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 format applying Stack's workflow. It is not authorization to remediate or suppress an alert.
Title, category and affected service: State what is actually known.
Trigger and observation window: Record the alert source, first/last seen times and evidence of provenance. Mark signature verification unknown unless inspected.
Correlation: List related incidents and repeated notifications. Explain whether the symptoms are unchanged or new; separate model classification from the rule deciding incident state.
| Finding | Supporting evidence | Time/scope | Confidence or limitation |
|---|---|---|---|
| Observed fact | Query result, log or supplied record | Actual window | Missing or conflicting evidence |
Include deployments, configuration, dependencies and runbook checks relevant to this alert. Explicitly list checks unavailable or not completed.
Rank plausible explanations only as far as evidence permits. For each, give supporting evidence, a competing explanation and the next discriminating check. Do not label an agent hypothesis a confirmed root cause.
Describe recommended next steps, their operational consequences and what additional judgment is needed. State what has and has not been changed.
Use the team's existing incident and permission process. A read-only dossier does not imply that a rollback, certificate rotation or page suppression is authorized.
Record the operator's question, investigation performed and answer in the incident history. Preserve source timing and scope.
After resolution, capture one workflow improvement: a missing check, a clearer field, a correlation rule or an access fix. Define a representative replay and expected result, marking it planned until performed.
End with a concise decision-ready summary, unresolved uncertainty and the next responsible action. Keep the layout stable across incidents so operators can find evidence quickly.
.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