profsynapse/nexus/skill

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Read, search, and edit the user's Obsidian vault (notes, folders, canvas, bases, tasks, memory/workspaces, saved prompts) from the shell via the `nexus` CLI — no MCP connection needed. Use whenever the user refers to their vault, notes, daily notes, second brain, or Obsidian, or asks you to find/read/change something stored there and the `nexus` command is on PATH. Do not use it to edit files in the current code repository; use normal file tools for those.

Install

npx vskill@latest install profsynapse/nexus/skill

SKILL.md

Nexus vault CLI

nexus drives a running Nexus (Obsidian) vault from the shell over a local socket — no MCP config. It has two verbs: discover what you can do, then execute.

Start here

Run `nexus --help` first. It is the authoritative, always-current manual — commands, the context contract, CLI syntax, gotchas, and the tool catalog. It's offline and instant (no socket), so read it before your first real command instead of guessing.

For a common task, `nexus playbook <name>` gives you a ready-to-run recipe plus your workspaces and the exact tools it needs, in one call. Run nexus playbook to see what's available (typically: vault-work, organize, tasks, prompt).

The mindset (this is what --help can't teach you)

  • Explore → inspect → exploit. Search/list find locations; content read

gets contents; then you write. A search hit is a {path, score}, not the note — never quote, summarize, or edit from a hit without reading it first.

  • `nexus tools` returns schemas, not data. It's discovery. Don't loop it

hoping for vault content — that comes from nexus use --memory … --goal … -- content read ….

  • `--memory` and `--goal` are real and enforced. You're operating a person's

live vault; pass a genuine running summary and objective, not placeholders.

  • `--workspace` and `--session` are pass-once. The vault remembers them:

name a session and choose its workspace on the first call of a task (or run memory load-workspace <name>), then omit both — every later call continues that session and inherits its workspace. Nothing defaults silently: a session that never chose a workspace fails with "This session has no workspace yet" (only memory list-workspaces / load-workspace / create-workspace run before the choice). Pass a different value once to switch. nexus context shows what the vault currently remembers.

  • You can't escape the vault. Paths are vault-relative; .., ~, and

absolute paths are rejected. That's a guardrail, not a bug.

  • Nothing is destroyed. The AI gets archive (reversible), not delete.
  • Windows: nexus vaults discovers local named pipes. If policy blocks

enumeration, pass --vault <name> or set NEXUS_VAULT.

The shape

nexus tools [selector] # discover — tool schemas (never vault data)
nexus use --memory "<what you're doing>" --goal "<objective>" -- \
<agent command --flags> # execute — runs one tool, prints the result
nexus context # what this vault remembers: session + workspace

Add --session <name> --workspace <name> to the first use of a task only; the vault remembers both for every call after it.

The -- delimiter is canonical: context belongs before it; the tool command belongs after it. This avoids nested command-string quoting, especially in Windows PowerShell. The legacy one-string form remains supported.

Three rules that cover almost every way this goes wrong:

  • `--` splits the two halves, and only that. Context flags (--memory,

--goal, --session, --constraints, --vault) go before it; the agent name, tool name, and every tool flag go after it.

  • Pass a tool's required value positionally. Write

memory load-workspace "Silicon Zone", not memory load-workspace --workspace "Silicon Zone". --workspace is also a context flag, so the positional form is the one that can't be misread.

  • Keep the agent name with the tool name. The command after -- is always

<agent> <tool> [flags] — storage list, not list.

  • Context flags may sit before or after the verb. nexus --vault V use …

and nexus use --vault V … are equivalent.

Malformed commands fail loudly with the corrected command in the error text — read it and retry rather than switching syntax forms. Nothing is silently dropped, so an error never means a partial write happened.

For multiline Markdown or content containing embedded quotes, keep the body out of shell argv. Any value-taking tool flag has a transport form: pipe with --<flag>-stdin or pass a local path with --<flag>-file (e.g. --content-stdin, --conversation-context-file ctx.md). Put the transport after the -- delimiter and do not also pass the flag directly. Never flatten multiline content to one line to dodge quoting:

powershell
Get-Content -Raw .\note.md |
nexus use --memory "importing note" --goal "write note" -- content write --path Notes/Imported.md --content-stdin

Everything else — the flag table, per-tool schemas, syntax rules, the live per-vault catalog (including any enabled app agents) — comes from nexus --help, nexus tools <tool>, and nexus playbook <name>. Prefer those over guessing; they're always current.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
157
Repository forks
21
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/profsynapse/nexus/skill/badge)](https://verified-skill.com/skills/profsynapse/nexus/skill)

Something wrong with this skill or its page? Tell us.