tomevault-io
- 62k skills
- 0 followers
- 5 hours ago last updated
- ▌ Code Review 232 · tomevault-io bundleReviews Workers and Cloudflare Developer Platform code for type correctness, API usage, and configuration validity. Load when reviewing TypeScript/JavaScript using Workers APIs, wrangler.jsonc/toml config, or Cloudflare bindings (KV, R2, D1, Durable Objects, Queues, Vectorize, AI, Hyperdrive). Use when this capability is needed.
- ▌ Brainstorming 38 · tomevault-io bundleYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Use when this capability is needed.
- ▌ Writing Plans 20 · tomevault-io bundleUse when you have a spec or requirements for a multi-step task, before touching code
- ▌ Backend Testing 3 · tomevault-io bundleTesting de APIs y servicios backend generados por LuxCode AI. Aplica cuando el usuario pide tests, coverage, mocks, fixtures, o revisión de calidad en APIs Node.js/Express. Use when this capability is needed.
- ▌ Golang Patterns 10 · tomevault-io bundleIdiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications. Use when this capability is needed.
- ▌ Feishu E2e Test 2 · tomevault-io bundleLocal E2E debug and test framework for clawd-feishu plugin development. Use when debugging message flow, testing bot responses, verifying Feishu web UI interactions, or performing end-to-end validation of the OpenClaw-Feishu integration during development. Use when this capability is needed.
- ▌ Dev 10 · tomevault-io bundleMaintainer guide for atlas_doc_parser development. Use when implementing ADF marks/nodes, understanding codebase architecture, or writing tests. Use when this capability is needed.
- ▌ API Integration 5 · tomevault-io bundleUse when integrating Apidog + OpenAPI specifications with your React app. Covers MCP server setup, type generation, and query layer integration. Use when setting up API clients, generating types from OpenAPI, or integrating with Apidog MCP.
- ▌ Tailwind Setup 2 · tomevault-io bundleSet up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling Use when this capability is needed.
- ▌ Writing Assistant 2 · tomevault-io bundleWriting assistant for polishing, rewriting, expanding, and structuring text. Handles articles, emails, reports, and social media posts. Use when this capability is needed.
- ▌ Skill Creator 165 · tomevault-io bundleThis skill provides guidance for creating effective skills. Use when this capability is needed.
- ▌ Debugging 12 · tomevault-io bundleSystematic approach to debugging Python code - use when user encounters errors or unexpected behavior Use when this capability is needed.
- ▌ AI Agent Development 3 · tomevault-io bundleAI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents. Use when this capability is needed.
- ▌ Git Commit 32 · tomevault-io bundleAutomatically analyzes code changes and creates git commits with conventional commit messages when the user indicates they want to save/commit their work. Use when user mentions committing, saving work, or wants changes recorded in git history. Examples - "commit these changes", "save this work", "I'm done with this feature, let's commit", "create a commit for the auth updates". Use when this capability is needed.
- ▌ Brainstorming 40 · tomevault-io bundleUse when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
- ▌ Writing Plans 22 · tomevault-io bundleUse when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
- ▌ Security 19 · tomevault-io bundleScan a repository for security vulnerabilities — SSRF, injection (SQL, command, query-language), path traversal, unsafe deserialization, secret exposure, GitHub Actions injection, and missing rate-limit handling. Uses grep patterns plus contextual code reading to reduce false positives. Use when this capability is needed.
- ▌ Summarize 13 · tomevault-io bundleAuto-generate session summary using AI analysis of the conversation Use when this capability is needed.
- ▌ Gemini CLI 9 · tomevault-io bundleRun autonomous dev tasks using Gemini CLI (gemini-cli) with Maxime's free Google quota. Use for programming projects where MARS needs to delegate agentic coding work — file edits, code gen, refactoring, analysis — to Gemini in a project directory. Use when this capability is needed.
- ▌ Skill Creator 166 · tomevault-io bundleGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations. Use when this capability is needed.
- ▌ Tdd 33 · tomevault-io bundleTest-Driven Development enforcement skill - write tests first, always Use when this capability is needed.
- ▌ Rdkit 4 · tomevault-io bundleModern RDKit workflows for cheminformatics, including molecular fingerprints, drawing, and property calculations. Use when working with molecules, SMILES, molecular fingerprints (Morgan, ECFP, RDKit, atom pairs, topological torsions), molecule visualization/drawing, substructure search, or chemical property calculations. This skill provides up-to-date syntax patterns as RDKit's API evolves. Use when this capability is needed.
