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 Lorenc's talk. Use it for defensive maintenance of a system the user is authorized to manage.
Record the dependency, resolved version, upstream project, transitive consumers, and running artifact. Map discovery, maintainer acceptance, release, packaging, application integration, validation, and deployment. Identify ownership, evidence, and waiting time at each stage.
Keep “patch available,” “release available,” “rebuilt,” and “running” separate. Mark missing evidence instead of assuming completion.
Choose a regular maintenance path or a specific incident response. Describe compatibility constraints and the operational reason for delay. For a large version gap, propose small steps with checkpoints and behavior comparisons. Record recovery for code, state, and external effects.
State whether the work repairs one defect or removes a recurring unsafe pattern. For modernization, define the dangerous capability and behavior a replacement must preserve. A language or library choice does not guarantee security.
If using a cooldown, specify delayed-release risk, new-package risk, exception criteria, and transitive-dependency handling. Do not copy seven or fourteen days merely because those examples appear in the talk.
If copying or forking code, retain origin, version, modifications, update tracking, and a maintenance owner. Explain how future vulnerability information will reach the copied component.
List evidence needed to confirm affected versions, migration correctness, deployment identity, and operational health. Use authoritative current advisories for live vulnerability claims; the transcript is not one.
Finish with the first bottleneck, proposed action, expected benefit, unmeasured cost, and expansion condition. Keep experiment results and speaker anecdotes separate from outcomes actually verified in this system.
.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