Agent skills for Zed

Redesign bounded contexts, define aggregates, generate context maps, and open the Architecture Decision Record log every later design…

Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent…

Assembles comprehensive board and investor update decks by pulling perspectives from all C-suite roles.

Chief AI Officer advisory for startups: model build-vs-buy decisions (API vs fine-tune vs in-house), AI risk classification under EU AI…

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.

M&A strategy for acquiring companies or being acquired.

Quality-gate any artefact against a shared QA rubric before it ships.

De-identify clinical research data before LLM-assisted analysis.

Three.js performance optimization and best practices guidelines.

Use when reviewing a specific inbound deal before close — when sales has asked for a discount that exceeds AE authority, when the customer…

Write deal memos for PE acquisitions and CRE investments.

Automated deal scoring based on thesis alignment, market size, team, and traction metrics

Quickly screen inbound deal flow — CIMs, teasers, and broker materials — against the fund's investment criteria.

Find material deal changes; not a full deal review.

Model close-date slip scenarios; never invent win odds.

Uncover customer jobs, pains, and gains in a structured JTBD format.

Guides competitive debaters through motion analysis, argument building, and strategic rebuttals using the Debate Universal Grammar system.

Alias for `/origin:handoff` — symmetric brief/debrief naming.

Evaluates borrowing sustainability by rebuilding repayment schedules, calculating DSCR, repayment years, and borrowing headroom under…

Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction

Debug a Pulumi update or preview that failed: read the failure Pulumi already recorded, find what caused it, and fix it.