/arrow-maintenance
Run an audit-and-update pass on the docs/arrows/ overlay. Dispatches on project state — audits an existing overlay, bootstraps the overlay from existing LID docs, or redirects to /map-codebase or /linked-intent-dev for projects without LID.
$ npx -y skills add jszmajda/lid --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/arrow-maintenance
Context preview
What this command does when you run it.
Run an audit-and-update pass on the docs/arrows/ overlay. Dispatches on project state — audits an existing overlay, bootstraps the overlay from existing LID docs, or redirects to /map-codebase or /linked-intent-dev for projects without LID.
Command definition
arrow-maintenance.mdname: arrow-maintenance description: Run an audit-and-update pass on the docs/arrows/ overlay. Dispatches on project state — audits an existing overlay, bootstraps the overlay from existing LID docs, or redirects to /map-codebase or /linked-intent-dev for projects without LID.
Invoke the `arrow-maintenance` skill in command mode. The skill dispatches on project state: audits and updates an existing overlay, bootstraps the overlay from existing LID docs if absent, or redirects the user to `/map-codebase` (for brownfield) or `/linked-intent-dev` (for greenfield — invoke with a description of what to build; the workflow bootstraps LID as part of Phase 1) when LID is not installed. See `plugins/arrow-maintenance/skills/arrow-maintenance/SKILL.md` for the full behavior.
A structured design-before-code methodology for agentic coding. Stop building the wrong thing — get alignment on what before writing how. Works with any coding agent that reads per-project instructions.
Repo: jszmajda/lid
Other commands on lid.
- /map-codebase
Bootstrap LID in an existing (brownfield) codebase. Reads every file in scope, proposes lens-based clusterings, walks the user through reconciliation, generates skeleton LLDs/HLD/EARS and the arrow overlay, then prompts the user to flesh out the skeletons. Token-intensive by
Open command - /differential-audit
Audit EARS↔code coherence via a bidirectional differential. With no arguments, opens a scoping conversation that interprets what the user wants audited, maps it to arrows, and captures an explicit EARS selection. With one or more EARS IDs, audits those specs directly using
Open command