- ▌ PDF Processing 4 · tomevault-io bundleProcess and extract information from PDF documents. Use this skill when the user asks to read, analyze, or extract data from PDF files. Use when this capability is needed.
- ▌ Inject Nextjs Docs 2 · tomevault-io bundleRun the Next.js agents-md codemod to inject compressed framework documentation Use when this capability is needed.
- ▌ Code Review 240 · tomevault-io bundleReview pending changes in the transformer-spectrum repo for correctness and the silent-bug classes this spectral-analysis research codebase actually hits — SGT/robust-loss math & gradients, spectral-metric reliability (HTSR vs Zipf, small-matrix Hill/KS, Marchenko-Pastur), the paired-seed/leakage/test-split experiment protocol, the ES/GA tiny-model + matched-loss contract, the MLflow metric-name & artifact-selector contract, model tensor-shape/autoregressive/checkpoint contracts, and secrets/large-file hygiene. Read-only by default; surfaces findings grouped by severity. Use before every commit, or via /commit-push. Use when this capability is needed.
- ▌ Documentation Writer 12 · tomevault-io bundleDiátaxis Documentation Expert. Expert technical writer specializing in high-quality software documentation guided by the Diátaxis framework (tutorials, how-tos, reference, explanation). Use when this capability is needed.
- ▌ Run Tests 17 · tomevault-io bundleGuide for running pytest tests locally. Use this when running tests to verify code changes. Use when this capability is needed.
- ▌ Mobile 2 · tomevault-io bundleMobile development with React Native, Flutter, and native patterns Use when this capability is needed.
- ▌ Python 13 · tomevault-io bundlePython programming patterns and best practices Use when this capability is needed.
- ▌ Research 31 · tomevault-io bundle多 Agent 並行研究框架 - 多視角同時研究,智能匯總成完整報告 Use when this capability is needed.
- ▌ Tooluniverse 2 · tomevault-io bundleRouter skill for ToolUniverse tasks. First checks if specialized tooluniverse skills (105+ skills covering disease/drug/target research, gene-disease associations, clinical decision support, genomics, epigenomics, proteomics, comparative genomics, chemical safety, toxicology, systems biology, and more) can solve the problem, then falls back to general strategies for using 2300+ scientific tools. Covers tool discovery, multi-hop queries, comprehensive research workflows, disambiguation, evidence grading, and report generation. Use when users need to research any scientific topic, find biological data, or explore drug/target/disease relationships. ALSO USE for any biology, medicine, chemistry, pharmacology, or life science question — even simple factoid questions like "how many X in protein Y", "what drug interacts with Z", "what gene causes disease W", or "translate this sequence". These questions benefit from database lookups (UniProt, PubMed, ChEMBL, ClinVar, GWAS Catalog, etc.) rather than answering from me
- ▌ Mobile Use Setup 2 · tomevault-io bundleInteractive setup wizard for Minitap mobile-use SDK. USE WHEN user wants to set up mobile automation, configure mobile-use SDK, connect iOS or Android devices, or create a new mobile testing project. Use when this capability is needed.
- ▌ Frontend Testing 2 · tomevault-io bundleWHEN testing any front-end UI with DOM Testing Library; behavior-first queries, userEvent flows, async patterns. Use when this capability is needed.
- ▌ Google Workspace 3 · tomevault-io bundleAccess Google Workspace APIs (Drive, Docs, Calendar, Gmail, Sheets, Slides, Chat, People) via local helper scripts without MCP. Handles OAuth login and direct API calls. Use when this capability is needed.
- ▌ Update Changelog 6 · tomevault-io bundleRead this skill before updating changelogs Use when this capability is needed.
- ▌ Memory 6 · tomevault-io bundlePersistent memory system — use proactively to remember decisions, fixes, learnings, and preferences across sessions. Invoke when you need to save or recall important context. Use when this capability is needed.
- ▌ Agents Md Generator 4 · tomevault-io bundleAnalyze repository structure and generate standardized AGENTS.md files that serve as contributor guides for AI agents. Measures LOC to determine character limits and produces 5-section documents covering overview, folder structure, patterns, conventions, and working agreements. Use when this capability is needed.
- ▌ Conventional Commit 2 · tomevault-io bundleCreates conventional commit messages and commits changes to git. Use when committing code changes, following conventional commit standards, or preparing commits with proper formatting.
- ▌ Make Skill Template 2 · tomevault-io bundleCreate new Agent Skills for AI assistants from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional scripts/references/assets folders. Use when this capability is needed.
- ▌ Coding Standards 11 · tomevault-io bundlePython/Terraformのコーディング規約。コード作成、修正、レビュー時に参照。型ヒント、dataclass、Ruff、CIDR設定など。 Use when this capability is needed.
