AI Native DevCon 2026 New York — practical agent skills grounded in conference talks
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Use this record to review one delivery path. It applies Duvall's model without changing access or deployment policy.
Intended outcome: Accepted criteria and their source: Artifact or commit: Scope changes: Required evidence: Known limitations:
Separate confirmation of the requirement from verification of the implementation.
| Actor | May read | May author | May reject or escalate | May deploy | May change controls |
|---|---|---|---|---|---|
| Builder | |||||
| Validator | |||||
| Pipeline | |||||
| Monitor / emergency operator |
Record actual permissions rather than role names alone. Identify standing credentials, signing keys, and routes that bypass the intended pipeline.
Checks and versions: Results bound to this artifact: Mutation evidence and limits: Independent validator inputs: Spec-to-code findings: Code-to-spec findings: Provenance: Attestation issuer and trust boundary: Decision when evidence is absent or stale:
An authentic signature does not show that the underlying check was adequate.
Pinned dependencies and actions: Untrusted cache isolation: Deployment identity lifetime: Control-change path: Source and telemetry containment: Dependency admission rule:
Mark each item observed, proposed, or unknown.
Production drift response: Pipeline drift response: Specification drift response: Independent monitoring boundary: Break-glass activation: Alarm and temporary redeploy suppression: Rollback evidence: Return through the trusted pipeline:
Test that recovery does not overwrite the emergency fix or create a second uncontrolled production writer.
Most consequential gap: Smallest authorized change: Verification case: Owner: Remaining risk:
Do not certify the system from a completed worksheet. Attach inspection or test evidence before claiming the boundary works.
.tessl-plugin
skills
talk-arcolano-autonomy-and-trust
talk-aroussi-decision-context
talk-bevin-agent-assisted-instrument-design
talk-boeckeler-context-lifecycles
talk-braun-context-graphs
talk-carmont-evolving-agent-harnesses
talk-chanezon-gordon-agent-experience-evaluation
talk-cox-secure-agentic-workflows
talk-cunniffe-reusable-agent-platform
talk-davis-agent-tool-policies
talk-debois-concurrent-delivery
talk-dzialets-team-automation
talk-fahmy-harness-api-design
talk-finster-continuous-delivery
talk-fowler-regenerative-software
talk-gavrilescu-factory-architecture
talk-graciolli-amin-verification-aware-programming
talk-gruenbaum-reverse-graph-engineering
talk-hassan-agentic-engineering
talk-hossain-enterprise-agent-adoption
talk-huntley-patch-ready-factories
talk-jain-verifying-intent
talk-katsioloudes-montei-agentic-lifecycle
talk-knox-harness-engineering
talk-kovac-deterministic-memory
talk-lee-perkins-code-readiness
talk-lorenc-machine-speed-security
talk-lubken-software-of-one
talk-meijer-software-specialization
talk-meppiel-versioned-agent-contracts
talk-moss-concurrent-agent-risk
talk-myers-understanding-agent-generated-code
talk-ocytko-scaling-agentic-engineering
talk-oza-automating-design-quality
talk-panzica-agentic-sdlc
talk-pari-patel-agent-awareness
talk-podjarny-trustworthy-software-factories
talk-poulter-factory-improvement
talk-pratik-patel-refined-rag-data
talk-re-ferre-development-platforms
talk-sadogursky-factory-of-factories
talk-shah-training-agent-skills
talk-sharma-mohapatra-evolving-intent
talk-singhal-operating-agents-at-scale
talk-stack-incident-dossiers
talk-tyler-team-coding-benchmarks
talk-wotherspoon-agent-execution-environments
talk-yegge-ai-powered-factories
talk-zuber-leadership-through-coding