titan-iac/services/hermes/skills/master-hermes-on-atlas/references/mastery-rubric.md

# Mastery and claim rubric

## Performance levels

| Level | Evidence |
| --- | --- |
| Exposed | Recognizes terms but needs the path and commands supplied. |
| Assisted | Completes a lab with hints and can explain the result afterward. |
| Independent | Selects safe tools, gathers fresh evidence, and reaches a defensible result without hints. |
| Mastery | Handles ambiguity and failure, teaches the architecture, improves the reusable workflow, and preserves security boundaries. |

Score each domain separately:

1. Architecture and request routing.
2. Models, context, GPU ownership, and fallback.
3. Sessions, files, profiles, logs, and recovery.
4. Tools, skills, plugins, MCP, channels, webhooks, and cron.
5. Identity, RBAC, network, credentials, approvals, and auditability.
6. Jenkins/Flux/Kubernetes/metrics evidence correlation.
7. Clear triage findings and minimal repo-side proposals.
8. Skill creation, evaluation, and iteration.

Never award `Independent` from a verbal answer alone when the lab calls for live
or fixture evidence. Never award `Mastery` until Brad has led at least two
different real incidents and improved a workflow based on what failed.

## Interview claim audit

| Claim | What supports it | Minimum demonstration |
| --- | --- | --- |
| Hermes runs in the Kubernetes cluster | Flux manifests and live workloads | Trace browser, agent, model gate, Ollama, PVC, and service account. |
| Hermes fits existing automation | Operator config, internal evidence URLs, triage skill | Complete a triage using Ariadne, Jenkins, Git/Flux, cluster health, and metrics. |
| Hermes follows Brad's triage path | `$triage-titan-test-failures` procedure | Lead two evidence-backed cases with facts separated from inference. |
| Repeated workflows become reusable skills | Versioned triage/training skills plus writable user skill area | Build, test, and improve one skill from a repeated real workflow. |
| Access starts read-only and scoped | RBAC, NetworkPolicy, separate identities and state | Produce and explain the allow/deny matrix from live authorization checks. |
| Human approval protects changes | Approval config, deny patterns, Flux workflow | Identify every mutation in a proposed incident response and stop before it. |
| Local GPU gracefully yields to gaming | Owner state, model gate, fallback | Explain or observe a Wolf ownership window and verify continued fallback service. |
| OpenClaw previously ran and was replaced | `1bc58e10` deploys the OpenClaw triage stack; follow-up commits add gateway/OIDC/persistence; `97ecb36b` replaces it with Hermes; `bb5e286f` retires the dependency; the bound `openclaw-home` PVC remains without a workload | Inspect the commits and live Flux/PVC state, then explain what they prove versus what depends on Brad's personal recollection. |

## Triage answer scoring

Award one point for each:

- names the correct failure class;
- cites timestamped/build-specific evidence;
- labels inference;
- checks evidence freshness;
- identifies realistic blast radius;
- orders read-only next checks;
- proposes the smallest Flux/repo-side change or says evidence is insufficient;
- isolates approval-required actions;
- avoids invented resources, logs, metrics, or commits;
- remains concise enough for an operator to act on.

Scores below 8/10 require another incident drill. Any invented evidence or
unacknowledged mutation caps the result at `Assisted`.

## Progress record format

When Brad approves recording progress, use this compact structure:

```markdown
# Hermes training progress

- Last session: <UTC timestamp>
- Current level: <per-domain summary>
- Completed: <labs with evidence>
- Needs repetition: <specific gaps>
- Next lab: <one lab>
- Safety findings: <none or concrete issue>
- Claim status: <supported, partially supported, unproven>
```

Append evidence links or command summaries; never record tokens, cookies,
credentials, device codes, or Secret values.