creo-devops — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited creo-devops (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
DevOps expert specializing in CI/CD pipeline management, infrastructure coordination, and deployment automation. Self-sufficient agent with built-in CLI capabilities for GitHub, Cloudflare, Railway, and Stripe.
| Command | Description |
|---|---|
/creo devops deploy | Coordinate deployment workflow |
/creo devops github <cmd> | GitHub CLI operations (PRs, Actions, Secrets) |
/creo devops cloudflare <cmd> | Cloudflare operations (Workers, R2, KV) |
/creo devops railway <cmd> | Railway operations (Services, Deployments) |
/creo devops stripe <cmd> | Stripe operations (Payments, Webhooks) |
.claude/project-config.mdproject_id, hosting providers, deployment targets.claude/skills/creo-devops/creo-devops-{project_id}.md. This file contains project-specific infrastructure topology, Railway/Cloudflare/Vercel services, secret names, and deployment conventions. {project_id} comes from project-config.md. Always load it before doing work.This skill absorbs routing from the DevOps orchestrator. Specialized subagents exist for deep expertise:
| Subagent | Focus |
|---|---|
| creo-github-cli | Deep gh CLI expertise |
| creo-cloudflare-cli | Deep Wrangler/R2/KV/D1 expertise |
| creo-railway-cli | Deep Railway CLI expertise |
| creo-stripe-cli | Deep Stripe CLI expertise |
Handle most tasks directly. Only delegate to subagents for deeply specialized operations.
#### GitHub CLI (gh)
# Pull Requests
gh pr create --title "feat: ..." --body "..."
gh pr list / gh pr view <number> / gh pr merge <number> --squash
# Workflows
gh run list --limit 10
gh run view <run-id> --log-failed
gh workflow run pipeline.yml
# Secrets
gh secret list / gh secret set SECRET_NAME --body "value"#### Cloudflare Wrangler
npx wrangler deploy # Deploy worker
npx wrangler tail <worker-name> # Stream logs
npx wrangler deployments list # List deployments
npx wrangler secret put SECRET_NAME # Set secret
npx wrangler r2 object list <bucket> # R2 storage#### Railway CLI
railway list / railway status # Project info
railway up # Deploy
railway logs / railway logs -f # View logs
railway variables list / set / delete # Manage vars#### Analyze Current Pipeline
cat .github/workflows/pipeline.yml
ls -la .github/workflows/
gh run list --limit 10
gh workflow view pipeline.yml#### Debug Failed Workflow
gh run view <run-id> --log-failed
gh run view <run-id> --log
gh run rerun <run-id> --failed#### Classify Failures
Job failure type?
- SETUP: checkout, setup-node, cache restore failed
- BUILD: compile error, missing dependency, type error
- TEST: assertion failure, timeout, flakiness
- DOCKER: image build, container startup, health check
- ENV: missing secret, wrong env var, wrong port
- PERMISSION: token scope, branch protectionBefore modifying workflows:
| Problem | Fix |
|---|---|
| Cloudflare deploy failed | Check wrangler.toml, verify API token |
| Railway deploy failed | Check railway logs, verify env vars |
| Build failed | Check error logs, verify env vars and dependencies |
| Port conflict | Use unique ports per job |
| Secret not found | Verify name matches exactly (case-sensitive) |
Use WebFetch to access official documentation when needed:
docs.github.com/en/actionsdevelopers.cloudflare.com/workers/docs.railway.appdocs.docker.comLoad these on demand for extended guidance:
| File | Purpose |
|---|---|
references/workflow-patterns.md | GitHub Actions workflow templates |
references/deployment-checklist.md | Pre-deployment verification |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.