agentleFS
dmzoneilldmzoneill/skills/bootstrap-all-knowledge/SKILL.md

bootstrap-all-knowledge

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Iterate all configured projects and personas to build project knowledge. Use to initialize knowledge for all projects at once or scheduled maintenance. Use when user says "bootstrap all knowledge", "scan all projects", or "refresh all knowledge".

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Call knowledge generation (merge with existing if not force)

    line 45
  2. Distinctive:

    Update state/knowledge: last_full_bootstrap, per-project personas

    line 59

≈ “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

Bootstrap All Knowledge - Batch Knowledge Generation

Processes all projects × all personas. Skips existing unless force=true.

Inputs

InputTypeDefaultPurpose
forceboolfalseRegenerate even if exists
projectsstring""Comma-separated; empty = all
personasstring""Comma-separated; empty = all
skip_existingbooltrueSkip project/persona with knowledge

Workflow

1. Get All Projects

  • Load config.json → repositories
  • Filter by projects if provided
  • Include only where path exists
  • Output: to_process, skipped (path not found)

2. Get All Personas

  • Scan personas/*.yaml (exclude "core")
  • Filter by personas if provided
  • Output: to_process, invalid (not found)

3. Check Existing Knowledge

  • For each project × persona: check memory/knowledge/personas/<persona>/<project>.yaml
  • to_generate: force OR missing OR (not skip_existing)
  • Build knowledge_status: existing, to_generate, counts

4. Generate Knowledge

  • For each in to_generate:
    • Get project path from config
    • Load existing knowledge (unless force)
    • Call knowledge generation (merge with existing if not force)
    • Save to persona/project.yaml
  • Track: success_count, error_count

5. Build Summary

  • Timestamp, projects processed, personas, total combinations
  • Already had knowledge, generated/refreshed, errors
  • Table: Project | Persona | Status | Action
  • Skipped projects, invalid personas, error details

6. Log and Track

  • memory_session_log("Knowledge bootstrap completed", "N generated, M errors, K existed")
  • Update state/knowledge: last_full_bootstrap, per-project personas

7. Output Format

## 🧠 Knowledge Bootstrap Complete

**Timestamp:** YYYY-MM-DD HH:MM:SS

### 📊 Summary

- Projects processed: N
- Personas processed: N
- Total combinations: N
- Already had knowledge: N
- Generated/refreshed: N
- Errors: N

### 📁 Projects

| Project | Path |

### 📋 Generation Results

| Project | Persona | Status | Action |

### Next Steps

- knowledge_query(project='...', persona='...')
- knowledge_update(...)

Key Details

  • Chains to: reindex_all_vectors - reindex after bootstrap
  • Validates: bootstrap_knowledge at scale
  • Uses _load_knowledge, _generate_initial_knowledge, _save_knowledge from aa_knowledge

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.