claude-skills-marketplace

Run a model through the omni-bench benchmark to MEASURE it — produce a run-artifact and score it, then read the numbers. Use when asked to run, benchmark, measure, evaluate, or "test the results of" a model with omni-bench — ASR (WER/CER, RTFx) or text generation (tok/s, TTFT, prefill tok/s, prompt-cache speedup). Covers the adapter seam (Transcriber/Generator), the prepare→run→score→diff CLI flow, the offline no-download smoke task, and how to interpret each metric. NOT for publishing to a leaderboard (use omni-bench-publish) or changing the framework itself (use omni-bench).

Publish a scored omni-bench result (ASR or text-generation) to a leaderboard platform (e.g. bench.bshk.app) via its write API. Use when asked to publish, upload, submit, or "send a report" for an omni-bench result.json or parity-report.json — sharing ASR WER/RTFx numbers or text-generation TTFT/tok-per-s/prompt-cache numbers. Covers the one modality-agnostic `omni-bench publish` command and the MANDATORY secret handling: the api-key is injected from a secrets manager (1Password `op run` / AgentVault `av run`) at runtime, never read into context, never hardcoded.

Develop the omni-bench benchmark framework (ASR/STT + text generation) built on a producer/scorer split with an open JSON spec as SSOT. Use when working in an omni-bench checkout — changing the JSON schemas, the prepare/producer/scorer/diff pipeline, the adapter seams (Transcriber / Generator), datasets, fixtures, or the Swift producer SDK; or when running and validating benchmark artifacts. Encodes the schema-evolution rules, determinism invariants, commands, and repo gotchas that are easy to get wrong.

Use when generating/managing the offline root signing key or signing & publishing Zamok product keysets from the terminal (the Swift CLI; the ZamokApp GUI is the co-equal interface). Triggers — "generate root key", "rotate root", "publish keyset", "sign keyset", "escrow root key", "zamokctl", "trusted-roots.json", Tish/Zamok license signature setup.

Use when auditing websites or apps for Canadian accessibility law compliance, checking AODA (Ontario) or Accessible Canada Act (federal) requirements, or advising on CAN/ASC-EN 301 549 obligations.

Use when auditing digital products or services for European Accessibility Act (EAA) compliance, checking EN 301 549 conformance, or advising on EU Web Accessibility Directive obligations.

Use when determining which accessibility law applies to an organization, comparing requirements across jurisdictions (US, EU, Canada, Japan), or planning multi-country accessibility compliance strategy.

Use when auditing websites for Japanese accessibility compliance, checking JIS X 8341-3 conformance, or advising on Japan's Act for Eliminating Discrimination against Persons with Disabilities.

Use when reviewing accessibility of websites, apps, or facilities, conducting WCAG audits, preparing for ADA Title II/III deadlines, or checking digital/physical accessibility requirements.

ZenStack access policies and enhanced Prisma ORM. Use when defining access control rules (@@allow/@@deny), integrating with tRPC, setting up auth(), or working with ZModel schemas.

Use Codex CLI for AI-powered code review. Triggers on "codex review", "review with codex", "code review pr", or when user wants AI code review before PR/merge.

Fast linting/formatting for TypeScript/React. Use when setting up linter, migrating from ESLint/Prettier, or running code quality checks.

Advanced TypeScript types (generics, conditionals, mapped, utilities). Use when building type-safe libraries or implementing complex type logic.

Review iOS code for Apple HIG compliance. Use when validating SwiftUI/UIKit code, checking accessibility, or auditing iOS design implementation.

Orchestrates complete iOS app design workflow from idea to implementation. Use when starting a new iOS feature, planning iOS app architecture, or need end-to-end iOS design process.

Apple Human Interface Guidelines quick reference. Use when needing iOS design guidelines, HIG rules, or Apple design best practices.

Generate SwiftUI components following Apple HIG. Use when creating iOS UI components, building SwiftUI views, or need code scaffolding for iOS interfaces.

Use safe-rm script instead of rm -rf. Prevents accidental deletion of protected system, config, and project paths.

Manage Python with uv instead of pip/virtualenv. Use when running Python scripts, installing packages, or creating virtual environments.

Format and structure content as clean, well-organized Markdown. Use when asked to create documentation, format text, or generate Markdown output.

Review code for quality, security, and best practices. Use when asked to review code, find bugs, or suggest improvements.

Orchestrate full development workflow. Use when implementing features, starting structured development, or user mentions "workflow" or "implement issues".

Manage git worktrees for branch isolation. Use when creating feature branches, working on isolated tasks, creating PRs, and cleaning up after merge.

Generate and validate JSON Schema definitions. Use when asked to create schemas, validate JSON structure, or document API payloads.

Structure meeting transcripts into organized notes with action items, decisions, and key points. Use when processing meeting recordings or creating meeting summaries.

Fetch data from URLs. Use when asked to download content, fetch remote files, or read web data.

Develop SwiftUI applications for iOS/macOS. Use when writing SwiftUI views, managing state, or building Apple platform UIs.

Create new Claude Agent Skills. Use when asked to create, build, or develop a skill.

A template for skills that include executable code for deterministic operations.

Brief description of what this Skill does and when to use it. This field is critical for Claude to discover when to invoke your skill.