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-panzica-agentic-sdlc/references/

Bounded delegation pilot

This worksheet is a recommended application of Panzica's journey, not an Agent Fabric implementation.

Task and current phase

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.

Confidence design

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.

Responsibilities

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.

Measurement

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.

Decision

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.

skills

tile.json