agentleFS
Sign inStart free
lilly-buildslilly-builds/ads-cooking/skills/check/SKILL.md

check

Skill0 starsChanged 2 months agoMITView on GitHub

Check that the Meta connection works, before publishing or when something has stopped working. Tests the token, the ad account, the page, and lead form access in the order they usually break, and names the fix for whichever one failed. Read-only, spends nothing. Use when the user says "/ads-cooking:check", "is my Meta connection working", "check my token", "my ads stopped working", or before any publish.

  • Reads credentials

80 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval 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.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

Create a free account to mount
Files
SKILL.md

Check the Meta connection

Four reads, in the order things actually break. Run this first whenever anything is wrong.

Run it

PYTHONPATH="${CLAUDE_PLUGIN_ROOT}" python3 -m adscooking check

Exit code 0 means everything works and they can publish. 1 means the account, page or forms need attention. 3 means the setup itself is broken, which now includes a dead token: a key that needs regenerating must never be reported as the ads being in trouble.

Reading the result

It checks the token, then the ad account, then the page, then lead form access. It stops being useful to guess past the first failure, so fix them in order.

Lead forms failing while everything else passes is the common one, and it is almost always the same cause: the system user has the ad account but was never given a task on the page. Fix it in Business Settings by giving the system user MANAGE or ADVERTISE on the page.

Everything failing at once with Meta's generic error usually means Meta is down, not that anything is wrong with the setup. Wait an hour and re-run. Do not regenerate the token and do not rebuild anything: see ${CLAUDE_PLUGIN_ROOT}/context/api-notes.md.

A token error means it expired or was revoked. Generate a new one in Business Settings under Users, System users, and update the .env file. Never paste the token into chat.

The expiry line

A clean run ends with the token's expiry date. Say it out loud and tell them to write it down. /ads-cooking:pulse warns 14 days out, but only on a token that still works: once it has expired, the warning that would have prevented it is the thing that stops running. This line at setup time is the only chance to diary it.

What to tell the user

Lead with whether they can publish or not. If something failed, give them the one fix for the first failure, not a list of everything that might be wrong.

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