agentleFS
Sign inStart free
tykisgodtykisgod/quick-question/skills/changes/SKILL.md

changes

Skill12 starsChanged 8 months agoMITView on GitHub

Summarize all changes Claude Code made during this conversation.

3 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

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After producing the summary, if qq-run-record.py is available, persist a changes run record so controller state can advance:

    line 15
  2. Distinctive:

    If there are architectural changes (file moves, namespace changes, asmdef changes), call them out separately

    line 49
  3. Distinctive:

    If there were multiple rounds of changes in the conversation (e.g., did A first, then changed B), group them in chronological order

    line 51
  4. Distinctive:

    If any changes were rolled back or overwritten, show only the final state, but note "tried X then changed to Y"

    line 52

“Common” is measured: kept by at least 6 in 10 of the 3 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

Run qq scripts as ${CLAUDE_PLUGIN_ROOT}/bin/<name>: they are not on PATH, so a bare qq-run-record.py exits 127.

Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).

Behavior

Identify all file changes actually executed by Claude in this conversation (via Edit/Write/Bash tools) and summarize them grouped by logic.

The data source is the conversation context, not git diff — include every round, committed or not.

After producing the summary, if qq-run-record.py is available, persist a changes run record so controller state can advance:

qq-run-record.py record \
  --project . \
  --stage changes \
  --command qq:changes \
  --status checked \
  --summary "Conversation change summary captured" \
  --capture-local-changes

Output format

## Summary of changes in this conversation

### <Group 1 title>
- What was done
- Key files: ...

### <Group 2 title>
- ...

### Status
- Committed: <list of commit hashes, if any>
- Uncommitted: <list of files, if any>
- Compilation: passed / not verified
- Tests: N/N passed / not run

Notes

  • List the main file paths for each group (omit the Assets/Scripts/ prefix to save space)
  • If there are architectural changes (file moves, namespace changes, asmdef changes), call them out separately
  • .meta files do not need to be mentioned
  • If there were multiple rounds of changes in the conversation (e.g., did A first, then changed B), group them in chronological order
  • If any changes were rolled back or overwritten, show only the final state, but note "tried X then changed to Y"

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.

Check your setup, free