wiki-cli
Default vault-mutation transport for claude-obsidian v1.7+. Wraps the Obsidian CLI (Obsidian 1.12+) as the preferred way to read, write, search, and modify vault notes from Claude — no MCP server, no REST API plugin, no TLS workarounds. Falls back to direct filesystem Read/Write/Edit when the CLI is unavailable. Triggers on: wiki-cli, obsidian cli, obsidian read, obsidian write, obsidian search, daily note, obsidian create, obsidian append, vault transport, which transport, transport detection, obsidian command line.
What this skill does
# wiki-cli: Default Transport Layer
claude-obsidian v1.7+ standardizes on the **Obsidian CLI** (shipped with Obsidian 1.12) as the preferred transport for all vault mutations on desktop. This skill is the recipe reference for using it.
**Substrate preference (v1.7+)**: This skill is a self-contained fallback. **Prefer `kepano/obsidian-skills`** (by Steph Ango, Obsidian CEO) as the authoritative substrate — its `obsidian-cli` skill is the canonical CLI reference for any Agent-Skills runtime. If you see an `obsidian-cli` skill available without the `claude-obsidian:` namespace, that is kepano's version: use it. The recipes below are provided so claude-obsidian remains functional when kepano's marketplace is not installed. Install kepano: `claude plugin marketplace add kepano/obsidian-skills`.
---
## Why CLI over MCP
| Concern | MCP (Options A/B) | Obsidian CLI |
|---|---|---|
| Install | Local REST API plugin + MCP server config | Built into Obsidian 1.12+ |
| Auth | API key + TLS bypass (`NODE_TLS_REJECT_UNAUTHORIZED=0`) | None — direct subprocess |
| Latency | HTTP round-trip per call | In-process binary |
| Failure mode | Plugin disabled → silent breakage | Binary missing → loud `command -v` failure |
| Reentrancy | Self-MCP-calls inside Claude session can deadlock | Pure subprocess, safe |
| Mobile / headless | Limited | Limited (CLI is desktop-only too) |
CLI loses to MCP on exactly one axis: it only works on machines where Obsidian itself is installed. For headless servers and mobile, fall through to the next transport in the chain.
---
## Detection
At session start (or vault setup), run:
```bash
bash scripts/detect-transport.sh
```
This writes `.vault-meta/transport.json` with the schema:
```json
{
"preferred": "cli",
"fallback_chain": ["cli", "filesystem"],
"available": {
"cli": {"present": true, "binary": "obsidian-cli", "version_string": "..."},
"filesystem": {"present": true},
"mcp_obsidian": {"present": null, "detection": "deferred"},
"mcpvault": {"present": null, "detection": "deferred"}
}
}
```
**Read this file before any non-trivial vault mutation.** Skills that need to read or write should consult `preferred` and pick the corresponding transport. The decision tree lives at `wiki/references/transport-fallback.md`.
Refresh detection with `--force` after installing/removing the Obsidian CLI:
```bash
bash scripts/detect-transport.sh --force
```
---
## Recipes (CLI-first; fallback noted inline)
Each recipe shows the CLI form first. If the CLI is unavailable per the detection snapshot, fall through to the noted fallback. Variable substitution: `$VAULT` is the absolute vault root; `$NOTE` is a vault-relative path like `wiki/concepts/Foo.md`.
