agentleFS
jezwebjezweb/vite-flare-starter/skills/enrich-error/SKILL.md

enrich-error

Skill49 starsChanged 3 months agoMITView on GitHub

SessionEnd hook for routines — turns raw error messages into actionable findings (e.g. "Error: 401" → "Gmail token expired — reconnect at /dashboard/connectors"). Routine-only.

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    If the error is a programming bug (TypeError, ReferenceError, schema mismatch), produce a short routine_error finding tagged for the …

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Enrich Error

Purpose

Raw error messages are useless to non-developer users. Error: fetch failed (status 401) doesn't tell anyone what to do.

This skill rewrites errors into findings with three properties:

  1. What happened — in plain English, no jargon.
  2. Why — the underlying cause if you can guess.
  3. What to do — the specific next step (link if possible).

Pattern

For each error, produce an inbox_add payload like:

{
  "kind": "routine_error",
  "summary": "<plain English what + actionable next step>",
  "importance": "medium",
  "reasoning": "<technical detail for debugging>",
  "suggestedAction": { "label": "<verb-led link text>", "link": "<dashboard path>" }
}

Common error patterns + rewrites

Raw errorPlain summarySuggested action
401 Unauthorized from Gmail"Gmail connection expired"Reconnect at /dashboard/connectors
403 Forbidden from Slack"Slack token doesn't have the scope this routine needs"Re-authorise in Connectors
429 Too Many Requests"Hit rate limit on <service>"(no action — auto-retries)
5xx from any service"<service> is down or having issues"(no action — wait it out)
corrupt or unsupported data"Couldn't process the file"Check the source file format
BudgetExceededError"Daily budget cap reached for this routine"Raise the cap on the routine detail page
Network timeout"Connection timed out reaching <service>"(no action — auto-retries)

Severity rules

  • high: auth/connector failures (user MUST act for the routine to keep working)
  • medium: transient errors that have happened ≥3 fires in a row
  • low: one-off transient errors (rate limits, timeouts) — log it but don't pester

When NOT to enrich

If the error is a programming bug (TypeError, ReferenceError, schema mismatch), produce a short routine_error finding tagged for the developer rather than the user, with the raw stack in reasoning. The user can't fix code; the dev can.

Tags to add when relevant: ["dev-bug"] or ["transient"] or ["auth-needed"].

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.