From recording-rig
Diagnose a failed recording-rig run (CLI or desktop) — examines the cast or bridge transcript/.mov/bridge-log, sentinels, rendered hooks, and spec to identify the failure mode and propose a fix.
How this command is triggered — by the user, by Claude, or both
Slash command
/recording-rig:diagnose <session-name-or-cast-path> [spec.json]This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
Invoke the `diagnose` skill on `$ARGUMENTS`.
The skill first detects the backend, then walks the matching taxonomy.
**CLI backend:**
- Validator `FAILED`: missing required / forbidden present
- Hung before `session-start` (consent dialogs)
- Hung after `session-start` but no `prompt-submitted` (attach race / trust dialog)
- Hung after paste but no `turn-end` (slow model / unanswered AskUserQuestion)
- Companion never ran (envfile malformed / hook didn't fire)
- `must_contain_in_order` order mismatch (cursor overwrite reordering)
**Desktop backend** (runs `bin/diagnose-desktop.sh ${SESSIO...Invoke the diagnose skill on $ARGUMENTS.
The skill first detects the backend, then walks the matching taxonomy.
CLI backend:
FAILED: missing required / forbidden presentsession-start (consent dialogs)session-start but no prompt-submitted (attach race / trust dialog)turn-end (slow model / unanswered AskUserQuestion)must_contain_in_order order mismatch (cursor overwrite reordering)Desktop backend (runs bin/diagnose-desktop.sh ${SESSION} [spec]):
.mov duration vs the transcript's tool-call spanReports symptom + root cause + specific fix + how to verify. Read-only — does not apply fixes.
npx claudepluginhub hellblazer/recording-rig --plugin recording-rig/diagnoseDiagnoses compilation errors, runtime errors, performance issues, and Protheus logs in ADVPL/TLPP code, providing severity levels, root causes, fixes with examples, and preventive advice.
/diagnoseTraces a failed or stalled pipeline run from a GitHub issue — identifies missing or malformed FORGE annotations, diagnoses the failure point, and suggests remediation steps.
/diagnoseInitiates Dr. Ralph's multi-phase diagnostic workflow: interviews user on symptoms, researches via web, generates differential diagnosis, treatment plan, and SOAP report with running notes.
/diagnoseDiagnoses FilamentPHP v4 errors and issues by parsing descriptions, consulting docs, analyzing logs/caches/code, and providing root causes with code fixes.
/diagnoseDebugs failed or low-quality extractions by analyzing logs and probing the source site to identify root causes and suggest fixes.
/diagnoseRuns a self-check on the AI Brain Starter install, verifying CLAUDE.md, Meta folder, skills, hooks, and MCPs are properly configured.