Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Autonomous local-development debugging loop for Helmor bugs. Use when the user asks an agent to reproduce, diagnose, instrument, fix, or verify a Helmor local dev build issue using repeated local UI simulation, temporary logging, Tauri MCP/towery MCP, screenshots, DOM/accessibility snapshots, IPC traces, console/system logs, terminal/run-script logs, or multi-attempt verification. This skill coordinates with $helmor-debug-operate for operating the running desktop app.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -37% | 0% |
Use this skill to drive a bounded reproduce -> instrument -> inspect -> fix -> verify loop for Helmor local-dev bugs. Always use $helmor-debug-operate for actual local app control through Tauri MCP; this skill owns the debugging strategy and evidence discipline.
$helmor-debug-operate with real UI actions when possible. Start with screenshots, DOM/accessibility snapshots, IPC monitor, console/system logs, and terminal buffers.[debug-loop:<slug>], rerun the flow, then remove or justify the probe before finalizing..agent-contexts/<task-slug>/ with repro attempts, logs, screenshots, IPC, fix summary, and remaining uncertainty.not reproduced, preserve evidence, inspect code paths that should have fired, and report the most likely missing precondition.$helmor-debug-operate recovery steps. If the bridge remains unavailable, fall back to static code analysis and terminal tests, and label UI verification as blocked.$helmor-debug-operate stale-skill rules: reason from fresh screenshots/DOM/code, record a candidate skill update, and ask before editing that skill unless the user explicitly requested it.Use the available signals in this order:
$helmor-debug-operate's Call App Commands helper to run debug_list_terminal_buffers, then debug_read_terminal_buffer with the returned raw scriptType.Read references/debug-loop.md when the task needs the full loop checklist or when reproduction fails. Use scripts in scripts/ to summarize logs and build evidence packs instead of pasting raw dumps into the chat.
Other measured skills in the registry, with their headline benchmark lift.