Agent skills for OpenAI Agents SDK

Suede-owned recovery discipline for recurring charges billed outside Amazon: App Store, Google Play, PayPal, direct-bill streaming, gyms…

Apply when sequencing an addition, refactor, or rewrite.

Finds out who a brand competes with. Reads what the brand sells from its site, searches the web for the alternatives buyers compare it…

Use when designing and documenting the systematic literature search for a Psychological Bulletin review or meta-analysis — databases…

Use when executing the systematic search, screening to a PRISMA flow, and extracting data for a Review of Educational Research (RER)…

Use when drafting a TACAS (ETAPS) author response for the rebuttal window, covering the short single-round rebuttal, answering soundness…

Analyze all vault tags: find unused, orphan, near-duplicate, over-used, and under-used tags.

TanStack React Start auth patterns with @clerk/tanstack-react-start

TanStack Router best practices for type-safe routing, data loading, search params, and navigation.

Create sales collateral such as decks, one-pagers, objection docs, demo scripts, playbooks, and proposal templates.

USER-INVOKED ONLY. Use only when the user explicitly invokes $targetify or asks where to spend scarce/premium/frontier/super-model…

This skill should be used when the user asks which Space Apps award category to aim at, "how do we win Best Use of Data", "which award…

Mark a task or epic complete with integrity reporting.

Design taste and identity. Use for UI polish, landing pages, redesigns, "it looks like AI", and client brand work. Loads the project…

Designs, builds, redesigns, and audits high-quality visual frontends using a guided research-to-render workflow.

Ask Claude Code to make a taste-driven call on something ambiguous — UI polish, prose phrasing, naming, formatting.

Design taste and process for anything a person will look at in a browser — landing page, dashboard, prototype, deck.

Routes and queries Traditional Chinese Medicine learning tasks across eight specialized TCM AI knowledge sources with cross-school…

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test…

Classicist by default, pragmatic about doubles, strict about test purpose and boundaries.

Test-Driven Development (TDD) and Incremental Implementation discipline.