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 worksheet is a recommended application of Gavrilescu's loop. It does not claim to implement Groma.
Task intent and product behavior: What should the feature do, and which user flow demonstrates it?
Baseline and result: Identify the actual revisions or snapshots being compared. Mark whether the map was initialized before this work; do not invent earlier architecture history.
Coverage: List relevant languages, frameworks and components. Note known scanner limitations or areas that were not inspected.
| Component or relationship | Observed source | Meaning or flow | Confidence |
|---|---|---|---|
| Fill with an actual entity | File, symbol or inspected evidence | Curated explanation | Verified, inferred or unknown |
Keep deterministic facts separate from agent-generated labels and flow descriptions. Include a small set of important paths that were checked against source. For every missing edge, distinguish “not observed” from “confirmed absent.”
Describe components added, removed or modified, changed dependencies and which changes are expected from the task. Identify duplication, bypasses around shared services and code apparently disconnected from product behavior.
Cumulative concern: Explain whether this change continues a pattern visible across several features. Include the comparison period rather than implying one pull request proves system-wide drift.
For each concern, state evidence, architectural consequence, proposed correction and the behavior or source inspection that would validate it. Record any focused code review needed where the map is insufficient.
Product check: Describe how the final application was or should be exercised. Do not mark planned checks as completed.
Next baseline: State how reviewed names, groupings and stable component identity will be maintained. End with accepted changes, unresolved uncertainty and the next review trigger appropriate to this project.
.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