Agent skill

vault

Operate Joel's Obsidian Vault through the joelclaw CLI. Use when reading ADRs/projects, searching notes, listing PARA sections, or auditing ADR hygiene with `vault adr` commands. Triggers on: 'check the vault', 'read ADR', 'find this note', 'vault search', 'ADR collisions', 'ADR audit', 'decision inventory', or any Vault command task.

View SKILL.md on GitHub Repository
Stars 51
Forks 3

Install this agent skill to your Project

npx add-skill https://github.com/joelhooks/joelclaw/tree/main/skills/vault

SKILL.md

Vault CLI Operations

Use joelclaw vault as the canonical interface for Vault reads and ADR governance checks.

When to Use

Trigger this skill when the request involves:

  • Reading ADRs by number/reference
  • Searching Vault markdown
  • Listing projects/decisions/inbox/resources
  • ADR hygiene checks (status drift, collisions, index drift)
  • Decision inventory/gardening workflows

Command Tree

bash
joelclaw vault
├── read <ref>
├── search <query> [--semantic] [--limit <limit>]
├── ls [section]
├── tree
└── adr
    ├── list [--status <status>] [--limit <limit>]
    ├── collisions
    ├── audit
    ├── locate <query> [--limit <limit>]
    ├── refs <query>
    ├── prompt <text>
    └── rank [--band <band>] [--unscored] [--all]

Core Workflows

1) Read ADRs or notes

bash
joelclaw vault read "ADR-0168"
joelclaw vault read "project 12"
joelclaw vault read "~/Vault/Projects/12-example/index.md"

2) Search vault content

bash
joelclaw vault search "talon watchdog"
joelclaw vault search "content lifecycle" --semantic --limit 5

3) ADR governance checks

bash
joelclaw vault adr list --status proposed --limit 50
joelclaw vault adr collisions
joelclaw vault adr audit
joelclaw vault adr locate "gateway guardrails"
joelclaw vault adr refs 0189-gateway-guardrails
joelclaw vault adr prompt "compare [[0189-gateway-guardrails]] with [[0218-gateway-availability-lifecycle-qol-improvements]]"
joelclaw vault adr rank
joelclaw vault adr rank --band do-now
joelclaw vault adr rank --unscored

vault adr audit is the canonical pre-flight for ADR grooming. It reports:

  • canonical status counts
  • missing/non-canonical statuses
  • duplicate ADR number collisions
  • broken superseded-by targets
  • broken or ambiguous wiki links inside ADR bodies
  • ADR README index drift

vault adr locate resolves ADR files and heading sections by ADR number, slug, title, or heading text.

vault adr refs finds backlinks from ADRs to a resolved ADR file or section.

vault adr prompt expands [[ADR refs]] into canonical ids and appends an <adr-context> block suitable for agents.

vault adr rank is the daily prioritization pass. It enforces NRC scoring and applies a novelty/cool-factor facet (priority-novelty, alias priority-interest) with a neutral default of 3 when missing.

Rules

  1. CLI-first only: Do not grep random vault files when joelclaw vault can answer directly.
  2. Use audit before ADR surgery: Run joelclaw vault adr audit first, then patch.
  3. Canonical statuses only: proposed|accepted|shipped|superseded|deprecated|rejected.
  4. Keep index synced: After ADR renames/additions, update ~/Vault/docs/decisions/README.md.
  5. Respect collisions as bugs: Any duplicate ADR numeric prefix is a governance bug to resolve.

References

  • ADR-0081: Vault CLI & Agent Tool Access
  • ADR-0173: ADR Number Collision Remediation
  • ADR-0174: Vault Command Tree + ADR Audit CLI
  • CLI docs: ~/Code/joelhooks/joelclaw/docs/cli.md

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

joelhooks/joelclaw

skill-review

Audit and maintain the joelclaw skill inventory. Use when checking skill health, fixing broken symlinks, finding stale skills, or running the skill garden. Triggers: 'skill audit', 'check skills', 'stale skills', 'skill health', 'skill garden', 'broken skill', 'skill review', 'fix skills', 'garden skills', or any task involving skill inventory maintenance.

51 3
Explore
joelhooks/joelclaw

cli-design

Design and build agent-first CLIs with HATEOAS JSON responses, context-protecting output, and self-documenting command trees. Use when creating new CLI tools, adding commands to existing CLIs (joelclaw, slog), or reviewing CLI design for agent-friendliness. Triggers on 'build a CLI', 'add a command', 'CLI design', 'agent-friendly output', or any task involving command-line tool creation.

51 3
Explore
joelhooks/joelclaw

daily-summary

Generate a daily system activity summary across all joelclaw subsystems. Triggers on 'daily summary', 'what happened today', 'system report', 'today's tally', 'activity summary', 'what did we do', 'daily report'.

51 3
Explore
joelhooks/joelclaw

inngest-durable-functions

Create and configure Inngest durable functions. Covers triggers (events, cron, invoke), step execution and memoization, idempotency, cancellation, error handling, retries, logging, and observability.

51 3
Explore
joelhooks/joelclaw

recall

Fan-out search across all memory sources when context is unclear or vaguely referenced. Triggers on: 'from earlier', 'remember when', 'what we discussed', 'that thing with', 'the conversation about', 'did we ever', 'what happened with', 'you mentioned', 'we talked about', 'earlier today', 'last session', 'the other day', or any vague reference to past context that needs resolution before the agent can act.

51 3
Explore
joelhooks/joelclaw

inngest-local

Set up self-hosted Inngest on macOS as a durable background task manager for AI agents. Interactive Q&A to match intent — from Docker one-liner to full k8s deployment with persistent state. Use when: 'set up inngest', 'background tasks', 'durable workflows', 'self-host inngest', 'event-driven functions', 'cron jobs', or any request for a local workflow engine.

51 3
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results