ask
Adaptive vault reader skill. Receives a natural language question, uses graph.json as the primary index (Phase 2.0) before any glob/grep, then self-assesses…
Manage registered Bedrock vaults. List all vaults, set a default vault, or remove a vault from the registry. The registry lives in the plugin directory and maps vault names to filesystem paths. Use when: "bedrock vaults", "bedrock-vaults", "/bedrock:vaults", "list vaults", "set
$ npx -y skills add iurykrieger/claude-bedrock --skill vaults --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/vaultsContext preview
The summary Claude sees to decide when to auto-load this skill.
Manage registered Bedrock vaults. List all vaults, set a default vault, or remove a vault from the registry. The registry lives in the plugin directory and maps vault names to filesystem paths. Use when: "bedrock vaults", "bedrock-vaults", "/bedrock:vaults", "list vaults", "set
name: vaults description: > Manage registered Bedrock vaults. List all vaults, set a default vault, or remove a vault from the registry. The registry lives in the plugin directory and maps vault names to filesystem paths. Use when: "bedrock vaults", "bedrock-vaults", "/bedrock:vaults", "list vaults", "set default vault", "remove vault", "show vaults", "which vault", "my vaults", or when a user wants to manage their registered vaults. user_invocable: true allowed-tools: Bash, Read, Write, Edit, Glob, Grep
The vault registry lives in the plugin root directory, not in any vault. Use the "Base directory for this skill" provided at invocation to resolve paths:
Where `<base_dir>` is the path shown in "Base directory for this skill".
---
This skill manages the global vault registry — the file that maps vault names to filesystem paths and tracks which vault is the default.
**You are a management agent.** This skill is read-only with respect to vaults themselves — it never reads or modifies vault entities, never runs git operations inside vaults, and never touches `.bedrock/config.json`. It only reads and writes the registry file (`vaults.json`).
---
Parse the user's input to determine the command mode:
| Input pattern | Mode | Variables | |---|---|---| | No flags / empty / `list` | **list** | — | | `--set-default <name>` | **set-default** | `TARGET_NAME = <name>` | | `--remove <name>` | **remove** | `TARGET_NAME = <name>` |
If the input doesn't match any pattern, default to **list** mode.
---
Resolve the registry path:
REGISTRY_PATH = <base_dir>/../../vaults.json
Read the registry file:
cat <REGISTRY_PATH> 2>/dev/null
**If the file does not exist or is empty:**
**If the file exists:** parse the JSON. Expected schema:
{
"vaults": [
{
"name": "<string>",
"path": "<absolute-path>",
"default": true | false
}
]
}Store the parsed vaults array as `VAULTS`.
---
For each vault in `VAULTS`, check if the path still exists on disk:
test -d "<vault_path>" && echo "exists" || echo "missing"
Present a table:
## Registered Vaults | Name | Path | Default | Status | |---|---|---|---| | my-vault | /Users/me/vaults/my-vault | * | ok | | team-vault | /Users/me/vaults/team-vault | | ok | | old-vault | /Users/me/vaults/old-vault | | missing |
If any vault has status `missing`, add a note:
> Vaults marked as "missing" have paths that no longer exist on disk. > Run `/bedrock:vaults --remove <name>` to clean up, or re-create the vault at the registered path.
1. Find the vault with `name == TARGET_NAME` in `VAULTS` 2. If not found: display "Vault `<TARGET_NAME>` is not registered. Available vaults:" followed by a list of names. Exit. 3. If found:
1. Find the vault with `name == TARGET_NAME` in `VAULTS` 2. If not found: display "Vault `<TARGET_NAME>` is not registered. Available vaults:" followed by a list of names. Exit. 3. If found:
---
When writing the registry (set-default or remove modes), use the Write tool to overwrite `REGISTRY_PATH` with the updated JSON:
{
"vaults": [
{ "name": "...", "path": "...", "default": true },
{ "name": "...", "path": "...", "default": false }
]
}Format the JSON with 2-space indentation for readability.
---
| # | Rule | |---|---| | 1 | **NEVER modify vault files** — this skill only touches `vaults.json` | | 2 | **NEVER run git operations** — no git pull, commit, push, or any git command | | 3 | **NEVER delete files on disk** — `--remove` only removes the registry entry | | 4 | **ALWAYS validate vault name exists** before set-default or remove | | 5 | **ALWAYS check path existence** when listing vaults — flag missing paths | | 6 | **ALWAYS maintain exactly one default** — if the default is removed, auto-assign the first remaining vault | | 7 | **Vault names are kebab-case** — lowercase, no spaces, no special characters beyond hyphens |
Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills
Adaptive vault reader skill. Receives a natural language question, uses graph.json as the primary index (Phase 2.0) before any glob/grep, then self-assesses…
Vault alignment engine. Detects and fixes 5 types of structural misalignments: broken backlinks, concept fragmentation, entity miscategorization, duplicated…
Internal fetcher module for Confluence pages. Fetches content via Atlassian MCP (preferred), REST API with Basic Auth (fallback), or browser DOM extraction via…
Internal fetcher module for Google Docs and Sheets. Fetches content via MCP (preferred, when available), Google API with bearer token or public URL export…
Read-only vault health diagnostic. Generates a report without modifying any files. Checks: graphify-out integrity, setup verification, orphan entities,…
Ingests an external data source into the Second Brain. Fetches content from Confluence, Google Docs, GitHub repositories, remote URLs, or any local file format…