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 adapts Kovac's argument into an audit artifact. It does not assume a particular indexer or memory product.
Learning: Observed behavior: Supporting artifact or trace: Repository: Human-readable declaration: Tool-produced identity: Observed code version: Relevant dependency versions: Source permissions:
Keep the claim separate from its reference. A reproducible key does not validate the claim.
Indexer and configuration: Same-code cross-machine check: Same-name declaration check: Rename or move behavior: Changed-body behavior: Unchanged-caller / changed-helper behavior: Collision or unresolved-reference behavior:
Mark each behavior as observed, specified, or unknown. Do not invent stability guarantees from an identifier's appearance.
Existing findings for the same identity and version: Duplicate wording versus duplicate claim: Conflicting claim: Evidence for each side: Context that may explain the difference: Resolution: Remaining uncertainty: Authorized audience:
Do not select the newest claim solely because it is newer. Do not merge similar function names without verifying the actual declaration.
Current state: Valid / disputed / stale / superseded: Event requiring revalidation: Promotion policy for new code versions: Retention requirement: Forgetting or archival rule: Reason and evidence for transition: Owner:
Separate a local observation from an organizational convention or global instruction. Preserve relevant audit history when correcting an error.
Expected aggregation: Actual aggregation: Attribution accuracy: Finding correctness: Retrieval usefulness: Access correctness: Regression cases: Smallest authorized improvement:
Keep these dimensions separate. A grouping test can pass while the learning is wrong or exposed to the wrong audience. This record does not authorize ingestion, cross-team promotion, or deletion of memory.
.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