Operator Agent Skills

Taste Is the Bottleneck

Source-grounded pack with Quality Bar Review, Reference Set Builder, and Taste Calibration Loop, plus 1 more.

Get this pack

Grounded in the complete Taste Is the Bottleneck series.

Open the pack, choose a workflow, and follow its setup and input instructions. You can also open each workflow below.

10 source essays · 4 usable skills · reviewed Jul 2026

Use this pack when

Choose this pack when the work touches Taste Is the Bottleneck and you need a bounded workflow with explicit inputs, a defined output, and human review gates.

Choose the job in front of you.

4 source-grounded skills. Load one workflow at a time.

Quality Bar Review

Use this workflow when a specific artifact, decision, or AI workflow must be accepted, revised, cut, escalated, or rejected against explicit load-bearing qualities, constraints, examples, tradeoffs, risk tier, and ownership rather than polish or reviewer mood.

Output specification

Return the job, load-bearing bar, proportional tradeoffs, rejection list, option compression, evidence and risk assessment, decision, revision criteria, owner, gate, and reusable standard; include the AI rubric and tier when applicable.

Reference Set Builder

Use this workflow when a team needs to learn what good looks like through a small, evidence-backed museum of excellent examples, plausible failures, before-and-after corrections, explicit reasons, constraints, and downstream consequences.

Output specification

Return a domain charter, five exemplars, five anti-examples, annotated reasons and consequences, shared vocabulary, critique prompts, use protocol, permissions, owner, and refresh rule.

Taste Calibration Loop

Use this workflow when standards may be stale, private, inconsistent across leaders, applied too late, dependent on a few reviewers, impressed by polish, or disconnected from current customers, external benchmarks, downstream outcomes, and AI-era baselines.

Output specification

Return the surface audits, real-artifact evidence, calibration findings, stale and conflicting standards, updated examples and rules, owner and review design, AI acceptance audit, uncomfortable currently-accepted work, and next session date.

Taste Gap Diagnosis

Use this workflow when a team produces abundant polished or plausible work but struggles to decide what deserves making, what fits the customer and strategy, what is merely acceptable, what should be cut, and why a judgment is more than senior preference.

Output specification

Return the work surface, preference-versus-taste findings, selection-debt evidence, failure-mode scan, hidden-quality risks, centralized judgment, root gap, transfer move, owner, and proof.

Keep consequential decisions explicit.

These workflows structure analysis and artifacts; they do not authorize autonomous external, personnel, financial, legal, security, or other high-impact action.

Choose your reading rhythm.

Start with a weekly briefing, add daily notes, or hear only when a durable essay or research update is ready.

You've successfully subscribed to Antoine Buteau
You've successfully subscribed to Antoine Buteau
Welcome back! You've successfully signed in.