obsidian-learn — Claude Code command: what it does, install
The obsidian-learn command reviews lessons in an Obsidian vault, marks stale or replaced findings, and surfaces repeated patterns for _CLAUDE.md.
MIT ★ 5,412 updated 2026-10-24
/plugin marketplace add eugeniughelbur/obsidian-second-brain
/plugin install obsidian-second-brain@obsidian-second-brainWhat obsidian-learn does
obsidian-learn first loads vault context from _CLAUDE.md, index.md, and recent operation logs. Five parallel subagents then search daily notes, ADRs, reports, development logs, and recurring success patterns. The command uses those findings to build a review rather than relying on one note source.
Each learning is marked Active, Stale, Superseded, or Promoted. The generated report covers current lessons, items that may be archived, replaced positions, promotion candidates, and the top five lessons for the period. It is saved in the concepts folder, while the operation log and today’s daily note are updated.
You can pass recent, all, or a topic name. recent is the default and limits the review list to the last 30 days, but Stale and Superseded checks still scan the whole vault. If references/ai-first-rules.md cannot be read, the command must report that before writing a note.
What it helps with
- review lessons scattered across daily notes
- separate current findings from stale ones
- trace decisions replaced by newer ADRs
- spot repeated lessons for
_CLAUDE.md - write the review and update the vault log
Example prompts for the agent
- Run
/obsidian-learn recentand review lessons from the last 30 days. - Use
/obsidian-learn allto inspect learnings across the entire vault. - Run
/obsidian-learn testingto focus the review on a topic.
How to install obsidian-learn
1Plugin marketplace
/plugin marketplace add eugeniughelbur/obsidian-second-brain/plugin install obsidian-second-brain@obsidian-second-brain2Manually: put the files in place
.claude/commands/obsidian-learn.mdCall it with /obsidian-learn. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/obsidian-learn.mdCall it with /prompts:obsidian-learn. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/obsidian-learn.prompt.mdManually: put the files in place
.gemini/commands/obsidian-learn.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about obsidian-learn
How do I install obsidian-learn in Claude Code?
Run /plugin marketplace add eugeniughelbur/obsidian-second-brain, then /plugin install obsidian-second-brain@obsidian-second-brain. The command file is .claude/commands/obsidian-learn.md.
What does obsidian-learn do?
It gathers lessons, decisions, reports, failures, and recurring wins from an Obsidian vault. It classifies the findings and writes a report with possible rules for _CLAUDE.md.
Does recent scan the whole vault?
recent limits the displayed review list to the last 30 days. Stale and Superseded classification still scans the full vault, so older learnings can be included there.
Source text
obsidian-learn.md · MIT
--- description: Review vault learnings, prune stale ones, surface active patterns - the vault's lessons compound or expire category: thinking triggers_en: ["review learnings", "what have I learned", "show lessons", "prune learnings"] triggers_de: ["Erkenntnisse durchgehen", "was habe ich gelernt", "Lerneffekte zeigen", "Erkenntnisse bereinigen"] triggers_es: ["revisa los aprendizajes", "qué he aprendido", "muéstrame las lecciones", "poda los aprendizajes"] triggers_pt: ["revise aprendizados", "o que eu aprendi", "mostre lições", "reduza aprendizados"] triggers_zh: ["回顾我学到的东西", "我最近学到了什么", "整理知识库里的经验", "清理过时的学习记录"] --- Use the obsidian-second-brain skill. Execute `/obsidian-learn $ARGUMENTS`: The optional argument is a scope: `recent` (last 30 days, default), `all` (entire vault), or a topic name. Scope limits the review LIST only - the Stale and Superseded classifications always scan the entire vault, since a 6-months-old learning cannot appear inside a 30-day window. 1. Read `_CLAUDE.md` first if it exists in the vault root 2. Read `index.md` and recent operation log for vault context (if `Logs/` exists: read the last 2-3 `Logs/YYYY-MM-DD.md` files; otherwise read `log.md`) 3. Spawn parallel subagents to gather learnings: - **Lessons agent**: scan all daily notes for "Lesson learned" sections, "What didn't" sections, evening review insights - **Decisions agent**: read all ADRs in the decisions folder (resolved per `references/folder-map.md` - wiki-style `wiki/decisions/`, Obsidian-style `Knowledge/` with `ADR-` filename prefix) - extract the rationale and outcome of each - **Reports agent**: read recent emerge/synthesize/connect/challenge reports in the concepts folder (resolved per `references/folder-map.md`) - the auto-generated pattern reports - **Mistakes agent**: scan dev logs and daily notes for "what didn't work", "wasted time on", "next time", "lesson", phrases indicating learning from failure - **Wins agent**: scan for patterns that worked - "this saved time", "this approach worked", recurring success patterns 4. For each learning found, classify: - **Active**: still relevant, recurring, reinforced by recent activity - **Stale**: 6+ months old with no recent reinforcement, or contradicted by newer evidence - **Superseded**: explicitly replaced by a newer ADR or pattern - **Promoted**: appeared 3+ times - should become a permanent rule in `_CLAUDE.md` 5. Generate the Learnings Report: ## Active Learnings (still applies) - List learnings reinforced in the last 90 days - Cite the original source and most recent reinforcement ## Stale Learnings (consider archiving) - List learnings with no recent reinforcement - Suggest: keep, archive, or convert to history note ## Superseded Learnings (already replaced) - Old position → New position with ADR reference ## Promotion Candidates (appeared 3+ times) - Learnings strong enough to become permanent rules in `_CLAUDE.md` - Suggest exact wording for the operating manual ## Top 5 Lessons of the Period - Most impactful learnings ranked by frequency × recency × consequence 6. Save the report to the concepts folder (resolved per `references/folder-map.md`) as `YYYY-MM-DD - Learnings Review.md` (`type: learnings-review`, schema in `references/ai-first-rules.md`) 7. Append to the operation log: if `Logs/` exists write `**HH:MM** - learn | X active, Y stale, Z superseded, N promotion candidates` to `Logs/YYYY-MM-DD.md`; otherwise append `## [YYYY-MM-DD] learn | X active, Y stale, Z superseded, N promotion candidates` to `log.md` 8. Update today's daily note with a brief summary 9. Offer to: - Promote candidates to `_CLAUDE.md` (with user confirmation) - Archive stale learnings (with user confirmation) - Export top 5 as a shareable markdown for content/journaling Lessons that aren't reviewed don't compound. This command turns scattered notes into a living rulebook. --- **AI-first rule:** Every note created or updated by this command MUST follow `references/ai-first-rules.md` - `## For future agent` preamble, rich frontmatter (`type`, `date`, `tags`, `ai-first: true`, plus type-specific fields), recency markers per external claim, mandatory `[[wikilinks]]` for every person/project/concept referenced, sources preserved verbatim with URLs inline, and confidence levels where applicable. If that path does not resolve from your working directory, search upward for it; if you still cannot read it, say so before writing rather than producing a note that silently skips the rule. The vault is for future agent retrieval - not human reading. **Anti-fabrication:** Search exhaustively before claiming any note, person, or file is absent - false absence is the most common failure mode - and never invent facts, entities, or dates (mark unknowns as `TBD`). See the anti-fabrication and search-completeness hard rules in `references/ai-first-rules.md`.
© Eugeniu Ghelbur · MIT · eugeniughelbur/obsidian-second-brain