← ClaudeAtlas

sync-statuslisted

Read application status from ATS dashboards via the session browser, normalize each raw label to the canonical tracker vocabulary, and hand real transitions to track-outcomes — which remains the only writer of workspace/tracker.json. Opt-in, user-initiated, read-only at the portal.
CodesWhat/careerrat · ★ 3 · AI & Automation · score 72
Install: claude install-skill CodesWhat/careerrat
# sync-status > **Runs under AGENTS.md.** These contracts bind without being restated here: Privacy Invariant (`current_base` never outbound), Honesty Firewall, Placeholder/Bracket Ban, Gate Write-back, Domain-Neutral Rule, Browser Automation Contract, Activity Pulse logging, Tracker verify+snapshot, and Sent-Clears-Draft. Inline reminders at point-of-use are intentional; standalone restatements point back to the relevant AGENTS.md section. ## STEP 0 — Consent gate (hard stop) Run: ``` careerrat automation status --json ``` Inspect the `capabilities.status_polling` entry. The applicable platforms are `greenhouse`, `workday`, `ashby`, and `lever`. For each platform, `allowed: true` means all three conditions are met: the capability global switch is on, that platform's per-capability switch is on, and the platform's one-time ToS consent is recorded. This is the three-part AND from `mayRun()` in `src/core/automation/consent.mjs` — never hardcode it here. If **no platform** shows `allowed: true`, explain exactly how to opt in, then stop — do not open a browser: 1. Read the platform's terms of service yourself. 2. Record consent: `careerrat automation consent <platform> --write` 3. Enable the capability: `careerrat automation enable status_polling --write` 4. Enable for the specific platform: `careerrat automation enable status_polling <platform> --write` 5. Verify: `careerrat automation status --json` This skill is always user-initiated. Never run it unprompted or on a sc