updating-ai-knowledgelisted

## Is this worth updating? Not every lesson belongs in a file. Before editing, pass these gates: 1. **Name the gap in one sentence.** *"This file says X, but the correct behavior is Y."* If you can't say that, you don't have the fix yet — synthesize from what the session produced 2. **Would the next agent hit the same wall?** If the problem was a one-off misread, a transient environment issue, or a one-time deploy workaround, the knowledge base isn't the problem 3. **Is the gap already covered somewhere?** Search the target file first. Duplicating a rule in a second location creates two things to maintain and eventually contradicts Stop if any gate fails. Not every session produces a knowledge update, and that's fine ## Route to the right file Work through these tests in order. The first match wins ### Skill (`~/Documents/harness/skills/`) **Test**: Would this fact be true in a different repo using the same tool or platform? If you swapped the repo but kept the tool, would the lesson still apply? Cross-repo knowledge about tools, platforms, workflows. Group by skillset folder (`project-skillset/`, `harness-skillset/`). Run `./skills/install.sh` from the harness repo root after adding or moving a skill directory **Guardrails**: Don't change `name:` — tied to symlinks and the loader. Edit `description:` only if triggering is wrong (fires when it shouldn't, or doesn't fire when it should) *Examples: Jira skill has a wrong field name. Terraform module changed its variab