← all publishers

majiayu000

@majiayu000 source repo

Report this profile Claim this profile

• 75k skills
• 0 followers
• 567 repo stars
• 3 weeks ago last updated

1. ▌
   Analyze Bug · majiayu000 bundle

   Use this skill when you receive a bug report or issue description and need to verify whether the reported behavior is actually a bug. This agent will attempt to reproduce the issue systematically, validate the steps to reproduce, and confirm whether the behavior deviates from expected functionality.
   567 repo stars
2. ▌
   API Testing · majiayu000 bundle

   Test and debug Next.js API routes, validate responses, check authentication, and troubleshoot API errors. Use when testing API endpoints, debugging 500 errors, validating API responses, or checking authentication flows.
   567 repo stars
3. ▌
   Ark Testing · majiayu000 bundle

   Test the Ark Dashboard with Playwright and create PRs with screenshots. Use this skill when testing dashboard UI, taking screenshots for PRs, or validating dashboard changes.
   567 repo stars
4. ▌
   Audit Tests · majiayu000 bundle

   Audit the test suite for useless tests, consolidation opportunities, over-mocking, weak assertions, placement/organization issues, xdist safety violations, and other test quality issues. Use when user says "audit tests", "audit test suite", "review tests", or "test quality check". Generates an improvement plan in temp/ with explanations for each proposed change.
   567 repo stars
5. ▌
   Auto Verify · majiayu000 bundle

   Attempt automated verification of criteria before falling back to manual. Parses criterion text for automation hints and executes appropriate tool (curl, browser, file check). Invoked by verify-task and phase-checkpoint for MANUAL and MANUAL:DEFER criteria.
   567 repo stars
6. ▌
   Autofixture · majiayu000 bundle

   Guidance for AutoFixture test data generation library. USE FOR: auto-generating test data for unit tests, reducing boilerplate in the Arrange phase, creating anonymous objects and collections, customizing test data generation rules, integrating with Moq (AutoMoq) and xUnit for fully automated test setup. DO NOT USE FOR: integration test data seeding, production data generation, load testing data, or replacing dedicated faker libraries when realistic domain data is required.
   567 repo stars
7. ▌
   Backend Dev · majiayu000 bundle

   This skill should be used when developing backend services for Manjha using Encore.ts, implementing agents, writing E2E tests, or working with the message-driven architecture. It ensures adherence to TDD practices, type safety, proper logging, and Manjha's development principles.
   567 repo stars
8. ▌
   Barqnet E2e · majiayu000 bundle

   Orchestrator agent that coordinates all BarqNet specialized agents (backend, integration, client, documentation, audit, testing) to execute complete end-to-end workflows. Plans multi-agent deployments, manages task dependencies, tracks progress across all platforms, and ensures comprehensive completion. Use for complex multi-component tasks, full-stack features, or production deployments.
   567 repo stars
9. ▌
   Browser CLI · majiayu000 bundle

   Control Firefox browser from the command line. Use for web automation, scraping, testing, or any browser interaction tasks.
   567 repo stars
10. ▌
    Browser Ops · majiayu000 bundle

    Browser automation skill for AI coding agents. 25 Playwright-based tools for navigation, interaction, observation, and session management.
    567 repo stars
11. ▌
    Browser Use · majiayu000 bundle

    Web scraping, screenshots, form filling, file downloads/uploads, Google/DuckDuckGo image search, YouTube video downloading, and TikTok video downloading.
    567 repo stars
12. ▌
    Check Tests · majiayu000 bundle

    Analyze test health beyond coverage numbers
    567 repo stars
13. ▌
    Create Test · majiayu000 bundle

    Analyze a Java class and scaffold a JUnit 5 test with proper structure and assertions
    567 repo stars
14. ▌
    Cypress API · majiayu000 bundle

    API testing patterns with Cypress for CRUD operations. Covers BaseAPIController, entity controllers, test structure, and BDD documentation. Use this skill when writing API tests or creating new entity API controllers.
    567 repo stars
15. ▌
    Cypress E2e · majiayu000 bundle

    End-to-End testing patterns with Cypress for UAT tests. Covers test structure, cy.session(), batch execution, tags, POMs, and BDD documentation. Use this skill when writing UAT tests or creating new entity test files.
    567 repo stars
16. ▌
    Github Sync · majiayu000 bundle

    Two-way synchronization between SpecWeave specs and GitHub Projects (push & pull by default). Activates ONLY when user asks questions about GitHub integration or needs help configuring GitHub sync. Does NOT activate for slash commands. For syncing, use /sw-github:sync-spec command instead.
    567 repo stars
17. ▌
    Golden Test · majiayu000 bundle

    Write or update low-noise golden prompt tests in puppeteer/tests, including minimal decks, replay scripts, and golden regeneration.
    567 repo stars
18. ▌
    Ha Emby Tdd · majiayu000 bundle

