Menü
Reproduce, isolate, fix, and verify bugs. Use for "debug", "this is broken", "fix the bug", and failing tests.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | Debug |
| description | Reproduce, isolate, fix, and verify bugs. Use for "debug", "this is broken", "fix the bug", and failing tests. |
| triggers | ["debug","this is broken","fix the bug"] |
Use this skill for bug reports, failing checks, broken UI behavior, regressions, and "make this work" requests.
Reproduce before changing code. Use workspace_context to find likely commands, then use shell_command for a targeted failing test, typecheck, log read, or repro script. Record the observed failure in plain terms.
Isolate the smallest responsible area by reading the failing file, nearby tests, and relevant call sites. Avoid broad rewrites. Once the cause is clear, make the narrowest fix that preserves existing patterns.
After editing, verify the original failure path first. Then run verify_workspace or the relevant focused check so the final result is not just "the edit saved." If the bug is visual and the user gave a URL, use frontend_qa after the code check.
Stop when the original failure is gone or when you can name the blocker and the next exact diagnostic step.
How changes are classified, gated, approved, committed, and shipped in the Lamprey Harness repo. Load this BEFORE making any change — code, docs, config, or release — or when you see terms like P-SPR, STS, verify gate, era-lock, commit trailer, push policy, or when a commit/push is rejected by a hook.
How Lamprey runs and ships — run modes, userData layout, Windows release artifacts, the one-command "Bucket" pipeline, macOS/Linux CI mirroring, GitHub publication, CDN purge, and failure recovery. Load when the user says "ship", "release", "tag it", "Bucket", or when a release step fails partway.
The multi-provider LLM domain pack for Lamprey — OpenAI-compatible streaming across 17 built-in providers (frontier labs, open-source hosts, keyless local runtimes) plus user-defined custom endpoints, per-provider quirks (reasoning field names, Anthropic's compat-layer limits, base-URL overrides), capability flags, the native-vs-fallback tool-calling contract, retry/backoff, retired-model handling, and the checklists for adding a model or a provider. Load when touching electron/services/providers/, debugging provider HTTP errors, or adding/retiring models.
Lamprey's load-bearing design decisions, the invariants that must hold, what was deliberately deleted, and the honestly-stated weak points. Load before modifying electron/ipc, electron/services, the provider or tool layers, or the renderer stores — or when you need to know WHY the system is shaped the way it is.
Recreate the Lamprey dev environment from scratch and get past its known traps — Node/Electron/better-sqlite3 ABI story, the ELECTRON_EXEC_PATH dev-server workaround, esbuild antivirus blocks, the tsconfig node/web split, electron-vite and electron-builder specifics. Load when setting up a machine, when npm install / dev server / build fails, or before touching build configuration.
Catalog of every Lamprey configuration axis — AppSettings keys with defaults and readers, inert retired keys, keychain/keys.json, custom models, loop and timeout knobs, environment variables, per-conversation runtime state — plus the exact checklist for adding a setting without breaking the parity-lock test. Load when reading/changing settings.json, adding a setting, or wondering what a flag does or whether anything still reads it.
