agentleFS
Sign inStart free
uplikauplika/uplika-plugin/skills/troubleshoot/SKILL.md

troubleshoot

Skill3 starsChanged 34 days agoMITView on GitHub

When something did not work: read the error code, call get_help, then retry, reconnect or wake the Naver extension, or report it to the team.

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ecosystem-reference, fractal-delegation and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • naman10parikhSkill

    ecosystem-reference

    Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.

    Also in 5 projects that use this

  • naman10parikhSkill

    fractal-delegation

    Also in 5 projects that use this

  • MicrosoftSkill

    act-on-feedback

    Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.

    Also in 3 projects that use this

  • MicrosoftSkill

    generate-run-commands

    Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

    Also in 3 projects that use this

  • KirchliveSkill

    skill-routing

    Decides which of the installed skills a task needs and loads them before the work starts. This skill should be used at the beginning of any multi-step task — build, fix, refactor, migrate, review, plan, release, research, write, design, video — and again at every phase change, after context compaction, and when work moves into a different part of the codebase. Use it for requests like "let's build X", "fix this bug", "refactor Y", "plan the migration", "review this", and also when the user asks which skill applies, why a skill did not fire, or asks to check what is available.

    Also in 5 projects that use this

  • sublimotionSkill

    agent-runtime

    Launch and manage detached agent runs on EKS via the agent-runner CLI. Use when the user says "launch an agent run", "agent runtime", "agent-runner", "run this spec on the cluster", "check run status", "agent run logs", or "stop a run". Do NOT use for writing the agent-runner code itself (edit the sibling ../agent-runner repo), Terraform of the foundation (use terraform-automation), or GPU serving deployments (use infra-deployer).

    Also in 5 projects that use this

  • +6 more from naman10parikh

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 22 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this when a call fails, a post is stuck, an automation did not react, a DM did not arrive, or the person asks why something happened.

    line 8
  2. Very specific:

    Read the error code from the response (error.code), or the target's reason from get_post.

    line 12
  3. Very specific:

    Call get_help with that code (or a short query in any language, and platform when it is one channel).

    line 13

“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “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

Troubleshoot

Use this when a call fails, a post is stuck, an automation did not react, a DM did not arrive, or the person asks why something happened.

Procedure

  1. Read the error code from the response (error.code), or the target's reason from get_post.
  2. Call get_help with that code (or a short query in any language, and platform when it is one channel). Use locale for the person's language. Give them the answer's steps and its link.
  3. Act on it with the table below. Never repeat the same failing call more than once without changing something.
  4. If that does not solve it and the person wants the Uplika team to look, ask them first ("Should I send this to the Uplika team?"). Show what you will send: their own words (personSaid, in their language, not rewritten) and your account of what you tried (summary). On their OK call report_problem once, with the code, requestId, tool, post and helpId you have. Do not paste logs, tokens or keys; Uplika attaches its own request records. Tell them the reply goes to the email on their Uplika account, without promising when. A repeat of the same problem within a day is recorded but not emailed again, so do not send it twice. If it answers support_daily_limit, point them to Contact at the bottom right of the dashboard (faq:report-to-team).

By code

CodeWhat it meansWhat to do
reconsent_requiredThe connected account is missing a permission this action needs: the DM permissions, or the own permission of liking on Instagram or of Threads mentions (faq:dm-reconnect)Send the person to https://uplika.com/dashboard/connections to reconnect that account and approve every permission (when connecting through Facebook, Edit settings rather than Continue with previous settings), then try again
feature_in_reviewThe permission is still in the platform's review (faq:feature-in-review)Reconnecting does not help until the review passes. Say so and stop
account_disconnectedThe post's account was disconnected (faq:disconnected-posts)Reconnect the same account; the post comes back with it
workspace_requiredThe account has more than one workspace (faq:workspace-required)Show the listed workspaces, ask which, pass workspaceId
research_tool_disabledA research tool still in beta is turned off for agents (released tools never answer this)Ask the person once to turn it on at the link in the error, and do not retry until they say it is on
window_closedA DM outside the messaging window (faq:dm-24h-window)Nothing can be sent until the person writes again
naver_rate_limitedNaver capped posts for that IDWait retryAfterSeconds; the draft is already in Naver, do not send again
youtube_quota_exhausted · youtube_daily_capUplika's daily YouTube limit, which everyone on Uplika shares, ran out. It is not the person's account (faq:youtube-daily-limit)Wait until resetsAt (midnight Pacific time), then try again or retry_post. A scheduled YouTube-only post keeps its schedule; publish_now answers 429 until resetsAt. Do not ask them to reconnect
bridge_offlineThe Chrome running the Uplika extension is not connected right now (faq:naver-extension-offline)Call bridge_status and follow its nextStep (see Naver Blog extension below). Naver posts wait in the queue (the FAQ says for how long), so do not publish again
a target still publishingThe post is still going out (faq:publish-still-publishing)Check get_post later; do not publish again
a failed targetThe channel refused itFix the cause the reason names, then retry_post

Naver Blog extension

Naver Blog posts are written by the Uplika extension in the person's Chrome (faq:naver-extension-offline). Call bridge_status. When a response carries bridge.nextStep:

  • run_wake: Chrome with the extension is closed. Show the person bridge.userMessage and the wake command for their system. With a terminal on the same computer you may offer to run it, but ask first. Retry once after they say Chrome is open.
  • ask_user_login, ask_user_update: tell the person bridge.userMessage.

A Naver category the person names but list_accounts does not show: refresh_account re-reads the blog's categories.

Tools

  • get_help: the answer, steps and link for a code or question
  • report_problem: send the problem to the Uplika team when get_help did not solve it and the person agreed
  • get_post: per-channel status and the reason a target failed
  • retry_post: retry failed targets after the cause is fixed
  • publish_now: send a scheduled or draft post now (a YouTube-only post answers 429 on a YouTube-limit day and keeps its schedule)
  • refresh_account: re-read a Naver Blog account's categories
  • list_accounts: confirm the categories (and accounts) after a refresh
  • bridge_status: whether the Naver Blog extension is online, and the wake commands

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.

Check your setup, free