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 application of Aroussi's principles, not an Acropolis schema.
State the exact decision question, requested time period and caller's authorized scope. Identify which evidence may enter the response and which access rules are unknown.
Assertion: Write the proposed answer in one sentence.
Status: Draft, proposal, accepted decision, superseded decision or unresolved. Choose only what the evidence supports.
Scope: Name the relevant party, transaction or exception. A special term for one client does not change the standard policy for all clients.
Authority: Record evidence that the decision-maker could approve this change, or mark it unverified.
| Evidence | What it supports | Date and scope | Limitation |
|---|---|---|---|
| Actual source reference | Narrow supported claim | Effective/observed timing | Missing context or conflict |
Link earlier and superseding claims without silently erasing history. Follow actual retention and access rules.
List sources and periods inspected. Distinguish “searched and not found” from “not covered.” Do not interpret absence of an acceptance record as rejection.
Identify the smallest additional source or confirmation that could resolve the question. Avoid asking for broad new access when a narrow fact would suffice.
Give the supported decision, evidence and uncertainty. If the claim cannot be established, say what is unknown and why.
Keep private raw values outside an unauthorized caller's model context. A permitted aggregate must be authorized by policy, not invented as an informal compromise.
Confirm that the answer does not confuse proposal with agreement, latest message with authority, search similarity with truth, or an agent's memory with organizational provenance. Mark unresolved contradictions and any retrieval-ranking gap explicitly.
.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