Menü
Explain errors without editing files. Use when the user wants to understand an error or crash but not immediately fix it.
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
Generate commit messages for staged git changes. Use when the user asks to generate a commit message or wants help writing commit messages.
Debug errors using logs and stack traces. Use when the user shares an error message, crash log, or runtime issue to fix.
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
Analyze code for logical errors, runtime bugs, and edge cases. Use when the user wants a code review, asks to find bugs, or wants to check code correctness.
Image manipulation via a bundled script, resizing, rotation, flipping, cropping, padding, format conversion (JPEG/PNG/WebP/TIFF/HEIC), transparency operations (remove/replace/extract/blend), grayscale conversion, auto-cropping borders, and file size optimization.
Convert documents to Markdown. PDFs go through the LlamaParse API (best quality, costs credits, tier selectable) or a local PyMuPDF engine (free, offline, no API key); other formats (DOCX, PPTX, XLSX, HTML, EPUB) are converted locally with markitdown.
| name | explain-issue |
| description | Explain errors without editing files. Use when the user wants to understand an error or crash but not immediately fix it. |
When explaining an issue, follow every step in order:
Check input: If no error message was provided, stop and ask for the exact error text or log, plus the relevant file if it is not already available.
Hard rule, no edits: Do NOT edit, create, or delete any file. This skill only explains. If the user wants the fix applied, tell them to say so explicitly.
Break down the failure in this order:
Show the suggested fix as a snippet (before/after), clearly labeled as a suggestion the user can apply themselves.
Output template (use these exact sections):
## What the error means
<plain-language translation, 1-2 sentences>
## How it happened
<short chain of events>
## Root cause
<the single underlying cause>
## Suggested fix (not applied)
<before/after snippet>
## Why this fix works
<1-2 sentences>
Guardrails: no file edits under any circumstances; if multiple root causes are plausible, list them ranked with reasoning; keep the whole answer under 40 lines.