a structured summary of a topic to a persistent file. Supports saving the current topic, a specific topic by slug, or multiple topics at once.

Instructions

Preparation

  1. Get the session ID from the SessionStart injection in your context: [SessionStart] session=SESSION_ID source=...
  2. Get the plugin scripts path from the SessionStart injection: Plugin scripts path: /path/to/scripts
  3. Determine which topics to save:
    • "save topic" / "checkpoint" → current topic only
    • "save topic X" → the specified topic slug
    • "save all topics" → all topics in this session

Saving the current topic

  1. Get the current topic slug from your topic tag (the › \slug`` you've been outputting).
  2. Write a structured summary using the format below (section headings in English, content in user's language, skip empty sections):
## Status
What was done, key progress.

## Decisions
What was chosen, why, what was rejected.

## Failures
What was tried, why it failed, the fix or workaround.

## Next Steps
What to do next. Be specific and actionable.
  1. Run:
bash "<plugin_scripts_path>/save-topic.sh" "<slug>" "<session_id>" "<summary>"

Saving a non-current topic

For topics you are NOT currently discussing, your LLM context is likely incomplete. Use the --cold flag to force cold-read from JSONL:

bash "<plugin_scripts_path>/save-topic.sh" --cold "<slug>" "<session_id>" ""

The script will extract the conversation from JSONL and generate a summary via claude -p. The third argument (summary) is ignored when --cold succeeds.

Saving multiple topics

  1. Get all topic slugs by running extract-topic.js (same as list-topics skill step 4): node "<plugin_scripts_path>/extract-topic.js" "$HOME/.claude/projects/<project_id>/<session_id>.jsonl" __all__ Filter out __untagged__ from the output.
  2. Save the current topic using the normal path (LLM writes summary).
  3. Save each non-current topic using the --cold flag.

Rules

  • State facts only. No AI filler language.
  • If an existing file for this slug exists, it will be overwritten with the new summary.
  • This does NOT change the current topic — you continue with the same topic tag after saving.
  • The summary should cover the entire topic from the start, not just recent progress.
  • Do NOT copy or build upon any previous summary in your context. Write from scratch based on your full context each time.
  • For non-current topics, always use --cold — do not attempt to write summaries from degraded LLM memory.

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.