agentleFS
Sign inStart free
dmzoneilldmzoneill/skills/knowledge-refresh/SKILL.md

knowledge-refresh

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Refresh project knowledge and vector index. Updates vector index with recent code changes, re-scans for architecture changes, restarts file watchers. Use periodically or after major code changes.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Distinctive:

    If not provided: detect from cwd vs config repositories paths

    line 26
  2. Very specific:

    Update state/knowledge with last_refresh, files_indexed, watcher_status

    line 62

≈ “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

Knowledge Refresh

Refreshes vector index and optionally performs full knowledge rescan.

Inputs

InputTypeDefaultPurpose
projectstringautoProject from config (auto-detect from cwd)
full_rescanboolfalseFull rescan vs incremental
restart_watcherbooltrueRestart file watcher

Workflow

1. Check Known Issues

  • check_known_issues("code_index", "")

2. Detect Project

  • If not provided: detect from cwd vs config repositories paths

3. Get Current Stats

  • code_stats(project) — files, chunks, searches before refresh

4. Refresh Vector Index

  • code_index(project, force=full_rescan) — update embeddings

5. Restart Watcher (if requested)

  • code_watch(project, action="start") — auto-updates on file changes

6. Full Knowledge Rescan (if requested)

  • knowledge_scan(project, persona="developer", force=true)

7. Get Updated Stats

  • code_stats(project) — verify delta

8. Build Summary

  • Vector index updated (files, chunks, delta)
  • Watcher status
  • Full rescan result if run

9. Detect/Learn Failures

  • Permission denied → learn_tool_fix("code_index", "permission denied", ...)
  • Out of memory, watcher failed → record patterns

10. Log & Update State

  • memory_session_log("Knowledge refresh for {project}", "Files: ... Chunks: ...")
  • Update state/knowledge with last_refresh, files_indexed, watcher_status

Output

Summary with index stats, watcher status, current totals.

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.

Reviews can't be read right now.

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