richfrem/agent-plugins-skills / plugins/agent-memory/.apm/skills/managing-obsidian-vaults
managing-obsidian-vaults
VerifiedInteractive vault, wiki and Super-RAG setup in the main conversation. Use for "set up my wiki", "initialize the full knowledge stack" or combined RLM/vector/wiki setup. Manage Obsidian vaults and LLM wikis: initialize vaults, author Markdown and wikilinks, safely edit notes and Bases, create Canvas diagrams, traverse graphs, build concept wikis, distill summary/bullets/deep layers, query and lint knowledge.
references/wiki-distillation-guide.md
View on GitHub# Obsidian Wiki Distillation Guide
## Contents
- [Cheap Model Fallback Hierarchy](#cheap-model-fallback-hierarchy)
- [Three-Layer RLM Output Structure](#three-layer-rlm-output-structure)
- [Engine Detection & CLI Overrides](#engine-detection--cli-overrides)
- [RLM Cache Storage & Colocation](#rlm-cache-storage--colocation)
---
## Cheap Model Fallback Hierarchy
The distiller delegates distillation to cheap cloud LLMs, never local servers:
1. **GitHub Copilot CLI:** `gpt-5-mini` (primary, fast, credit-based)
2. **Claude CLI:** `claude-haiku-4-5` (first fallback)
3. **Antigravity CLI (`agy`) / Gemini CLI:** `gemini-3-flash-preview` (secondary fallback)
4. **None found:** Exits with diagnostic remediation steps
---
## Three-Layer RLM Output Structure
For each processed concept slug, distillation generates:
```
{wiki_root}/rlm/{concept}/
summary.md <- 1-5 sentence distilled summary
bullets.md <- 6-10 structural key idea bullets
deep.md <- Full multi-pass distillation
```
---
## Engine Detection & CLI Overrides
Detection tests availability and authorization via `shutil.which()`:
```bash
# Run distillation with auto-detected engine
python ./scripts/distill_wiki.py --wiki-root <path>
# Force specific CLI backend
python ./scripts/distill_wiki.py --wiki-root <path> --engine copilot
python ./scripts/distill_wiki.py --wiki-root <path> --engine claude
python ./scripts/distill_wiki.py --wiki-root <path> --engine agy
```
---
## RLM Cache Storage & Colocation
By default, RLM nodes land in `{wiki_root}/rlm/{concept}/`.
To colocate with system-wide caches:
```bash
python ./scripts/distill_wiki.py --wiki-root <path> \
--rlm-cache-dir .agent/learning/rlm_wiki_cache
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |