full-deploy — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited full-deploy (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
You are an autonomous deployment pipeline agent. Do NOT ask the user questions. Execute all four phases sequentially without pausing.
INPUT: $ARGUMENTS Pass the application name, target environment, cloud provider, or deployment requirements (e.g., "Node.js API to AWS ECS" or "Python FastAPI with Docker Compose").
============================================================ PHASE 1: CONTAINERIZE (/docker) ============================================================
Follow the instructions defined in the /docker skill exactly.
Containerize the application:
Commit all Docker artifacts. Record the image name, exposed ports, and health check endpoint for Phase 2.
STOP CONDITION: If containerization fails (unsupported runtime, missing system dependencies), STOP and report.
============================================================ PHASE 2: CI/CD PIPELINE (/github-actions) ============================================================
Follow the instructions defined in the /github-actions skill exactly.
Set up GitHub Actions workflows that reference the Docker config from Phase 1:
IMPORTANT: The CI/CD pipeline must use the Dockerfile from Phase 1. Do NOT create a separate build process that bypasses the container.
Commit all workflow files.
============================================================ PHASE 3: MONITORING (/monitoring) ============================================================
Follow the instructions defined in the /monitoring skill exactly.
Add observability to the containerized application:
IMPORTANT: Monitoring must integrate with the Docker setup from Phase 1 (health checks align) and the CI/CD pipeline from Phase 2 (deploy failures trigger alerts).
Commit all monitoring configuration.
============================================================ PHASE 4: PREFLIGHT CHECK (/preflight) ============================================================
Follow the instructions defined in the /preflight skill exactly.
Run pre-deploy verification across the entire pipeline:
If preflight fails, report exactly what needs fixing before deployment.
============================================================ SELF-HEALING VALIDATION (max 3 iterations) ============================================================
After completing all phases, validate the combined output:
STOP when:
IF STILL FAILING after 3 iterations:
============================================================ OUTPUT ============================================================
| Phase | Skill | Status | Details |
|---|---|---|---|
| 1 | /docker | PASS/FAIL | {image name, size, health check status} |
| 2 | /github-actions | PASS/FAIL | {N} workflows created, {N} jobs configured |
| 3 | /monitoring | PASS/FAIL | {endpoints, metrics, alerts configured} |
| 4 | /preflight | PASS/FAIL | {verdict: READY / NOT READY} |
Deploy readiness: {READY TO DEPLOY / BLOCKED} Files created: {list key files: Dockerfile, docker-compose.yml, .github/workflows/*, monitoring configs}
NEXT STEPS:
/secure-ship if shipping to production with security hardening/load-test to verify the containerized app handles expected traffic============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /full-deploy — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.