    Use when implementing ANY code for the Home Assistant Emby integration - enforces strict TDD with RED-GREEN-REFACTOR cycle, requiring tests to fail before implementation and pass after. No exceptions for simple code.
    567 repo stars
19. ▌
    Jepsen Test · majiayu000 bundle

    Run Jepsen-style cluster tests using Maelstrom (lightweight) or full Jepsen (heavyweight) — validates correctness of the deployed gossip-rs system with real network behavior, complementing in-process DST
    567 repo stars
20. ▌
    Jest Vitest · majiayu000 bundle

    Use this skill when writing unit tests with Jest or Vitest, implementing mocking strategies, configuring test runners, or improving test coverage. Triggers on Jest, Vitest, describe/it/expect, mocking, vi.fn, jest.fn, snapshot testing, test coverage, and any task requiring JavaScript/TypeScript unit testing.
    567 repo stars
21. ▌
    LLM Testing · majiayu000 bundle

    Testing patterns for LLM-based applications. Use when testing AI/ML integrations, mocking LLM responses, testing async timeouts, or validating structured outputs from LLMs.
    567 repo stars
22. ▌
    Memory Test · majiayu000 bundle

    Run E2E memory pipeline test — embed text, store in Qdrant, search and retrieve. Use to validate the memory system is working.
    567 repo stars
23. ▌
    Network 101 · majiayu000 bundle

    This skill should be used when the user asks to "set up a web server", "configure HTTP or HTTPS", "perform SNMP enumeration", "configure SMB shares", "test network services", or needs guidance on configuring and testing network services for penetration testing labs.
    567 repo stars
24. ▌
    Nw Pbt Rust · majiayu000 bundle

    Rust property-based testing with proptest, quickcheck, and bolero frameworks
    567 repo stars
25. ▌
    Pesttesting · majiayu000 bundle

    Laravel testing conventions using the Pest PHP framework. Covers test structure, AAA pattern, HTTP assertions, datasets, mocking, browser tests, and architecture tests.
    567 repo stars
26. ▌
    Postman API Testing · majiayu000 bundle

    API testing skill using Postman and Newman, covering collections, environments, pre-request scripts, test scripts, and CI/CD integration with Newman.
    567 repo stars
27. ▌
    Prepare App · majiayu000 bundle

    Starts development server for E2E testing. Detects package manager and verifies server startup. Triggers on keywords: prepare app, start server, dev server, start app
    567 repo stars
28. ▌
    Review Test · majiayu000 bundle

    Comprehensive test suite review across five phases. Surveys unit coverage, integration coverage, E2E (browser) coverage for webapps, fuzz coverage, and test quality — in that order. Advisory only — produces findings and proposes tickets; does not implement test changes.
    567 repo stars
29. ▌
    Spacing 001 · majiayu000 bundle

    "Fix the spacing on this component. The cards feel disconnected, like they're floating islands instead of a related group."
    567 repo stars
30. ▌
    Specsafe QA · majiayu000 bundle

    Run QA validation on completed implementation. Moves spec from CODE to QA stage.
    567 repo stars
31. ▌
    Test Bridge · majiayu000 bundle

    Bridge Server (TypeScript) のテスト実行・型チェック・テスト記述ガイド
    567 repo stars
32. ▌
    Test Design · majiayu000 bundle

    Apply test pyramid principles, coverage targets, and framework-specific patterns. Use when designing test suites, reviewing test coverage, or implementing tests. Covers Jest, Pytest, and common testing frameworks with naming conventions and organization patterns.
    567 repo stars
33. ▌
    Test Helper · majiayu000 bundle

    Write comprehensive, idiomatic tests following best practices and project conventions. Use this when writing unit tests, integration tests, or test fixtures. Helps ensure proper test structure, mocking, assertions, and coverage.
    567 repo stars
34. ▌
    Test Twilio · majiayu000 bundle

    Place Twilio test calls. Use when user invokes /test-twilio.
    567 repo stars
35. ▌
    Test Worker · majiayu000 bundle

    Generate a unit test for a Zeebe `@JobWorker` class using mockk (Kotlin) or Mockito (Java), without any Spring context or Camunda test runtime. Use when the user asks to "write tests for a job worker", "generate tests for a worker", or "test a @JobWorker".
    567 repo stars
36. ▌
    Tui Testing · majiayu000 bundle

    VHS-based TUI testing workflow using .tape files for visual analysis. Use when testing invowk tui commands, verifying visual layout/colors, or debugging TUI with screenshots.
    567 repo stars
37. ▌
    UI Evidence · majiayu000 bundle

    Use when an agent needs to bootstrap ui-evidence in a repo, then discover, configure, or run before/after UI screenshot capture, current UI snapshot capture, local HTML review generation, or git-baseline UI evidence workflows for a web app.
    567 repo stars
38. ▌
    Ultra Think · majiayu000 bundle