- ▌ Skill Creator 167 · tomevault-io bundleGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when this capability is needed.
- ▌ Kimi CLI Help 3 · tomevault-io bundleAnswer Kimi Code CLI usage, configuration, and troubleshooting questions. Use when user asks about Kimi Code CLI installation, setup, configuration, slash commands, keyboard shortcuts, MCP integration, providers, environment variables, how something works internally, or any questions about Kimi Code CLI itself. Use when this capability is needed.
- ▌ Skill Creator 168 · tomevault-io bundleCreate or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets. Use when this capability is needed.
- ▌ LLM Context 2 · tomevault-io bundleGuidelines for working with LLM context stored in the .llm/ directory. Use when this capability is needed.
- ▌ C Ecosystem 2 · tomevault-io bundleThis skill should be used when working with C++ projects, CMakeLists.txt, Ninja, clang-tidy, clang-format, GoogleTest, Catch2, or Modern C++ (C++11-23) language patterns. Provides comprehensive C++ ecosystem patterns and best practices. Use when this capability is needed.
- ▌ Golang Error Handling 2 · tomevault-io bundleIdiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log aggregation 3rd-party tools. Apply when creating, wrapping, inspecting, or logging errors in Go code. Use when this capability is needed.
- ▌ Golang Project Layout 2 · tomevault-io bundleProvides a guide for setting up Golang project layouts and workspaces. Use this whenever starting a new Go project, organizing an existing codebase, setting up a monorepo with multiple packages, creating CLI tools with multiple main packages, or deciding on directory structure. Apply this for any Go project initialization or restructuring work.
- ▌ Typescript 24 · tomevault-io bundleComprehensive TypeScript skill — language fundamentals, type system, generics, developer workflow (TDD, Vitest, DI), Red-Green-Refactor discipline, and clean architecture patterns. Use for any TypeScript development, testing, or design task. Use when this capability is needed.
- ▌ Code Reviewer 42 · tomevault-io bundleCode quality specialist who reviews changes, suggests improvements, and maintains standards Use when this capability is needed.
- ▌ Feature Creator 2 · tomevault-io bundleGuide for creating DevContainer features. Use when creating a new feature for devcontainer, implementing install.sh scripts (npm package, binary download, source build, dotnet tool, or directory setup patterns), or configuring devcontainer-feature.json metadata. Triggers on phrases like "create a feature", "add devcontainer feature", "install.sh template", or "devcontainer-feature.json". Use when this capability is needed.
- ▌ Python Quality 2 · tomevault-io bundleRun formatting, linting, and tests using uv + Ruff + pytest Use when this capability is needed.
- ▌ Test Writer 8 · tomevault-io bundleWrite tests with TDD following structured patterns. Ensures consistent AAA structure, proper coverage targets, and framework-specific conventions. Without this skill, tests lack consistent naming, miss coverage targets, and skip anti-pattern checks. Use when this capability is needed.
- ▌ Executing Plans 3 · tomevault-io bundleExecution discipline that translates plans into tracked tasks with orchestration and verification loops. Use when driving a plan through cortex’s task system, coordinating workstreams across agents, or ensuring every plan item is tracked, executed, and verified. Use when this capability is needed.
- ▌ Test Generation 2 · tomevault-io bundleUse when generating tests for new or existing code to improve coverage - provides a structured workflow for analyzing code, creating tests, and validating coverage goals.
- ▌ Librarian 4 · tomevault-io bundleResearch open-source libraries with evidence-backed answers and GitHub permalinks. Use when the user asks about library internals, needs implementation details with source code references, wants to understand why something was changed, or needs authoritative answers backed by actual code. Excels at navigating large open-source repos and providing citations to exact lines of code. Use when this capability is needed.
- ▌ CI CD Pipeline 10 · tomevault-io bundleGitHub Actions workflows, testing automation, deployment triggers for CampusOS. Use when setting up CI/CD, automating tests, configuring deployments, or managing workflow triggers. Use when this capability is needed.
- ▌ Executing Plans 4 · tomevault-io bundleExecute implementation plans one commit at a time. Follow the order from brainstorm, implement, test REAL, commit. Use when this capability is needed.
- ▌ Subagent Driven Development 7 · tomevault-io bundleExecute plans via delegate_task subagents (2-stage review). Use when this capability is needed.
- ▌ Git Workflow 131 · tomevault-io bundleGit workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes. Use when this capability is needed.
