cncf-agent-evaluation-reviewer

name	cncf-agent-evaluation-reviewer
description	Review Agent Evaluation using its official documentation and repository in the AI Agent / Evaluation category. A generative AI-powered framework for testing virtual agents
version	1.0.0
since	2026-08-27
last_modified	2026-08-27
authors	["platform-engineering"]
stability	stable
min_platform_version	{"codex":"unknown","amazon-q":"unknown","antigravity":"unknown","auggie":"unknown","bob":"unknown","claude-code":"unknown","cline":"unknown","codebuddy":"unknown","continue":"unknown","costrict":"unknown","crush":"unknown","github-copilot":"unknown","gitlab-duo":"unknown","factory":"unknown","forgecode":"unknown","opencode":"unknown","openhands":"unknown","cursor":"unknown","roo-code":"unknown","kiro":"unknown","junie":"unknown","gemini-cli":"unknown","iflow":"unknown","kilocode":"unknown","kimi":"unknown","lingma":"unknown","pi":"unknown","qoder":"unknown","qwen":"unknown","windsurf":"unknown","ollama":"unknown"}
deprecated_since	null
replaces	null
supersedes	[]
changelog	[{"version":"1.0.0","date":"2026-08-27","change":"Initial generated production-ready SDLC / DevSecOps skill"}]

Cncf Agent Evaluation Reviewer

Purpose

Review and operate Agent Evaluation using current official documentation, repository evidence, and its CNCF Landscape classification without treating Landscape inclusion as endorsement.

Goal and behavioral contract

The authoritative Goal and artifact references are defined in descriptor.yaml. Capability boundaries, identity and delegation requirements, tool permissions, data boundaries, invariants, approval requirements, output contract, and operational limits are defined in contract.yaml. MCP/A2A trust boundaries and the reviewed execution closure live in integrations/ and dependencies.yaml; ASPS and assurance requirements live in assurance.yaml.

Treat those declarations as mandatory execution constraints. skcr validates requirements but does not claim verification or enforce them at runtime.

When to use

• Agent Evaluation code, configuration, APIs, deployment, integrations, dependencies, upgrades, or operations are in scope.
• A technology choice or migration involving Agent Evaluation requires evidence-backed assessment.

Operating model

1. Detect the installed or proposed version and deployment model before giving version-sensitive guidance.
2. Use current official documentation and repository evidence; use the CNCF Landscape only for classification metadata.
3. Inspect boundaries with identity, secrets, network, storage, dependencies, observability, upgrades, rollback, and disaster recovery.

Spec-Driven Change Context

• Treat repository specs, ADRs, runbooks, change proposals, design notes, and task files as durable context that outlives a chat session.
• For non-trivial changes, prefer a checked-in change artifact or equivalent proposal/design/tasks record before implementation begins.
• Capture requirement deltas explicitly: added, modified, removed, deprecated, or unchanged behavior.
• Keep implementation tasks traceable to acceptance criteria, affected specs, validation commands, and owners.
• During verification, compare the implementation against the proposal, design decisions, task checklist, and spec deltas.
• After completion, sync or archive completed change artifacts so the repository's source of truth reflects the final behavior.
• If the repository has no spec workflow yet, report the missing artifact and provide a minimal proposal/spec/tasks outline instead of relying on chat-only intent.

Skill-Specific Review Scope

• CNCF classification: AI Agent / Evaluation
• CNCF project maturity field: not specified