nickwinder

Use when setting up a new project for structured AI-agent development - scaffolds a knowledge-base harness with architecture docs, workflow phases, ADRs, patterns, and verification types with worktree isolation

Interactive, multi-phase GitHub PR review with human-in-the-loop triage before posting. Use when asked to "do a thorough PR review", "interactive review of PR", "review PR with triage", "comprehensive review of PR #N", or any request for a full/deep/structured code review of a PR. Also triggers on "review PR and post comments" or "walk through PR findings with me". This skill runs specialized review agents in parallel, deduplicates findings across categories, presents them to you in configurable batches so you decide what to include, then posts the final review as inline GitHub comments — ensuring every finding that goes up has your explicit approval.

Autonomous optimization loop — measures metrics, scores pages by opportunity, runs experiments, and makes data-driven keep/discard decisions. Use when running the optimization cycle, checking experiment status, or after deploying changes to evaluate impact. Use PROACTIVELY when the user mentions optimization, A/B testing, experiments, metrics review, or site performance.

Use when asked to explain, understand, walk through, or summarize a GitHub pull request. Triggers on phrases like "explain this PR", "walk me through PR

Use when defining product requirements, creating feature specifications, or establishing contracts between stakeholders - creates verification-agnostic acceptance criteria in Gherkin format with multi-modal verification support and contradiction analysis

Consult a distilled persona of a colleague for their likely take, critique, or pushback on an idea — locally, without involving them. Use when the user wants to brainstorm, pressure-test a plan, anticipate a reaction, spot missed objections, or stress-test a decision through a specific person's lens. Personas live at ~/.synthteam/personas/<name>.md and capture knowledge, opinions, and decision-making patterns (not voice or style). Invoke when the user says "ask <name>", "what would <name> think", "get <name>'s take", "/ask-colleague <name> ...", or any similar request for a colleague's perspective.

Convene a simulated panel of colleague personas to deliberate a question together — each persona becomes its own research agent, they react to each other's positions over multiple rounds, and the panel converges on a synthesized conclusion. Use when the user wants more than one perspective on a decision, a cross-functional gut-check, a debate between viewpoints, or a comprehensive answer that surfaces where teammates would agree and disagree. Invoke when the user says "ask the team", "/ask-team ...", "what would the team think", "get a panel on this", "run this past everyone", "convene the personas", or asks for multiple colleagues' takes at once. For a single colleague's take, use ask-colleague instead.

Build or refresh a distilled persona doc for a colleague from their Slack history — dump their channel messages, then run a multi-agent distillation into a structured persona file that the ask-colleague and ask-team skills consume. Use when the user wants to "dump <name>'s Slack", "distill <name>'s persona", "build a persona for <name>", "add <name> as a colleague", "refresh <name>'s persona", or otherwise create/update the source files behind ask-colleague. This is the ingestion-side skill; ask-colleague and ask-team only read what this produces.