mcpField
O
observe-before-editing

observe-before-editing

github.com/parcadeiDevelopment3.9k483 installsUpdated 39w ago
Repository

About observe-before-editing

A debugging skill that guides developers to inspect actual outputs, files, and logs before changing code. It emphasizes verifying evidence rather than assuming what failed.

Key features

  1. 01Check whether directories and files exist
  2. 02Inspect logs for errors
  3. 03Run failing commands manually
  4. 04Compare project and global paths

Use cases

  1. 01Investigate whether a hook ran
  2. 02Confirm cache files were created
  3. 03Use command errors to locate failures

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/parcadei/continuous-claude-v3 --skill observe-before-editing

After installing, type/observe-before-editingin Claude Code to confirm it loaded.

Details

From the project README

Observe Before Editing

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

Pattern

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

DO

  1. Check if expected directories exist: ls -la .claude/cache/
  2. Check if expected files were created: ls -la .claude/cache/learnings/
  3. Check logs for errors: tail .claude/cache/*.log
  4. Run the failing command manually to see actual error
  5. Only then edit code

DON'T

  • Assume "hook didn't run" without checking outputs
  • Edit code based on what you think should happen
  • Confuse global vs project paths (check both: .claude/ and ~/.claude/)

Source Sessions

  • 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

Comments

Markdown supported