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 Debois's talk. Fill it for two or more real requests that may interact. Do not assume that a clean Git merge makes them compatible.
| Request and intent | Initiator | Claimed code or domain | Shared state | Expected completion |
|---|
Record contradictions in desired behavior separately from overlapping files. Include maintenance work and incident fixes in the queue. Identify whether the pressure is active execution, waiting, repeated testing, or human review.
State the code revision, test definitions, data snapshot, API assumptions, configuration, and external context for each run. Mark what remains live and can change. Explain how a changed assumption invalidates earlier evidence. A worktree alone does not freeze the wider environment.
Describe the signal when an agent expands its scope and the response to overlap: wait, transfer, renegotiate, or revise the plan. Name the authority for resolving incompatible product intent.
Define a combined-state behavior check. For example, if one request changes monetary units while another adds invoice arithmetic, verify the agreed units across the complete calculation. This example follows the talk's semantic-conflict discussion; use the team's real invariant.
If proposing grouped or speculative merges, record the exact combination tested, conditions that invalidate it, and a fallback when the group fails. Keep the final change understandable to its reviewer.
List information the agent can retrieve and decisions it must surface. Provide concise options with consequences. Record accepted decisions with rationale and scope in the team's chosen location; the talk does not settle one universal storage system.
State the consequence of a bad change, required checks, release routing, and how code, data, and external side effects could be recovered. Finish with factory ownership, role-appropriate status updates, and one bottleneck measure to compare before and after the proposed change.
.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