claudette-debug

Solid

Debug the running Claudette Tauri app by executing JavaScript in the webview and reading results back. Inspect Zustand store state, trace state changes, monitor sessions long-term, run end-to-end UAT, and diagnose UI bugs in real-time. Only works in dev builds.

AI & Automation 61 stars 10 forks Updated 2 days ago MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
60
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Claudette Debug Execute JavaScript inside the running Claudette Tauri webview via a TCP debug server on `127.0.0.1`. Dev-build only (`#[cfg(debug_assertions)]`). The server listens on port **19432 by default**, but the devshell `dev` helper auto-selects a free port (and writes a discovery file) so multiple dev instances can run in parallel against different branches. `debug-eval.sh` discovers the right instance automatically — you do not need to know the port. Details in [Port discovery](#port-discovery) below. ## Quick Start ```bash /claudette-debug status # One-shot workspace status (agent, messages, scroll, tools) /claudette-debug discover actions # List all store functions with parameter names /claudette-debug discover state # List all state slices with types and values /claudette-debug send "read README.md" # Send a chat message to the active workspace /claudette-debug wait # Block until agent goes idle (run_in_background) /claudette-debug screenshot # Capture screen, return image path for Read tool /claudette-debug state # Contextual store overview /claudette-debug eval 'return 1+1' # Execute arbitrary JS /claudette-debug monitor start # Start background session monitor ``` ## Prerequisites - App running via the devshell `dev` helper (or `cargo tauri dev`) — debug TCP server starts automatically - `python3` in PATH (used by eval helper) **Do NOT launch ...

Details

Author
utensils
Repository
utensils/claudette
Created
4 months ago
Last Updated
2 days ago
Language
Rust
License
MIT

Integrates with

Anthropic · AI

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

claudette

Drive the running Claudette desktop app from the command line — list and create workspaces, inspect chat transcripts/tool turns/attachments, answer or approve pending agent controls, send or steer prompts to chat sessions, schedule recurring cron-style agent routines, fan out batch manifests across many workspaces, list pull requests via SCM plugins, invoke arbitrary plugin operations. Use when the user asks to list/create/archive workspaces, inspect or control Claudette chat sessions, send a message to a Claudette session, schedule a recurring prompt or cron routine for a session, kick off a phase plan or multi-workspace fan-out, check PRs from a workspace, or otherwise interact with their open Claudette app from outside the GUI.

61 Updated 2 days ago
utensils
AI & Automation Solid

debug

Debug container agent issues. Use when things aren't working, container fails, authentication problems, or to understand how the container system works. Covers logs, environment variables, mounts, and common issues.

48 Updated today
sliamh11
AI & Automation Solid

verify

Build, launch, and drive Claudescope against sandboxed fixtures to verify a change end-to-end without touching real agent sources or ~/.claudescope.

13 Updated today
vladar107