agentleFS
creanlabcreanlab/agent-genome-lab/.agents/skills/api-error-troubleshooting/SKILL.md

API Error Troubleshooting

Skill2 starsChanged 4 months agoMITView on GitHub

Guide users through resolving 4xx and 5xx API errors.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When operating in the support domain.

    line 13
  2. Distinctive:

    When resolving incidents related to api error troubleshooting.

    line 14
  3. Distinctive:

    If the issue requires manual human intervention.

    line 17
  4. Distinctive:

    If the domain does not apply.

    line 18
  5. Distinctive:

    Ask the user for the exact endpoint, HTTP method, and payload they used.

    line 29
  6. Distinctive:

    If 401/403, advise checking the Authorization header and token expiration.

    line 32
  7. Distinctive:

    If 422, explain the validation error based on the response payload schema.

    line 35
  8. Distinctive:

    If 500, escalate to engineering with a constructed cURL reproduction of the request.

    line 38
  9. Distinctive:

    Always verify changes in a staging environment before applying to production.

    line 48
  10. Distinctive:

    Do not execute destructive commands without explicit authorization.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

API Error Troubleshooting

Guide users through resolving 4xx and 5xx API errors.

When to use

  • When operating in the support domain.
  • When resolving incidents related to api error troubleshooting.

When not to use

  • If the issue requires manual human intervention.
  • If the domain does not apply.

Triggers

  • Pattern: api-error-troubleshooting
  • Keywords: support, api

Inputs

  • Context from the current user session or incident report.

Steps

1. Step 1

Ask the user for the exact endpoint, HTTP method, and payload they used.

2. Step 2

If 401/403, advise checking the Authorization header and token expiration.

3. Step 3

If 422, explain the validation error based on the response payload schema.

4. Step 4

If 500, escalate to engineering with a constructed cURL reproduction of the request.

Success signals

  • The task is resolved without regressions.
  • Logs confirm the procedure was successfully applied.

Failure modes

  • Incorrect application of the steps leading to side effects.

Safety notes

  • Always verify changes in a staging environment before applying to production.
  • Do not execute destructive commands without explicit authorization.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.