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 Panzica's journey, not an Agent Fabric implementation.
Describe one real workflow and classify it as assist, bounded delegation or an outcome-oriented orchestration experiment.
State the desired result, accountable owner, allowed repositories/systems and existing release authority. Separate the task's execution scope from broad organizational ambition.
Context: Identify product intent, architecture, standards and environment dependencies the agent needs.
Golden path: Describe the reusable default and which domain-specific extensions are permitted. Keep operating boundaries explicit.
Verification: Name checks that assess both the change and intended outcome. Record evidence requirements before execution.
Recovery: Define failure detection, containment, rollback or escalation and audit evidence. Mark untested recovery mechanisms as unverified.
Platform support: List shared access, execution, catalog and telemetry capabilities actually available. Distinguish them from proposed additions.
Identify what the central platform team owns and what the domain team must supply. Include the task semantics, acceptance criteria and maintenance of reusable guidance.
Catalog presence is not approval. Record whether a skill is experimental, evaluated or approved under the organization's actual process.
Pair impact measures with confidence measures. Track representative task completion, time and quality alongside reliability, interventions and recovery outcomes.
Use a comparison period and task mix. Do not treat more merge requests or fewer questions as sufficient proof of improved outcomes.
Choose expand, continue at the same boundary, revise or stop. State the supporting observations and unresolved evidence.
Document what worked, what broke and one change to context, platform or verification. Keep estimated or potential capacity separate from realized savings.
End with the next bounded delegation decision. Planned tests and recovery exercises must remain labeled planned until observed.
.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