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
This is Tessl's recommended application of Jain's framework. Complete it for one candidate change using actual session and repository evidence. Do not invent a result to fill a field.
State why the change is needed, the requested behavior, and the relevant constraints. List each acceptance criterion with its original source. Record any later amendment, the reason, and who made the decision. Distinguish accepted changes from agent proposals.
| Decision | Alternatives and rationale | Status | Human call or follow-up | Evidence |
|---|
Include choices made during implementation, agent disagreement, review responses, and repairs after verification failures. Preserve settled decisions; they help reviewers understand the system. An agent's “acceptable risk” label is not a human acceptance record.
For each reusable rule, provide its wording, applicable change scope, verification method, source review comments, and maintenance owner. Keep opinions specific to this change separate from reusable rules.
If converting a rule to a deterministic pattern, record shadow-mode comparisons, representative matching and nonmatching examples, disagreements, and promotion criteria. A repeatable result can still be wrong.
| Criterion | Scenario | Evidence type | Candidate revision and environment | Result or missing evidence |
|---|
Choose evidence that can establish the actual behavior. Use screenshots for visible state, responses for API contracts, state or network evidence for side effects, and test runs for temporal behavior. A screenshot alone may not prove a backend side effect.
Summarize settled issues, unresolved decisions, and follow-ups. State what the reviewer needs to understand and which code or artifact they should inspect if the packet is insufficient. Name rule owners and the person responsible for the change. End with the next verification or decision, preserving the team's existing merge authority.
.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