SSO, RBAC & audit · Any model, your keys · No seat tax
The daily compliance-drift runbook: reading the policy, checking bucket/tag/role state, cross-referencing the audit logs, and drafting proposed remediation.
kortix marketplace install kortix-starter:compliance-sweep-skillcat memory/compliance-policy.md 2>/dev/null || echo "(no policy file yet — using the defaults below)"
memory/compliance-policy.md from them on this run:owner and environment.*:* or an unscoped iam:PassRole.memory/compliance-policy.md (Step 0 above), edit it to reflect the
requested rule, and confirm the change back to the human. No AWS calls, no
findings, no change request — the policy file itself is the human-authored
input the rest of this skill checks against.list-buckets
and list-roles return the same full set no matter which region you ask from.
List and evaluate each one exactly once per sweep, outside any region loop:for bucket in $(aws s3api list-buckets --query 'Buckets[].Name' --output text); do
bucket_region=$(aws s3api get-bucket-location --bucket "$bucket" --query 'LocationConstraint' --output text)
[ "$bucket_region" = "None" ] && bucket_region="us-east-1"
aws s3api get-bucket-policy-status --bucket "$bucket" --region "$bucket_region" 2>/dev/null
aws s3api get-bucket-tagging --bucket "$bucket" --region "$bucket_region" 2>/dev/null
done
for role in $(aws iam list-roles --query 'Roles[].RoleName' --output text); do
aws iam list-attached-role-policies --role-name "$role"
aws iam list-role-policies --role-name "$role"
done
list-*, get-*). The credentials are brokered
server-side and read-only — you use them, you never see the raw key.$(echo "{{aws_regions}}" | tr ',' ' ') — never re-loop the global
bucket/role checks above.| Check | Violation condition | Finding type |
|---|---|---|
| Bucket exposure | PolicyStatus.IsPublic = true and the bucket isn't allow-listed | Newly public bucket |
| Tagging | Missing a required tag key from the policy | Untagged resource |
| IAM scope | Role holds *:* or an unscoped iam:PassRole | Over-broad role |
$bucket_region).aws cloudtrail lookup-events \
--lookup-attributes AttributeKey=ResourceName,AttributeValue="<resource-id>" \
--max-results 10 --region <region-per-rule-above>
project.cr.open (or one per resource
group when several findings share a fix). Title it with the resource and
violation, e.g. compliance: newly-public bucket acme-uploads. The CR body is
the diagnosis from Step 3 (what, when, who) plus the proposed fix. A human
reviews and applies it — you stop at opening the CR.The role-to-grant policy, extra-scrutiny cases, the approval handshake, and how an applied grant gets logged.
Get a complete picture of any company or person before outreach. This skill always works with web search, and gets significantly better with enrichment and CRM data.
Daily runbook for budget pacing, CPA/ROAS drift, underperformer detection, and anomaly flags across Google Ads and Meta Ads, plus how to rank and word optimization recommendations.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Extract-and-match runbook for incoming vendor invoices: line-item extraction, PO/prior-invoice matching, duplicate + overcharge detection, and the ledger + approval hand-off.
Search, dedupe against the seen-mentions ledger, classify sentiment and notability, and post a digest with suggested response drafts — the daily brand-monitor runbook.