CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

ainativedev/aidevcon-2026-nyc

AI Native DevCon 2026 New York — practical agent skills grounded in conference talks

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

application-template.mdskills/talk-wotherspoon-agent-execution-environments/references/

Remote execution and handoff worksheet

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.

Job and completion bar

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 handoff

StageConversationWorkspace and artifactRequired evidenceAllowed changes
ReproduceTask-specific contextKnown starting revisionReproduction or clear absence
ImplementRequirements and failure evidenceCandidate revisionDiff and checks
ReviewFresh context if appropriateExact candidate revisionIndependent 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.

Credential boundary

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.

Trigger and stopping behavior

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.

skills

talk-wotherspoon-agent-execution-environments

tile.json