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
Use this artifact for one generated change. It adapts the trail concept without requiring a particular product.
Work item: Current commit or artifact: Original intended outcome: Accepted scope changes: Excluded behavior: Remaining uncertainty:
Link each material intent claim to supplied evidence. Do not infer an unrecorded decision from the final implementation.
| Decision | Evidence | Alternative rejected | Reason | Effect on current scope |
|---|---|---|---|---|
Include only decisions needed to assess the change. Retain sensitive detail only when authorized and relevant.
| Revision | Check and version | Type | Result | Evidence | Finding disposition |
|---|---|---|---|---|---|
| Deterministic / model / human |
A pass applies only to the artifact checked. Record unresolved findings and reasons for dismissal. Keep planned checks visibly distinct from observed results.
Definition of done: Repeated finding detection: Conflicting judgment behavior: Budget or stopping condition: Current unresolved issue: Next authorized action:
Do not treat an agent's ready-for-review message as permission to merge.
Statement: Category: Scope: Originating decision or session: Why future work needs it: Known exceptions: Owner: Supersedes or conflicts with: Review outcome:
Distinguish a preference from an invariant and a rejected experiment from a permanent prohibition. Check that the memory does not claim more than the source decision supports.
What changed: Why this approach: What was actually verified: What still needs judgment: Evidence locations: Retention or permission limitations:
The handoff should make the story inspectable without requiring a full session read. It supports the existing review policy and does not replace required checks or grant authority.
.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