- ▌ Atomic Commits 2 · tomevault-io bundleOrganize git changes into clean, atomic commits for better history. Use when the user has accumulated multiple changes and wants to split them into separate, logical commits. Triggers on "atomic commits", "split commits", "organize my changes", "clean commit history", or when many unrelated changes are staged together. Use when this capability is needed.
- ▌ Evaluation 5 · tomevault-io bundleEvaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU", "evaluate quantized model", "run nel". Handles deployment, config generation, and evaluation execution. Not for quantizing models (use ptq), deploying/serving models (use deployment), or comparing completed baseline-vs-quantized results (use compare-results). Use when this capability is needed.
- ▌ Development 3 · tomevault-io bundleProvides development tools and guidance. Use when developing code, debugging, or running anything in the development environment.
- ▌ Rust Quality 3 · tomevault-io bundleRust quality workflow for cargo fmt, Clippy, warning fixes, import/module cleanup, dead-code removal, edition idioms, feature hygiene, and behavior-preserving cleanup in greenfield crates. Use when this capability is needed.
- ▌ Documentation Writer 13 · tomevault-io bundleDiátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework. Templates for tutorial / how-to / reference / explanation live under templates/. Use when this capability is needed.
- ▌ Documentation 64 · tomevault-io bundleThis skill should be used when the user is setting up MkDocs Material, configuring mkdocstrings, writing docstrings, generating API reference pages, structuring documentation with the Diataxis framework, deploying docs to GitHub Pages or ReadTheDocs, or writing a README. Covers mkdocs.yml configuration, Griffe, Google-style docstrings, versioned docs with mike, code example testing, nav structure. Use when this capability is needed.
- ▌ Receiving Code Review 3 · tomevault-io bundleUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
- ▌ Typescript Standards 2 · tomevault-io bundleTypeScript coding standards. Use when writing TypeScript, reviewing code, or refactoring. Enforces named exports, no dynamic imports, discriminated unions, proper type safety. Use when this capability is needed.
- ▌ Mobile Design 2 · tomevault-io bundleMobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps. Use when this capability is needed.
- ▌ Nestjs Expert 9 · tomevault-io bundleNest.js framework expert specializing in module architecture, dependency injection, middleware, guards, interceptors, testing with Jest/Supertest, TypeORM/Mongoose integration, and Passport.js authentication. Use PROACTIVELY for any Nest.js application issues including architecture decisions, testing strategies, performance optimization, or debugging complex dependency injection problems. If a specialized expert is a better fit, I will recommend switching and stop. Use when this capability is needed.
- ▌ Skill Creator 169 · tomevault-io bundleGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when this capability is needed.
- ▌ Nodejs Backend Patterns 2 · tomevault-io bundleBuild production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices. Use when creating Node.js servers, REST APIs, GraphQL backends, or microservices architectures. Use when this capability is needed.
- ▌ API Security 2 · tomevault-io bundleSkills for testing API security including GraphQL and REST API vulnerabilities. Use when this capability is needed.
- ▌ Swiftui 2 · tomevault-io bundleSwiftUI patterns, view composition, styling, and reusable UI elements Use when this capability is needed.
- ▌ Spec Writing 3 · tomevault-io bundleGuide for creating high-quality, architecturally compliant specifications for Open Mercato. Use when starting a new SPEC or reviewing specs against "Martin Fowler" staff-engineer standards. Use when this capability is needed.
- ▌ Snap O Network Inspector 2 · tomevault-io bundleFetch and inspect Android network captures for a selected device/socket using the Snap-O CLI. Use when you need raw CDP request/response data, headers, bodies, status, or websocket events. Use when this capability is needed.
- ▌ Test Runner 8 · tomevault-io bundleRun pytest tests in the openreview-py repository, including starting the required API servers. Use this skill whenever the user wants to run tests, validate code changes, check if tests pass, start/restart test servers, start services for browser testing, open an interactive shell, or mentions a specific test file. Also use when you've just written a significant chunk of code that should be tested. Even if the user just says 'run tests' or 'does this pass?', this skill applies. Use when this capability is needed.
- ▌ Bear Notes 13 · tomevault-io bundleCreate, search, and manage Bear notes via grizzly CLI. Use when this capability is needed.
- ▌ Web Search 16 · tomevault-io bundleSearch the web for information and fetch URL content. Use when user asks to search for recent information, look up websites, fetch web page content, or find online resources. No external tools required — uses built-in web_search and web_fetch capabilities. Use when this capability is needed.
- ▌ Github Issues 9 · tomevault-io bundleManage GitHub issues using the GitHub CLI (gh) Use when this capability is needed.
