Agent skills for Cursor

Use when turning project evidence, AI-agent work logs, retrospectives, or decision histories into a traceable case library, reusable…

Encode and decode Cashu tokens that are hidden inside emojis using Unicode variation selectors.

Finds Fabric items across every workspace with the Catalog Search API when the workspace is unknown, locating an item by display name…

Start or refresh domain onboarding for the current project.

Generates complete CRUD module from database table definition.

Implement or repair stable, observable software behavior through a compact verified test-first Red-Green-Refactor loop.

Build falsifiable causal hypotheses: DAGs, FPCI, equivalence testing.

Use when the causal identification strategy is the bottleneck for a Quarterly Journal of Economics (QJE) manuscript — RCT, staggered DID…

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead…

How to write Cavekit-quality kits that AI agents can consume effectively.

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

Visualizes Claude Code skills and development roadmaps through an interactive HTML dashboard.

Automates structured code reviews across quick, full, and security dimensions for individual commits or branches.

When to activate: CCPA, CPRA, California privacy, consumer rights, opt-out, data deletion, privacy notice, California residents, do not sell

Teach CCR theory: product triple, exact eight semiotic contract axes, contracts, coupling discovery and factorisation, invariants…

Design, redesign, critique, and verify real product surfaces under CCR while generating exact-axis and appropriately factored coupling…

Maintain non-trivial CCR repo build/change work by deriving the law delta and keeping the exact eight product-axis contracts…

Shape a repo into CCR-governed form by discovering expected product law and making constitution, vocabulary, evidence, canonical owners…

Intelligent coordinator — classify intent via structured extraction (action × object × style), map to skill chain, execute wave-by-wave…

CCXT cryptocurrency exchange library for Python developers.

Configure, optimize, and troubleshoot CDN deployments with caching strategies, security hardening, and multi-provider management.