Agent skills for Microsoft Copilot

Drug delivery formulation skill for optimizing drug loading, encapsulation efficiency, and release kinetics

Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways…

Use when you're ready to define a feature before building it — generates a structured PRD using Jobs-to-be-Done thinking, success metrics…

Use when you need end-to-end tests for critical user flows that unit tests can't cover — scaffolds Playwright/Cypress tests from the happy…

Use when you want a quick security pass on code changes or dependencies — checks OWASP Top 10 patterns, runs dependency audits, and…

Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping — audits and…

Use when starting a new feature or function to write failing tests first, then implement the minimal code to pass (Red→Green→Refactor)

Use when a plan, spec, or PRD must become an actionable backlog — break it into thin dependency-aware issues that each deliver a…

Use before claiming any task is done — run the exact command that proves the fix works, read the output, and only then report success.

Review a pull request without posting any comments.

Use when designing, implementing, reviewing, or optimizing any app feature so data structures, algorithms, Big O, and real production…

Directed Self-Assembly skill for block copolymer lithography and nanoparticle templating

Autonomous design space exploration loop for computer architecture and EDA.

Review DeepSeek Harness session history as a local evidence-backed workflow retrospective.

Reverse custom JavaScript or WASM virtual machines and risk engines.

Draft or substantively rewrite argumentative prose for empirical ML and AI research papers when expert clarity, literature synthesis…

Use when the user asks to compare, diff, or find differences between two tabular data files (CSV, TSV, Parquet, Arrow, JSON, NDJSON, Excel).

Generates DTO (Data Transfer Object) for PHP 8.4.

Performs comprehensive code reviews by orchestrating a dual-analysis between Codex and Claude to ensure security, performance, and code…

Run a moderated dialectic between two models from two labs to decide a question.

Performs rigorous, evidence-based code reviews across pull requests and commits using specification and standard compliance dual tracks.