Coding & Dev Tools

Defines quality standards and validation checklists for agent workflows, Python tools, and documentation, including automated checks and pre-commit gates.

Automates the preparation of Easy difficulty diagram specifications from a CSV report and chapter files, generating reports, execution plans, and spec files for MicroSim generation.

Converts legacy agent resources such as subagents, commands, and rules into the unified Agent Skills format, with classification, conversion, and verification steps.

Provides guidelines and best practices for aggregates and aggregate roots, referencing detailed documentation.

Teaches Rust traits, generics, and type system concepts with code examples and best practices.

Reference for the Agent Script language used in Salesforce Agentforce, covering syntax, deployment methods, and troubleshooting.

Guides setting up Drizzle ORM with Vercel Postgres and Vercel KV for a manufacturing analysis app, covering schema definition, queries, migrations, caching, sessions, and rate limiting.

Runs throwaway experiments to validate feasibility before building, producing a verdict with evidence.

Renders text or images as ASCII art for terminal-friendly output, including banners, frames, QR codes, and weather.

Authenticates to GitHub using a token, SSH key, or the gh CLI, with guidance for troubleshooting common auth failures.

Create, search, triage, and label GitHub issues using the gh CLI or REST API, with guidance on avoiding duplicates and managing the backlog.

Runs three parallel reviewers to find code reuse, quality, and efficiency issues in a diff, then applies safe fixes and reports risky ones.

Reviews local git changes and GitHub pull requests, leaving inline comments and formal reviews.

Guides a coding agent through the full GitHub pull request lifecycle: branch, commit, open PR, monitor CI, fix failures, merge, and clean up, using either the gh CLI or git plus curl.

Diagnose bugs by establishing a tight feedback loop, tracing root cause, and verifying fixes with regression tests before making changes.

Manage GitHub repositories end-to-end: clone, create, fork, configure settings, protect branches, set secrets, create releases, and run workflows using gh or git+curl.

Verifies a code change before it lands by scanning the staged diff, running tests, and delegating to an independent reviewer.

麦当劳助手 - 查询/领取优惠券、活动日历、餐品营养信息、门店查询

Fetches recent GitHub activity from the Nom feed and presents it as a clear, readable summary.

Build on-chain relational databases on Solana using IQ Labs' IQDB, hanLock, and x402 tools, including CRUD operations, tamper-evident rolling hashes, password-based encoding, and payment-gated file inscription.

Generates structured VGL JSON for Bria FIBO models, giving deterministic control over objects, lighting, camera, composition, and style instead of natural language prompts.

Provides Git-like version control for ArcGIS web maps, wrapping the gitmap CLI to expose branch, commit, diff, push/pull, and map discovery as callable tools.

Manages aria2 downloads via its RPC interface, supporting magnet links, torrents, and HTTP files, with commands to add, monitor, pause, resume, and remove tasks.

Design and implement Oban background job workers for Elixir, covering queue configuration, retries, uniqueness, cron scheduling, and testing.

Interact with the Plaid finance platform to link bank accounts, fetch balances, and query transactions by date range using the plaid-cli tool.

Configures a self-driving development loop for JavaScript/TypeScript projects, generating configuration files and preparing OpenTangl to run autonomously.

Generates a pull request title and body from local git history, writing them to a draft file for review before publishing.

Turns working-tree changes into well-formed local commits following Conventional Commits, with atomic boundaries and issue references.

Systematically adds unit test coverage to existing source files in any project, tracking progress across sessions via scan, plan, and write modes.

Publishes a reviewed GitHub issue draft by creating or editing an issue with the gh CLI, assigning it to the current user, and never commenting, closing, or reopening issues.

Switches Claude Code into a teaching-first mode for unfamiliar technologies, explaining concepts and commands step by step without writing code until approved.

Enforces rigorous ML modeling, feature engineering, training, and evaluation standards at principal-engineer level.

Enforces principal-engineer-level Python code quality: formatting, type safety, idiomatic patterns, class and function design, and anti-pattern prevention.

Enforces system design, project structure, dependency management, error handling, testing, and documentation standards at principal-engineer level.

Enforces complexity analysis, correct data structure selection, vectorization, and algorithm implementation discipline at principal-engineer level.

Guides test-first development with vertical slices, one test at a time, and refactoring after green.