Observe Before Editing

by parcadeid07ff4b06b62No license3.9K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 8 months ago

AI-generated overview

Guides checking actual system outputs before editing code to fix a bug.

What it does: This skill provides a short debugging discipline: before changing code, verify what the system actually produced. It lists steps such as listing expected directories and files, tailing logs for errors, and running the failing command manually to see the real error. It also lists pitfalls, including assuming a hook did not run and confusing global and project paths.
When to use it: Use it when a bug or failure is suspected and the cause is not yet confirmed, especially when a hook, cache, or indexing step appears not to have run. It is meant to be applied before making code edits.
Requirements: No scripts or special tooling; it is instructions only. It assumes the agent can run shell commands such as ls and tail and can inspect project and home directories.

Before editing code to fix a bug, confirm what the system actually produced.

Outputs don't lie. Code might. Check outputs first.

a541f08a: Token limit error was invisible until manual run revealed it
6a9f2d7a: Looked in wrong cache path (~/.claude/ vs .claude/), assumed hook failure
a8bd5cea: Confirmed hook worked by finding output files in project cache
1c21e6c8: Verified Artifact Index indexing by checking DB file exists

Source and attribution

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.