- ▌ Plan 21 · tomevault-io bundleGenerates a detailed architectural or execution plan and saves it to docs/plan/. Use this ONLY when the user explicitly asks to "plan" or "create a plan".
- ▌ Osaurus Browser 2 · tomevault-io bundleTeaches the agent how to use the headless browser tools — per-agent persistent sessions, the open_login helper, refs, batching, detail levels, console/network inspection, dialogs, viewport/UA, cookies, and lock/unlock for multi-agent safety. Use when this capability is needed.
- ▌ Next Cache Components 7 · tomevault-io bundleNext.js 16 Cache Components - PPR, use cache directive, cacheLife, cacheTag, updateTag Use when this capability is needed.
- ▌ Debug Phase 2 · tomevault-io bundleStandard Operating Procedure for /debug phase. Covers error investigation, root cause analysis, systematic debugging, and error documentation. Use when this capability is needed.
- ▌ V3 MCP Optimization 2 · tomevault-io bundleMCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring for sub-100ms response times. Use when this capability is needed.
- ▌ Refactor 32 · tomevault-io bundleCode refactoring workflow - analyze → plan → implement → review → validate Use when this capability is needed.
- ▌ Research 32 · tomevault-io bundleDocument codebase as-is with thoughts directory for historical context Use when this capability is needed.
- ▌ Rewrite Tests Pest 2 · tomevault-io bundleUse when rewriting existing tests to PEST syntax. Follows project conventions, ensures DRY principles, uses data providers, maintains 100% coverage, and verifies test functionality.
- ▌ Swift Expert 3 · tomevault-io bundleExpert-level Swift development for iOS, macOS with SwiftUI, Combine, and modern Swift 5.9+ Use when this capability is needed.
- ▌ Brainstorming 41 · tomevault-io bundleYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Use when this capability is needed.
- ▌ Update Docs 24 · tomevault-io bundleUpdate documentation pages to match source code changes on the current branch Use when this capability is needed.
- ▌ Skill Creator 170 · tomevault-io bundleCreate new skills for FeatherBot Use when this capability is needed.
- ▌ Rust Pro 8 · tomevault-io bundleMaster Rust 1.75+ with modern async patterns, advanced type system features, and production-ready systems programming. Use when this capability is needed.
- ▌ Angular Forms 3 · tomevault-io bundleBuild signal-based forms in Angular v21+ using the new Signal Forms API. Use for form creation with automatic two-way binding, schema-based validation, field state management, and dynamic forms. Triggers on form implementation, adding validation, creating multi-step forms, or building forms with conditional fields. Signal Forms are experimental but recommended for new Angular projects. Use when this capability is needed.
- ▌ Git Workflow 132 · tomevault-io bundleEssential Git commands, GitHub CLI (gh) operations, and version control workflows for branching, collaboration, CI checks, and API queries. Use when working with git, GitHub, PRs, CI, or version control. Use when this capability is needed.
- ▌ Plurigrid Asi Integrated 2 · tomevault-io bundleUnified Plurigrid ASI skill combining ACSets, Gay-MCP colors, bisimulation games, world-hopping, glass-bead synthesis, and triad interleaving for autonomous skill dispersal. Use when this capability is needed.
- ▌ Plugin Validator 2 · tomevault-io bundleValidate Claude Code plugin structure, manifests, frontmatter, and dependencies. Use when user mentions "validate plugin", "check plugin health", "plugin broken", "plugin not loading", "plugin errors", "plugin.json invalid", "agent not working", "check plugin structure", or reports plugin-related issues. Use when this capability is needed.
- ▌ Web Research 10 · tomevault-io bundleQuery Pollinations text API with web-search models (gemini-search, perplexity-fast, nomnom, etc.). Use when you need web search grounded answers via Pollinations. Use when this capability is needed.
- ▌ Code Review 241 · tomevault-io bundlegit diff を外部 AI CLI(Claude Code / Codex / Gemini)に送ってレビューし、結果を集約・比較する。 Use when this capability is needed.
- ▌ Clean Architecture 3 · tomevault-io bundleClean Architecture principles and best practices from Robert C. Martin's book. This skill should be used when designing software systems, reviewing code structure, or refactoring applications to achieve better separation of concerns. Triggers on tasks involving layers, boundaries, dependency direction, entities, use cases, or system architecture. Use when this capability is needed.
- ▌ Brainstorm 9 · tomevault-io bundleRun interactive brainstorming across verifiers environments, evaluations, GEPA, and RL training. Use when the user wants ideation, literature scanning, concept teaching, roadmap planning, or research program design grounded in local CLI sources, verifiers, and RL trainer code. Use when this capability is needed.