Dev & Coding

Gives Claude the reference map and coding rules needed to build Genkit AI flows, tools and agents in Dart or Flutter.

A skill for writing idiomatic Dart 3 pattern matching, records and sealed classes, and for migrating pre-Dart-3 code.

A decision guide for delegating code lookup, small edits, and diff reviews to compressed-output subagents so your Claude Code context lasts far longer.

Forces every code review comment into one line — location, problem, fix — ready to paste into a pull request.

A step-by-step skill that diagnoses common Terraform/OpenTofu failure modes and proposes fixes with explicit risk controls.

Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery that extracts goals, constraints, and project scale before handing off to spec generation.

Runs one holistic codex review against three focused passes (security, Ecto, LiveView) on the same branch diff, then classifies findings to prove whether the extra passes catch real misses.

Tracks new Claude Code releases and reports their impact on your plugin as breaking changes, opportunities, or deprecations.

Turns a code change or part of a codebase into an animated architecture, data-flow or data-model diagram you can drop straight into a pull request.

Turns a code change or codebase into an animated architecture, data-flow or data-model diagram you can drop straight into a pull request.

An authoritative lookup skill for the Claude/Anthropic SDK covering model IDs, params, streaming, tool use, agents, caching, and model migration.

A lint skill that structurally validates Claude Code agent and skill markdown files — frontmatter, naming, and body rules — so misconfigured files don't fail silently at runtime.

Internal skill for adding or extending Paperclip Runner protocol eval definitions, rosters, assertions, and report fixtures with strict provenance and narrow validation.

Diffs HEAD against the latest published npm versions and reports every unpublished change per release layer, with semver bump recommendations.

Turns Claude into an orchestrator that delegates each phase of an implementation plan to specialized subagents and blocks commits until verification passes.

An internal, evidence-driven loop for improving Archify diagram accuracy, readability and authoring speed.

An architecture skill that audits your layers, boundaries and SOLID usage against the Dependency Rule and prescribes concrete inversions.

Keeps every change strictly inside the requested scope and routes extra ideas into a Suggestions list instead of the diff.

Commits the working tree as one commit per logical change, merges in upstream, resolves conflicts hunk by hunk, and pushes — never with force.

A staged playbook for publishing Python, R, and static content to a Posit Connect server with the correct commands and flags.