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-hassan-agentic-engineering/references/

Middle-loop workflow improvement record

Adapt this record to one recurring task. It operationalizes Hassan's principles without claiming that the speaker supplied this exact schema.

Capability boundary

Task and intended outcome: Current model and workflow: Known failure: Evidence and reproducible example: Temporary workaround: Durable domain requirement: Retest trigger and owner:

Use actual task evidence. Keep a proposed benchmark separate from a result. Record changes to inputs or tools that could make comparisons misleading.

Responsibility map

StepInput and outputAI may executeAI may decideVerificationEscalation authority

Identify where a person contributes judgment and where they merely transport information. Describe how each check is enforced and what a failed check does. Do not add approvals that serve no concrete decision.

Rescue-to-improvement loop

Observed failure: Human correction: Likely cause: Reusable guidance or tool change: Scope of that change: Regression example: How the next attempt receives the correction: Evidence of reduced recurrence:

A manual repair is not yet a durable improvement. Mark the improvement unverified until a relevant comparison has run.

Technology and cost choice

Candidate mechanisms: Reasoning needed: Deterministic validation available: Human expertise needed: Unnecessary steps to remove: Total cost per useful result: Error and retry burden:

Choose according to the task, not a preference for using AI everywhere. Include work delegated to people when estimating cost and delay.

Sustainable next step

Difference between demo and shipping requirements: Human attention required: Learning opportunity retained: Smallest authorized improvement: Owner and observation window: Decision after evaluation:

State remaining unknowns plainly. The record should support a concrete workflow review and later learning, not imply that a diagram or an automated reviewer guarantees quality.

skills

talk-hassan-agentic-engineering

tile.json