    Advanced analytical framework for deep problem solving and multi-dimensional thinking. Systematically analyzes complex problems from technical, business, user, and system perspectives to generate comprehensive solutions with structured recommendations.
    567 repo stars
39. ▌
    Valid Skill · majiayu000 bundle

    A valid skill for testing with proper structure and content
    567 repo stars
40. ▌
    Validate Mr · majiayu000 bundle

    Use when you need a diff-derived test plan for an MR — reads the diff, groups changes by area, runs targeted verifications, and proves revert-tests are genuine guards, not dead assertions.
    567 repo stars
41. ▌
    Validate UI · majiayu000 bundle

    Valider l'interface et capturer les erreurs console. TRIGGERS : validate-ui, vérifier console, 0 erreur, validation UI, test UI
    567 repo stars
42. ▌
    Verify Rule · majiayu000 bundle

    Validate that a rule has all required files (analyzer, descriptor, test cases, docs) and passes tests. Use after implementing or modifying a rule to confirm completeness.
    567 repo stars
43. ▌
    Verify Task · majiayu000 bundle

    Run code-verification on a specific task. Use to verify a single task's acceptance criteria after implementation.
    567 repo stars
44. ▌
    Visual Test · majiayu000 bundle

    Visual iteration workflow for Script Kit GPUI. Use when making UI changes that need visual verification — focus indicators, colors, layout, shadows, spacing. Covers the named-pipe test pattern, captureWindow screenshots, and the build-capture-verify loop.
    567 repo stars
45. ▌
    Woo Testing · majiayu000 bundle

    Test WooCommerce extensions — PHPUnit unit/integration tests, WP test suite, WooCommerce test helpers, E2E with Playwright, and WP-CLI test scaffolding. Use when writing tests for WooCommerce plugins or setting up a test environment.
    567 repo stars
46. ▌
    Write Tests · majiayu000 bundle

    Generates comprehensive unit tests and integration tests for code with test coverage analysis and edge cases
    567 repo stars
47. ▌
    Add Camera · majiayu000 bundle

    Internal implementation skill invoked by /add-native for camera, image picker, barcode scanner, QR scanner, and camera/gallery Dataverse artifact workflows.
    567 repo stars
48. ▌
    Babysitter Assimilate · majiayu000 bundle

    Assimilate an external methodology, harness, or specification into babysitter process definitions.
    567 repo stars
49. ▌
    Async Task · majiayu000 bundle

    Execute long-running tasks without HTTP timeouts. Use when you need to:
    567 repo stars
50. ▌
    Crypto Hft · majiayu000 bundle

    Trade crypto binary markets on Polymarket with 4 automated strategies. Support: 5-min BTC, 15-min/1h/4h/daily all assets (BTC, ETH, SOL, XRP)
    567 repo stars
51. ▌
    Ds Handoff · majiayu000 bundle

    Create structured handoff document for DS workflow session pause/resume.
    567 repo stars
52. ▌
    Esper Atom · majiayu000 bundle

    Create or refine a single increment. Smart stage detection — no active creates one, incomplete refines, ready waits for `esper:go`.
    567 repo stars
53. ▌
    Esper Sync · majiayu000 bundle

    Update spec files to match shipped implementation. Records sync notes in the increment and finishes it when complete.
    567 repo stars
54. ▌
    Esper Yolo · majiayu000 bundle

    Implement all pending plans for the current phase automatically — commits at milestones, opens the phase PR when done. No stopping between plans.
    567 repo stars
55. ▌
    Gsd Health · majiayu000 bundle

    Diagnose planning directory health and optionally repair issues
    567 repo stars
56. ▌
    Inbox Zero · majiayu000 bundle

    Scan your support inbox and batch-process tickets with quick actions (reply, tag, assign, close)
    567 repo stars
57. ▌
    Nw Deliver · majiayu000 bundle

    Orchestrates the full DELIVER wave end-to-end (roadmap > execute-all > finalize). Use when all prior waves are complete and the feature is ready for implementation.
    567 repo stars
58. ▌
    Nw Execute · majiayu000 bundle

    Dispatches a single roadmap step to a specialized agent for TDD execution. Use when implementing a specific step from a roadmap.json plan.
    567 repo stars
59. ▌
    Pacsomatic · majiayu000 bundle

    Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. Use this skill when the user needs to validate run inputs, generate pacsomatic-compliant samplesheets, prepare reproducible Nextflow launch artifacts, run locally or submit to schedulers (LSF/Slurm/PBS/SGE), and triage execution failures. Triggers on requests to run pacsomatic, prepare launch commands/scripts, perform dry-run checks, or troubleshoot pipeline startup and scheduler submission errors.
    567 repo stars
60. ▌
    Paper Talk · majiayu000 bundle

