agentic-production-readiness
Skill4 starsChanged 5 months agoMITView on GitHub
Prepare an AI agent system for production operation. Cover SHIELD controls, sandbox/canary/production rollout, OpenTelemetry observability with GenAI semantic conventions, Agent Card drafting, governance, and post-deploy monitoring. Use for production readiness checks, go-live checklists, agent monitoring, agent cards, canary rollout, or deploying agent systems. Do NOT use for standard web-app deployment, local setup, feature work, or non-agent infrastructure tasks.
In this repository3 other files it gives its agents.
- agentic-evalsSkill
- agentic-security-reviewSkill
- agentic-specSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Use this skill when an agentic system is close to deployment or operational handoff.
- Distinctive: line 34
Verify the current A2A location and schema before publishing.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agentic Production Readiness
Use this skill when an agentic system is close to deployment or operational handoff. Verify current protocol details instead of hardcoding unstable specs.
Workflow
- Identify deployment target, owner, data sensitivity, tool permissions, and rollback path.
- Apply SHIELD:
- Separation of duties.
- Human approval for high-impact actions.
- Input/output validation.
- Enforced security models.
- Least agency and least privilege.
- Defensive controls such as sandboxing and SCA.
- Plan staged rollout: sandbox, canary, then production. Define rollback triggers before release.
- Configure observability: logs, traces, metrics, token/cost tracking, model versions, tool calls, latency, and policy versions.
- Draft an Agent Card if external discovery or agent-to-agent use is required. Verify the current A2A location and schema before publishing.
- Generate
DEPLOY_CHECKLIST.mdfromassets/templates/DEPLOY_CHECKLIST.md.
Governance Checks
- Named accountable owner.
- Credential source and rotation policy.
- Memory retention and review policy.
- Eval thresholds and release gates.
- Incident response and audit trail.
- Regulatory mapping only when the domain requires it.
References
Read ../agentic-engineering-sdlc/references/day5_prototype_to_production.md
for Agent Ops, durable execution, and deployment patterns.
Done Criteria
- Rollout and rollback are explicit.
- Observability covers behavior, tools, cost, and safety.
- Agent Card details are marked draft until checked against the current spec.
- Governance and on-call ownership are assigned.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.