Check the official OpenAI, GitHub, npm, and Cloudflare status pages and produce an evidence-backed release health brief. Collect live status across four AI delivery dependencies with Lexmount Web Fetch, verify key pages in a cloud browser, and return an auditable GO, CAUTION, HOLD, or UNKNOWN decision.
Before your first run, search for and install the required Skills inside the WorkBuddy app.
Go to Experts, Skills & Connectors, choose Skills, then open SkillHub.
Enter lexmount in the search field and confirm that both Lexmount Skills appear.
Click + on both cards. After the installed confirmation appears, verify that both Skills are enabled.
Skills load immediately after installation, so a restart is usually unnecessary. On first use, each Skill may download its Rust CLI and open a browser for Lexmount OAuth. Never paste an API key into the conversation. If the prompt returns SKILL_REQUIRED, confirm that both Skills are installed and enabled.
Prerequisite:
Use the installed and enabled WorkBuddy Skills lexmount-webfetch and lexmount-browser. If either Skill is unavailable, stop with SKILL_REQUIRED, name the missing Skill, and tell the user to complete the WorkBuddy setup for this template. Do not create replacement Skills or use other web tools.
Follow each Skill's bundled bootstrap and doctor instructions. Start OAuth/PKCE login only when doctor reports missing credentials, wait for the user to authorize, and never request a pasted API key. Continue only when both doctor checks are ready.
Task:
Create an evidence-backed release-readiness brief using these official public status pages:
- OpenAI: https://status.openai.com/
- GitHub: https://www.githubstatus.com/
- npm: https://status.npmjs.org/
- Cloudflare: https://www.cloudflarestatus.com/
Check each provider's current status, release-critical components, active incidents, maintenance, and any material incident resolved within the previous 24 hours.
Decision rules:
- HOLD: a release-critical component has a major outage or is unavailable.
- CAUTION: an active incident, degraded service, partial outage, relevant maintenance, or material recent incident could affect a release.
- GO: all four providers explicitly report normal operation for relevant components.
- UNKNOWN: required evidence is missing, contradictory, or insufficient. Never treat unknown as normal.
Execution:
1. Create artifacts/workbuddy-release-readiness. If it already exists, append a UTC timestamp.
2. Use lexmount-webfetch first for all four URLs. Record requested_url, final_url, accessed_at_utc, overall_status, relevant components, current incidents, material incidents resolved within 24 hours, maintenance, original time text, and warnings. Convert times to UTC only when the source states a timezone.
3. Use lexmount-browser when a source is missing, conflicting, or non-operational. Even if every page is normal, open the Cloudflare Status Overview with lexmount-browser and save at least one screenshot as visual evidence.
4. Keep all browser activity read-only. Do not subscribe, enter contact information or webhooks, change settings, sign in, or submit forms.
5. Write brief.md, facts.json, evidence/*.png, and run-summary.json. Every material conclusion must reference a source_id from facts.json, and unknown values must never be invented.
6. Close every temporary Session.
Acceptance:
Every URL must have an explicit result; all required files must exist and be non-empty; all JSON must parse; every material conclusion must have a source and access time; every declared screenshot must exist; and every temporary Session must be closed. Return SUCCESS when all sources and cleanup succeed, PARTIAL_SUCCESS when any source or cleanup step fails, and FAILURE when fewer than two sources succeed. release_readiness must be UNKNOWN whenever evidence is insufficient.
Cleanup:
On success, failure, timeout, or cancellation, close only temporary Sessions created by this task. Do not close WorkBuddy, pre-existing Sessions, or persistent Contexts. Retain all generated evidence.
Return:
Report only the status, release_readiness, successful and failed source counts, brief path, facts path, evidence path, run summary path, screenshot count, cleanup result, and sanitized error summary. Do not expose API keys, Project IDs, Session IDs, connect URLs, WebSocket URLs, OAuth details, or credentials.