Agent skills for Claude Desktop

Design targeted interventions that strengthen belonging and inclusion for specific classroom dynamics.

Design a performance benchmark for an API — test scenarios, metrics, and tooling.

Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.

Agent skill for benchmark-suite - invoke with $agent-benchmark-suite

Manage benchmarks for algorithm engineering experiments and evaluations

Runs an honest before/after evaluation of any change — a model prompt, an algorithm, a feature, or a refactor — against a fair baseline…

Use when designing explicit state-machine behavior for systems with multiple modes (idle/loading/success/error, draft/submitted/approved…

Bounded interrogation between a raw need and a complete specification: an eleven-category ambiguity sweep, at most five questions ranked…

Interactive BPA rule generation for Power BI semantic models; guided discovery, model investigation, and expert rule authoring.

View and manage your personal best practices library with success/failure patterns.

Automate Bestbuy tasks via Rube MCP (Composio).

Better Every Run: capture explicit /ber corrections, review them, and promote only the lessons that deserve durable memory, skill rules…

Use when working with icons in any project.

Automate Better Stack tasks via Rube MCP (Composio).

Bevy game engine: ECS, rendering, input, and asset management.

For BGB At Output Expert Opinion Memo Written Contribution: draft prepared with application, evidence and attachments; result: written…

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.

Deterministic LLM-first SEO audits for websites, blog posts, and GitHub repositories.

Business intelligence and marketing dashboard creation with multi-platform support

Clean, format, deduplicate, and manage BibTeX bibliography files for LaTeX

Post investment ideas to the AI-native investment community