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 a recommended application of the joint talk, not executable LemmaScript.
Feature: Describe the real user outcome and a representative input.
Properties: State each invariant or postcondition in plain language. Separate a property required by the user from an implementation choice.
Assumptions: List preconditions, permitted input domains and environmental assumptions. Explain how an unverified caller establishes them.
| Property | Reason | Frozen or changeable | Evidence required |
|---|---|---|---|
| Fill from actual requirements | Intended behavior protected | Decision with rationale | Mechanical check and scope |
For a splitting feature, conservation of the total is distinct from the allocation of remainders, fairness, input validation and actual payment effects. Do not mark an omitted property as implicitly verified.
Pure core: Identify state, initializers and transitions covered by verification.
Invariant boundary: List all ways state can be created or changed. Mark any unverified code that can bypass the intended path.
Effects: Describe UI/API adapters and, if useful, commands represented as data. State what the interpreter does and which parts remain trusted or separately tested.
Record the candidate artifact, unchanged contracts, verifier verdict, failed obligations and next candidate. Keep an agent's narrative separate from actual mechanical output.
Acceptance statement: “This artifact satisfies [properties] under [assumptions] within [boundary].” Leave unknown fields visible; do not invent proof results.
For a proposed contract change, identify the changed requirement, rationale, lost guarantees and necessary new checks. Reject weakening that merely hides a failure.
End with the supported guarantee, unverified integration behavior, and the smallest next evidence needed. A valid contract proof does not by itself establish that the contract fully captures user intent.
.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