开发 Skill

--- name: novaeval-scorer description: Add a new scorer to the NovaEval repo end-to-end — implement the BaseScorer class and register it in ALL the required places (package __init__, the app.utils name→class map, model-dependency set, ScorerType enum + ScorerFactory if a new...

Implement a specification in code.

Evaluate Clojure code via nREPL using clj-nrepl-eval. Use this when you need to test code, check if edited files compile, verify function behavior, or interact with a running REPL...

Guide Clojure and ClojureScript development using REPL-driven workflow, coding conventions, and best practices. Use when writing, developing, or refactoring Clojure/ClojureScript...

Scaffold a new Metabase data-app into the connected remote-sync repository's directory from the . Use when the user asks to start, create, scaffold, or set up a data-app from...

Risk-scaled repo execution and code-evidence protocol. Skip architecture-only work, explanation, contract-preserving prose, and status. Use for contract changes, debugging, code...

Orchestrate the Rust compiler port end-to-end. Discovers the current frontier, fixes failing passes, ports new passes, reviews, and commits in a loop.

Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.

One-stop code change workflow.

Use when executing implementation plans with independent tasks in the current session

Builds with and operates Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings/environment variables, creating Pi...

Use when creating a new OpenCLI adapter from scratch, adding support for a new website or platform, exploring a site's API endpoints via browser DevTools, or when a user asks to...

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with...

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with...

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run...

Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages. Use when...

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action....

Commercial-grade Python installer expert for Windows: Nuitka extreme compilation, dist slimming, DLL footprint analysis, and Inno Setup packaging to ship the smallest, fastest...

C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.

Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns....

Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out...

Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.

Pattern for progressively refining context retrieval to solve the subagent context problem