obsidian
Skill1 starsChanged 5 months agoApache-2.0View on GitHub
Vault read/write primitives for an optional Obsidian vault. Handles daily-log writes, decision filing, weekly reviews, reading-list maintenance, archiving, and lint. Use this whenever the user types /obsidian, wants to file a decision into their vault, asks to log something to today's daily note, mentions "vault" or "Obsidian," needs vault hygiene checks, or another skill (morning, evening, housekeep) needs to read or write the vault. No-op silently if config.yaml has no vault_dir.
100 other projects use a version of this.
Adopted by
Most recently taken up by
- thegovind/skillstheir own version, first seen Nov 16, 2026
- zkManuel0123/CodexClawtheir own version, first seen Nov 16, 2026
- chuckplayer/claude-agent-packtheir own version, first seen Nov 16, 2026
- rodos4312/Meu-Agenttheir own version, first seen Nov 15, 2026
- metaspartan/cybaratheir own version, first seen Nov 15, 2026
- gapmiss/obsidian-plugin-skilltheir own version, first seen Nov 14, 2026
Used with
Projects with it also use taskflow-inbox-triage, discord-e2e and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AtomicBot-aiSkilltaskflow-inbox-triage
Also in 6 projects that use this
molt-botSkilldiscord-e2e
Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.
Also in 10 projects that use this
molt-botSkillopenclaw-repair-sweep
Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.
Also in 10 projects that use this
clawdbotSkillopenclaw-performance
Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.
Also in 7 projects that use this
clawdbotSkillplugin-sdk-impact
Count Plugin SDK consumers across live ClawHub releases and bundled OpenClaw plugins before deprecation, removal, or behavior changes; supports public release-date filters.
Also in 7 projects that use this
emanueleieloSkillsonos
Control Sonos speakers: discover, play/pause, volume, grouping, favorites, and queue management via sonos CLI.
Also in 5 projects that use this
- +2 more from molt-bot
Other versions100 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 100
- openclaw/openclaw★ 395ksame name
- moltbot/clawdbot★ 394ksame name
- steipete/warelay★ 394ksame name
- steipete/clawdis★ 394ksame name
- moltbot/moltbot★ 394ksame name
- clawdbot/clawdbot★ 394ksame name
- molt-bot/clawdbot★ 391ksame name
- NousResearch/hermes-agent★ 264ksame name
- spinabot/brigade★ 11ksame name
- steipete/agent-scripts★ 7.5ksame name
90 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 3 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 95 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Read config.yaml from the repo root.
- Distinctive: line 28
Run the bundled script:
- Very specific: line 48
If the file doesn't exist, create with # YYYY-MM-DD header and *Updated:* line.
- Very specific: line 50
Update the *Updated:* line.
- Distinctive: line 51
Keep evening wraps to ≤ 30 lines.
- Very specific: line 67
When the user reviews and decides, check off and move the line to ## Completed.
- Very specific: line 175
Only Iantha writes to the vault.
- Very specific: line 176
Never hard-delete — stage in _to-delete/, the user confirms trash.
- Distinctive: line 177
Don't fabricate content. If memory/context doesn't have it, ask.
- Very specific: line 179
All vault writes update the file's *Updated:* line if present.
“Common” is measured: kept by at least 6 in 10 of the 95 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.
Files
/obsidian — Vault Read/Write Primitives
Encode how Iantha consumes and writes to an Obsidian vault. No-op if config.yaml doesn't set vault_dir.
The deterministic parts (init, lint, archive) are bundled scripts so each invocation doesn't re-derive the recipe. Content writes (daily-log, decision, weekly) stay LLM-driven because they need session context.
When to invoke
The user typed /obsidian <mode> [args], OR another skill (morning, evening, housekeep) needs to read or write the vault.
Step 0: Config check
Read config.yaml from the repo root. If config.local.yaml exists, merge it (local wins). If vault_dir is missing or commented out, say so and stop:
"No
vault_dirconfigured. Set it inconfig.yamlto enable vault writes."
Resolve ${vault_dir} to an absolute path (expand ~). Resolve subdirectories using vault_daily, vault_weekly, vault_decisions, etc. — fall back to defaults (daily, weekly, decisions, tasks, personal, artifacts) if a key is unset.
Modes
init — one-time vault setup
Run the bundled script:
python3 .claude/skills/obsidian/scripts/init_vault.py --vault-dir "$VAULT_DIR"The script auto-finds vault-template/VAULT.md (pass --template <path> to override). It creates the standard subdirectories, copies VAULT.md, and writes a starter reading-list.md. Idempotent — never overwrites existing files. Reports created vs skipped.
Example:
$ python3 .claude/skills/obsidian/scripts/init_vault.py --vault-dir ~/Documents/MyVault
Vault: ~/Documents/MyVault
Created: daily/, weekly/, decisions/, tasks/, personal/, artifacts/, _to-delete/, VAULT.md, reading-list.mddaily-log — append or create today's daily note
Path: ${vault_dir}/${vault_daily}/YYYY-MM-DD.md.
