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 Tessl's recommended application of Wotherspoon's talk. Use it to design one job that currently requires repeated intervention. It does not represent an API schema.
Name the task, input source, expected deliverable, and the intervention the environment should eliminate. State the required behavior and the evidence that a reviewer can inspect. Separate “interaction finished” from “checks passed” and “result accepted.”
Record the harness, workspace setup, tools, team instructions, hooks, credentials, and trigger. For each item, mark available, missing, or unverified. Identify any dependency on the operator's laptop or logged-in browser.
| Stage | Conversation | Workspace and artifact | Required evidence | Allowed changes |
|---|---|---|---|---|
| Reproduce | Task-specific context | Known starting revision | Reproduction or clear absence | |
| Implement | Requirements and failure evidence | Candidate revision | Diff and checks | |
| Review | Fresh context if appropriate | Exact candidate revision | Independent assessment |
These stages are illustrative. Adapt them to the job rather than assuming every task needs three agents. Explain whether workspace state is shared, copied, or frozen, and prevent a later write from invalidating earlier evidence.
Record the intended destination, allowed operation, credential scope, proxy matching assumption, refresh capability, and expiry behavior. Distinguish keeping a token out of the sandbox from restricting what the agent may do through an allowed API. Do not put secret values in this worksheet.
Describe schedule or event, run identity, token or time budget, overlap policy, and the response to missing tools, expired credentials, failed checks, or budget exhaustion. Identify which files and traces must be retrieved and where the result may be delivered under the user's authorization.
Finish with unresolved assumptions and a small verification task for each. Label product behavior that needs current documentation, particularly handoff APIs, credential refresh, and available harness settings.
.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