agentleFS
nexmoenexmoe/VidBee/skills/diagnose-task/SKILL.md

diagnose-task

Skill11k starsChanged 48 days agoMITView on GitHub

Investigate failed or stalled tasks using their status, errors and logs. Use to recommend recovery steps or prepare feedback for a suspected VidBee defect.

Trending

Less talk lately.about the whole repository

Dec 2025: 3 mentionsJan 2026: 4 mentionsFeb 2026: 0 mentionsMar 2026: 2 mentionsApr 2026: 1 mentionMay 2026: 1 mentionJun 2026: 0 mentionsJul 2026: 2 mentionsAug 2026: 2 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 1 mention
Dec 2025Jun 2026Nov 2026
Mentions a month of the nexmoe/VidBee repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about nexmoe/VidBee

The biggest 5 of 17 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 17

Talked about on Bluesky, YouTube, GitHub and the web (17 times).

On Bluesky · 12

7 more on Bluesky

On YouTube · 3

On GitHub · 1

On the web · 1

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use the supplied task ID. If it is missing, find the relevant task with list_tasks or ask which task needs help.

    line 10
  2. Very specific:

    Read relevant public settings with get_settings only when needed.

    line 12
  3. Distinctive:

    Start with reasonable supported in-app remedies.

    line 17
  4. Very specific:

    If the evidence points to a VidBee defect or a fix requires a developer, explain why and offer GitHub or email feedback.

    line 22
  5. Distinctive:

    Keep credentials and raw private logs out of public issue URLs.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Diagnose a task

Inspect the evidence

  1. Use the supplied task ID. If it is missing, find the relevant task with list_tasks or ask which task needs help.
  2. Load get_task through load_tools and inspect the current status, error details, retry state, child tasks and latest logs. Do not infer progress or failure causes from a model-authored card or an old conversation.
  3. Read relevant public settings with get_settings only when needed. If a tool or evidence is unavailable, explain the limitation instead of inventing details.

Suggest supported recovery

  • Distinguish link, permissions, cookies, network, configuration and upstream website/extractor failures from a suspected VidBee software defect. A failed download alone does not prove an application bug.
  • Start with reasonable supported in-app remedies. Explain the evidence and any uncertainty, then give the next useful step. Avoid repeated retries that cannot address the cause.
  • A diagnosis request asks for an explanation and recommendations. Keep task changes and settings changes within the user's actual request and existing tool approvals.

Escalate a suspected VidBee defect

  • If the evidence points to a VidBee defect or a fix requires a developer, explain why and offer GitHub or email feedback. Do not route ordinary source or configuration problems to the developers without a reason.
  • Help draft a concise report with the task ID, reproduction steps, expected versus actual behavior, relevant error, and app/OS versions when known. Clearly identify missing facts; never invent versions or claim a bug is confirmed without evidence.
  • Point to the GitHub and email feedback buttons beside the failed task. The email button opens a report preview with copy/download options for the redacted diagnostic report, {{feedback.filename}}.
  • Keep credentials and raw private logs out of public issue URLs. Let the user review and submit the report; never claim it has already been sent.

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.