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 Lubken's talk, not a platform configuration.
Owner and users: Name the person accountable for the app and who may use it.
Task: State one concrete workflow or decision. Explain why a small deterministic program, an agent or a combination fits.
Inputs and outputs: Identify the real source systems and the useful result. Keep the scope separate from replacing a whole CRM or ERP.
Persistent state: Describe what must survive compute suspension or replacement. Specify data retention and export needs.
Isolation: Identify what separates this app from neighboring apps and what sharing is intentional.
Backend capabilities: List the exact resources and operations needed. Record app identity, user identity and credential-brokering location separately.
Pending access: Describe how unavailable access is represented. Clearly mark any test or dummy data and avoid presenting it as a live business result.
Capture usage, task success, owner, last maintenance, known defects, security-update needs and overlap with other apps.
Define a business-value signal suited to the task, such as time saved preparing a quote, while marking causal claims unproven until evaluated. Do not equate frequent use with value automatically.
Choose keep, consolidate, rebuild or retire. State the evidence and a trigger for revisiting the decision.
For rebuilding, preserve the validated task and user learning while specifying data migration, handover and retirement of the old implementation. “Disposable code” does not mean disposable user data.
Estimate compute, storage, network, access-layer and maintenance costs separately using verified inputs when available. Mark unknowns rather than importing the talk's napkin estimate as a quote.
End with the smallest next app or platform change and planned validation. Do not claim the design is deployed, secure or free to operate.
.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