agentleFS
neonwattyneonwatty/job-apply-plugin/skills/account-setup/SKILL.md

account-setup

Skill139 starsChanged 4 months agoMITView on GitHub

Inspect or configure Job Apply account and sign-in metadata for a supported ATS portal without handling credentials or verification codes.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Read answer-memory to resolve <plugin-root>, initialize the Store, and follow its private-file and revision rules.

    line 13
  2. Distinctive:

    Use only the packaged router:

    line 15
  3. Distinctive:

    After classification, read supported account flows for the matching adapter and mutation rules.

    line 23
  4. Distinctive:

    When setup is complete or deferred, hand ordinary application work back to job-apply.

    line 33

≈ “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

Account Setup

Resolve account and sign-in readiness through the shared Store contract. This skill configures redacted local metadata; it does not sign in, create an account on an ATS, or prove that a browser session is ready.

Start from the canonical contract

Read answer-memory to resolve <plugin-root>, initialize the Store, and follow its private-file and revision rules. For a first-use or cross-skill handoff, read the shared workflow map.

Use only the packaged router:

node "<plugin-root>/apps/companion/command.mjs" store account-flow-classify --url "$portal_url"

Classify the exact HTTPS portal or application URL supplied by the user. Route on the returned status, adapterId, flowKind, and accountRequired; do not recreate hostname or path matching in prose or shell. An unresolved classification is a stop, not permission to guess or persist a record.

After classification, read supported account flows for the matching adapter and mutation rules.

Keep values and authority out of this workflow

Never request, read, copy, print, transmit, or persist passwords, email values, one-time codes, recovery data, raw credential references, cookies, tokens, or browser secrets. Do not use an email value already visible elsewhere. Workday credentials remain exclusively in macOS Keychain and user-controlled native setup. Passwordless MyGreenhouse never gains a password or credential-provider record.

Use public redacted Store results only. Never read Store files directly or call authenticated Companion HTTP routes with hand-built session data. The Accounts & Sign-in workspace owns revision-safe clearing and removal controls and displays browser-session readiness separately; it does not establish or infer a live session. A revision conflict requires a fresh inspection and user review; never retry blindly.

Persisted configuration, portable classification, and native execution readiness are separate facts. A saved account record is not evidence of an active browser session, a usable credential, or authority to operate a live ATS. Leave sign-in, account creation, email-code entry, CAPTCHA, MFA, legal consent, and recovery to the user.

When setup is complete or deferred, hand ordinary application work back to job-apply. This handoff does not grant browser-fill or final-action authority.

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.