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-dzialets-team-automation/references/

Team automation workflow worksheet

This is Tessl's recommended application of Dzialets's talk. Use it for one team process whose current automations need coordination.

Shared task and setup

Name the team, outcome, workflow owner, and recurring task. Describe the common quality bar and existing variation between individual setups. Record reusable environment, instructions, required tools, internal context, and permissions. Identify which local limitation or collaboration problem the shared setup actually solves.

Stage map

StageInput and stateOutputVerificationOwner or next stage

Keep each automation scoped. Identify comments, issue fields, or manual copying currently used to transfer state. Replace hidden dependencies in the design with explicit status and evidence references. Do not claim a stage succeeded simply because it produced text.

Human intervention

State the decisions that need human judgment, including incomplete initial intent and consequential exceptions. Do not require approval at every routine transfer. For a failed stage, specify the current workspace, expected behavior, available evidence, failed check, and resume path a person would receive.

Explain how local intervention retains the team's shared setup. Mark any product handoff capability that still needs verification.

Operations and cost

Define actionable notifications and their owner. Separate failure, decision needed, progress, and completion. A shared inbox is a design proposal unless it already exists.

Record estimated cost with its assumptions and observed cost after the run. Set a justified run limit, review date, and condition for disabling a forgotten or unhelpful routine. Those controls are recommendations here, not numerical rules from the talk.

Pilot decision

Choose one representative task and a short observation period. Measure accepted outcomes, failed handoffs, intervention burden, quality, and spending. Finish with evidence needed to expand, revise, or stop. Distinguish the team's measured results from the speaker's reported adoption and staffing examples.

skills

talk-dzialets-team-automation

tile.json