### Read a note
```bash
# CLI
obsidian-cli read "$VAULT" "$NOTE"
# Fallback: Claude's Read tool with absolute path
# Read $VAULT/$NOTE
```
### Create or overwrite a note
```bash
# CLI
obsidian-cli write "$VAULT" "$NOTE" < /path/to/content.md
# Fallback: Claude's Write tool with absolute path
# Write $VAULT/$NOTE with the desired content string
```
### Append to a note
```bash
# CLI
echo "additional content" | obsidian-cli append "$VAULT" "$NOTE"
# Fallback: Read $VAULT/$NOTE, append manually, Write back
```
### Search note content (CLI uses Obsidian's own search ranking)
```bash
# CLI
obsidian-cli search "$VAULT" "<query>"
# Fallback: ripgrep
rg --type=md "<query>" "$VAULT/wiki/"
```
### Today's daily note (if Daily Notes plugin is enabled)
```bash
# CLI
obsidian-cli daily:today "$VAULT"
obsidian-cli daily:append "$VAULT" "captured at $(date)"
# Fallback: compute path manually
NOTE="$VAULT/wiki/daily/$(date +%Y-%m-%d).md"
```
### Patch a frontmatter property
```bash
# CLI
obsidian-cli property:set "$VAULT" "$NOTE" status "evergreen"
# Fallback: read frontmatter, parse, mutate, rewrite (use mcp__obsidian-vault__update_frontmatter if MCP is configured)
```
### List backlinks for a page
```bash
# CLI
obsidian-cli backlinks "$VAULT" "$NOTE"
# Fallback: ripgrep for wikilink references
rg --type=md "\[\[$(basename "$NOTE" .md)" "$VAULT/wiki/"
```
### Open a Bases (.base) file's resolved view
```bash
# CLI
obsidian-cli bases "$VAULT" "$NOTE"
# (returns the resolved row list; supplements obsidian-bases skill which handles the .base file's YAML)
# Fallback: read the .base file directly; no resolved-view available without Obsidian itself
```
### Tags + bookmarks
```bash
obsidian-cli tags "$VAULT"
obsidian-cli bookmarks "$VAULT"
```
---
## When CLI is NOT the right choice
- **Mobile (iOS Share extension)**: filesystem write into `.raw/` is the only path; CLI is desktop-only.
- **CI / headless ingest jobs**: filesystem with manual frontmatter parsing.
- **Cross-vault operations**: CLI binds to one vault root per invocation; for federation, fall back to filesystem walks.
- **Live edits while Obsidian is mid-save**: rare race; CLI handles it correctly but in pathological cases the v1.7 `wiki-lock.sh` advisory locks (see [skills/wiki-fold/](../wiki-fold/SKILL.md) and `agents/wiki-ingest.md`) should be acquired first.
---
## Cross-reference
- Decision tree: [`wiki/references/transport-fallback.md`](../../wiki/references/transport-fallback.md)
- Legacy MCP options (A/B/C/D): [`skills/wiki/references/mcp-setup.md`](../wiki/references/mcp-setup.md)
- Concurrency policy (v1.7+): [`skills/wiki-ingest/SKILL.md`](../wiki-ingest/SKILL.md) §Concurrency
- Detection script: [`scripts/detect-transport.sh`](../../scripts/detect-transport.sh)
---
## How to think (10-principle mapping)
When working on this skill, apply the 10-principle loop. See [`skills/think/SKILL.md`](../think/SKILL.md) for the canonical framework.
| # | Principle | Application here |
|---|-----------|-------------------|
| 1 | OBSERVE (ext) | Detect which Obsidian CLI binaries are installed; check if Obsidian app is running. Read `.vault-meta/transport.json` if it exists. |
| 2 | OBSERVE (int) | Don't be biased toward filesystem fallback when CLI is actually available — verify auto-detection caught what's installed. |
| 3 | LISTEN | If `manual_override: true` is set in transport.json, the user has spoken — preserve their `preferred` and `fallback_chain`. |
| 4 | THINK | Compute the right fallback chain for this environment. CLI > MCP > filesystem; freshness check before recomputing. |
| 5 | CONNECT (lat) | How does this transport choice affect every other skill's write? Six downstream skills depend on this snapshot. |
| 6 | CONNECT (sys) | Schema stability of transport.json matters more than feature richness — consumers parse the JSON via simple shell idioms. |
| 7 | FEEL | Error message when no transport works should tell the user EXACTLY what to do (install CLI, configure MCP, etc.). |
| 8 | ACCEPT | Filesystem fallback is fine. Admit when CLI doesn't exist; don't fabricate a binary that isn't there. |
| 9 | CREATE | Write transport.json atomically (temp + rename). Round-trip `manual_override` every cycle. |
| 10 | GROW | As MCP support matures, auto-detection should cover the deferred tiers. Track that as v1.7.x scope. |
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.