workbench-debug-investigate
Workbench Debug Investigate
Use this skill for bugs, regressions, suspicious runtime behavior, failed automations, and "this should not happen" reports.
Investigation Loop
- State the exact symptom and expected behavior.
- Collect the smallest real evidence: command output, log line, screenshot, issue ID, run ID, or file path.
- Identify the owner layer: user workflow, Multica issue/comment, agent runtime, local repo, CLI wrapper, gateway/API, or external vendor.
- Form one mechanism hypothesis and test it on the smallest real path.
- Patch only after the mechanism is supported by evidence.
- If two attempts fail, stop and report what is known instead of guessing harder.
Evidence Rules
- Prefer live runtime state over stale UI state.
- Separate dashboard symptoms from backend/request evidence.
- Do not use destructive reset or broad cleanup as a diagnostic shortcut.
- Do not expose secrets, tokens, OAuth material, raw private prompts, or account identifiers.
More from fearvox/multica-ultimate-workbench
workbench-design-docs
Product design, technical design documents, user-facing copy, specs, diagrams, and handoff documentation.
7workbench-token-context-discipline
Compact context, cache-aware execution, scoped evidence reads, and role-specific skill attachment discipline.
6workbench-gsd-tasking
Owner-scoped task decomposition with gates, rollback, verification commands, and smoke tests.
6workbench-memory-synthesis
Durable memory, session summaries, decision logs, issue closeout synthesis, and compact handoffs.
6workbench-implementation
Minimal-patch implementation, ops changes, scripts, automation specs, and local repository edits.
6workbench-research
Evidence-first research, architecture discovery, vendor documentation review, benchmark reading, and unknown-system analysis.
6