- If the file doesn't exist, create with
# YYYY-MM-DDheader and*Updated:*line. - Append the caller's content under a
## <section>heading. The caller passes the section name —## Briefingfor /morning,## Wrapfor /evening,## Notesfor ad-hoc captures, etc. - Update the
*Updated:*line. - Keep evening wraps to ≤ 30 lines; briefings to ≤ 20 lines. The LLM trims if needed.
Why one mode for both briefing and wrap: they're the same operation (append section to today's daily note) with different section names. One mode keeps the surface lean.
weekly — write weekly review
Path: ${vault_dir}/${vault_weekly}/YYYY-WXX.md (ISO week). Create if missing, otherwise append. Caller provides the body.
reading-list — append a doc to the review queue
Path: ${vault_dir}/reading-list.md. Append under ## Action Required:
- [ ] [YYYY-MM-DD] [Title](relative/path.md) — one-line contextWhen the user reviews and decides, check off and move the line to ## Completed.
decision — file a new decision
Path: ${vault_dir}/${vault_decisions}/YYYY-MM-DD-kebab-title.md. Body template:
# YYYY-MM-DD: [Title]
*Updated: YYYY-MM-DD HH:MM*
**Decision**: [what was decided]
**Why**: [reasoning]
**Notes**: [context, prior alternatives, links]Also append a one-line summary to memory/decisions.md so the in-repo SSOT stays current.
Example:
User: "Let's note we're going with the M5 MBA over the Pro for travel."
Output: ${vault_dir}/decisions/2026-05-01-mba-m5-for-travel.md with:
# 2026-05-01: MacBook Air M5 for travel
*Updated: 2026-05-01 14:22*
**Decision**: Use the M5 MBA as the travel laptop, not the 14" Pro.
**Why**: 1.24kg vs 1.55kg matters for long flights; M5 handles CC + light dev fine; battery life > Pro for the same workloads.
**Notes**: Pro stays as desk machine. Reconsider if travel workload shifts to multi-agent local runs.Plus one line in memory/decisions.md:
- 2026-05-01 — MBA M5 for travel — chosen over 14" Pro on weight + battery. ([[2026-05-01-mba-m5-for-travel]])archive <source> — stage for deletion
Run the bundled script:
python3 .claude/skills/obsidian/scripts/archive.py --vault-dir "$VAULT_DIR" --source "decisions/2026-05-01-foo.md"The script moves the file to ${vault_dir}/_to-delete/<flat-source>__<filename>, preserving subdirectory info in the flattened name (so research/topic/r1_foo.md becomes _to-delete/research_topic__r1_foo.md). Refuses to overwrite — appends a timestamp on collision. Never hard-deletes; the user reviews _to-delete/ periodically (handled in /housekeep).
lint — vault hygiene check
Run the bundled script:
python3 .claude/skills/obsidian/scripts/lint_vault.py --vault-dir "$VAULT_DIR"Reports (no auto-fixes):
- Broken wikilinks:
[[target]]where target file is missing - Orphans: markdown files no other file links to (excluding
daily/,weekly/,_to-delete/, which are intentionally orphaned) - Stale
_to-delete/: items older than the SLA (default 14 days, override with--sla-days) - Misnamed: files violating the ISO-date-prefix convention for their dir
Surface the report to the user. Ask before fixing anything.
Vault Structure
PARA-aligned and slimmed for personal life:
| Directory | Purpose | Writer |
daily/ | Daily notes, briefings | /morning, /evening |
weekly/ | Weekly reviews | /obsidian weekly |
decisions/ | Decisions with rationale | /obsidian decision |
tasks/ | Task plans, checklists | manual |
personal/ | Personal docs (preferences, routines, contacts) | manual |
artifacts/ | Misc — brainstorms, drafts, references | manual |
_to-delete/ | Staging for deletion (human reviews) | /obsidian archive |
Optional Karpathy-mode dirs (v0.2.0 will lean on these):
| Directory | Purpose |
wiki/ | Compiled, polished notes — the knowledge base |
raw/ | Ingested source material (clippings, quotes, raw notes) |
Top-level files:
| File | Purpose |
VAULT.md | This handbook (copy from vault-template/VAULT.md) |
reading-list.md | Docs pending the user's review (Rule G) |
Naming convention
Standard: ISO date prefix + kebab-case.
| Pattern | Example |
YYYY-MM-DD-kebab-title.md | Dated outputs (decisions, dated artifacts) |
kebab-title.md | Standing/reference docs (personal/, tasks/) |
YYYY-MM-DD.md | Daily notes |
YYYY-WXX.md | Weekly reviews (ISO week) |
Write contract
- Only Iantha writes to the vault. Manual edits by the user are fine; other agents do not write here.
- Never hard-delete — stage in
_to-delete/, the user confirms trash. - Don't fabricate content. If memory/context doesn't have it, ask.
- Daily logs ≤ 30 lines per section; briefings ≤ 20 lines.
- All vault writes update the file's
*Updated:*line if present.
Learned from runs
(empty — populated as the skill is used)
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
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.

