All authors
Claude Skills by PyModel
github.com/PyModel31 skills4 installs70 views
- NibletKeep interface work anchored to the product it belongs to instead of a generic template. Sets a short design contract, builds from the components and tokens already in the codebase, covers the states a surface can actually reach, and closes by looking at the rendered result. Use when building, reworking, or assessing a web or native interface. Trigger with "niblet", "niblet skill", "niblet designer ui", or "niblet review". Skip backend, CLI, data, and infrastructure work, prose-only tasks, an...Votes: 0GitHub stars: 101
- Jev McpUse before a step that judges material you already have — a claim against evidence, screening fetched text before reading it, classifying or keeping or dropping many items, finding or reranking candidates, one bounded choice, comparing two passages, grading on an ordered rubric, extracting a regex-matched value, reviewing a patch, or checking that work finished. Batch every question about one state into one call. Jev is invoked when an unresolved judgment earns a model decision. Deterministic...Votes: 0GitHub stars: 84
- Test AuditInvoke whenever writing, changing, reviewing, or sweeping tests in jev-judge-mcp. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand, under this repo's rule that a test is never deleted or weakened to make a failing build pass.Votes: 0GitHub stars: 84
- AdrA client that only speaks MCP never sees a checkout path. The routing skill already lived in docs. The `jev` skill teaches the Jev API, which is a different job. Both have to travel inside the installed package, and initialize has to say which is which.Votes: 0GitHub stars: 84
- JevUse when code needs a judgment about natural language that rules or regex cannot make (classify, route, triage, moderate, score, rank, match, dedupe, filter, extract, verify, or gate an action), when brainstorming where AI could fit in an app, when an LLM call exists only to pick a label, score, or yes/no, or when code uses TypeSafe AI, Jev, System One, typesafe-sdk, or @typesafe-ai/sdk.Votes: 0GitHub stars: 84
- Jev McpUse before a step that judges material you already have — a claim against evidence, screening fetched text before reading it, classifying or keeping or dropping many items, finding or reranking candidates, one bounded choice, comparing two passages, grading on an ordered rubric, judging a file without reading it into your context, extracting a regex-matched value, reviewing a patch, or checking that work finished. Batch every question about one state into one call. Jev is invoked when an unre...Votes: 0GitHub stars: 84
- CodexRun the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.Votes: 0GitHub stars: 31
- DelegateLet Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the Candidate Artifact, record a decision, and integrate only accepted bytes. Use for implementation delegation, Producer selection, or commitment-boundary review.Votes: 0GitHub stars: 31
- Subagent Driven DelegationExecute an implementation plan with the Superpowers subagent-driven-development loop while every task is implemented by a verified Claude Architect Producer — isolated worktree, frozen Candidate Artifact, independent verification, fresh-context review, runtime-gated acceptance. Use when executing a multi-task plan through delegation rather than editing directly.Votes: 0GitHub stars: 31
- Feature ArchFeature-based React folder structure and module boundaries.Votes: 0GitHub stars: 27
- MswMSW 2 API mocking for tests.Votes: 0GitHub stars: 27
- NextjsNext.js 16 App Router caching and routing.Votes: 0GitHub stars: 27
- Nuqsnuqs type-safe URL search-param state.Votes: 0GitHub stars: 27
- PlaywrightPlaywright end-to-end tests and flaky-test fixes.Votes: 0GitHub stars: 27
- React Hook FormReact Hook Form 7 forms and validation.Votes: 0GitHub stars: 27
- ReactReact 19 components and hooks.Votes: 0GitHub stars: 27
- Shadcnshadcn/ui components on Radix or Base UI.Votes: 0GitHub stars: 27
- TailwindTailwind CSS v4 styling and configuration.Votes: 0GitHub stars: 27
- Tanstack QueryTanStack Query v5 data fetching and caching.Votes: 0GitHub stars: 27
- TddTest-driven development with red-green-refactor.Votes: 0GitHub stars: 27
- TypescriptTypeScript types, tsconfig and TypeScript 7 migration.Votes: 0GitHub stars: 27
- Ui DesignAccessible, responsive frontend UI and UX design.Votes: 0GitHub stars: 27
- Vercel Composition PatternsReact component API design with compound components.Votes: 0GitHub stars: 27
- Vercel React Best PracticesReact and Next.js performance optimization.Votes: 0GitHub stars: 27
- VitestVitest 5 unit tests and mocking.Votes: 0GitHub stars: 27
- Web Design GuidelinesReview UI code against Web Interface Guidelines.Votes: 0GitHub stars: 27
- ZodZod 4 schema validation and type inference.Votes: 0GitHub stars: 27
- done-means-doneFinish every part of a substantial assignment (code, research, writing, analysis or operations) against a durable ledger of the requested outcomes, executed evidence for each, every confirmed defect fixed, and a gate that alone decides done. Use for multi-part or multi-step work, exhaustive repairs, requests to finish everything, and resuming an unfinished assignment. Resume the same task; never substitute a smaller one.Votes: 0GitHub stars: 5
- code-maxUse when implementing, debugging, reviewing, refactoring, hardening, or migrating code where correctness matters, such as multi-step changes, regressions, data or API migrations, and security or trust boundaries. Enforces evidence-backed acceptance criteria, regression protection, clean minimal diffs, and an honest completion report in any language or toolchain. Skip trivial edits such as typo fixes or one-line cosmetic changes.Votes: 0GitHub stars: 4
- Agy DelegateDelegate a coding task to the Google Antigravity CLI (`agy`) as a separate implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use Antigravity to implement/fix/refactor" - or wants to run a queue of coding tasks through agy while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user w...Votes: 0GitHub stars: 2
- Agy DelegationUse when analyzing large files (>200 lines), more than 3 files at once, deep git/grep searches, web lookups, or adversarial reviews - delegates to the Antigravity CLI via claude-agy-mcp MCP tools to save context.Votes: 0GitHub stars: 2