    End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: "做 talk", "做 PPT 全流程", "talk pipeline", "end-to-end slides", "做演讲", "conference talk full workflow". Use when the user wants the complete talk artifact, not just a slide deck.
    567 repo stars
61. ▌
    Prime Sync · majiayu000 bundle

    Syncs Claude config between prime repo and target projects. Trigger on 'sync', 'prime-sync', 'push config', 'pull config', 'update prime', 'sync claude config'. Push mode deploys to targets; pull mode imports changes back.
    567 repo stars
62. ▌
    Babysitter Retrospect · majiayu000 bundle

    Analyze a completed or in-flight run and propose process improvements for future runs.
    567 repo stars
63. ▌
    Rfc Status · majiayu000 bundle

    Show RFC details or update RFC status through lifecycle
    567 repo stars
64. ▌
    Run Config · majiayu000 bundle

    Run configuration handling for persistent command configuration storage
    567 repo stars
65. ▌
    Run Status · majiayu000 bundle

    Display current run status and progress. Shows work item, mode, duration, and files changed.
    567 repo stars
66. ▌
    Sop Writer · majiayu000 bundle

    Write a Standard Operating Procedure (SOP) for any operational task. Use when asked to write an SOP, standard operating procedure, work instruction, or operating manual. Produces a formal SOP with purpose, scope, procedure steps, quality checks, and version control.
    567 repo stars
67. ▌
    Sparc Spec · majiayu000 bundle

    Run the SPARC Specification phase — gather requirements, define acceptance criteria, identify constraints, and store the spec in memory
    567 repo stars
68. ▌
    Spec Setup · majiayu000 bundle

    Initialize project-level state and configure specs via interactive questionnaire using cli-explore-agent
    567 repo stars
69. ▌
    Stack Push · majiayu000 bundle

    Pushes all branches in a stack and opens or updates one dependent PR per slice. Use after stack-create to publish the stack or after adding commits to a slice.
    567 repo stars
70. ▌
    Superhuman · majiayu000 bundle

    AI-native software development lifecycle that replaces traditional SDLC. Triggers on "plan and build", "break this into tasks", "build this feature end-to-end", "sprint plan this", "superhuman this", or any multi-step development task. Decomposes work into dependency-graphed sub-tasks, executes in parallel waves with TDD verification, and tracks progress on a persistent board. Handles features, refactors, greenfield projects, and migrations.
    567 repo stars
71. ▌
    Working On · majiayu000 bundle

    Set a tracking document as the source of truth for the current feature or task. Use when starting work on a feature, bug fix, or multi-step task that benefits from a persistent record of decisions, discoveries, and progress. Keeps the document updated as work proceeds.
    567 repo stars
72. ▌
    Blog Growth · majiayu000 bundle

    Use when user says "今天写什么", "博客诊断", "blog growth", "运营博客", or any daily blog operations request. Triggers data-driven content creation workflow combining Search Console analysis, trending topic research, and parallel article production.
    567 repo stars
73. ▌
    Content Prd · majiayu000 bundle

    Generate a Content Requirements Document for blog posts, docs, and marketing pages. Creates structured briefs with user stories optimized for AI agent execution. Triggers on: create content prd, write content for, plan this article, content brief for, spec out content.
    567 repo stars
74. ▌
    Guide Recap · majiayu000 bundle

    Transform CHANGELOG entries into social content (LinkedIn, Twitter/X, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate ready-to-post content from guide updates.
    567 repo stars
75. ▌
    Iso 24495 2 · majiayu000 bundle

    Sector-specific Plain Language standard for legal communication (ISO 24495-2:2025). Applied during contract drafting, license review, and legal/compliance writing.
    567 repo stars
76. ▌
    Paper Write · majiayu000 bundle

    Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.
    567 repo stars
77. ▌
    Patch Notes · majiayu000 bundle

    Generate player-facing patch notes from git history, sprint data, and internal changelogs. Translates developer language into clear, engaging player communication.
    567 repo stars
78. ▌
    Paul Graham · majiayu000 bundle

    Write clear, direct prose that sounds like a smart person thinking in public. Optimize for insight per sentence.
    567 repo stars
79. ▌
    Ppw Caption · majiayu000 bundle

    Generate or optimize figure/table captions for academic papers. Geography-aware: study area, CRS notation, data source. Writes output to .tex file. 图表标题生成与优化。
    567 repo stars
80. ▌
    Strong Edit · majiayu000 bundle

    Critical editorial analysis of articles. Examines structure, argument strength, relevance, and readability. Use for substantive editing - challenging what's said and how, not just polish.
    567 repo stars
81. ▌
    Agent Identity · majiayu000 bundle

    Without identity infrastructure, every Claude Code session starts from zero. The agent has no name, no remembered preferences, no sense of who it works with or what it has learned. Context compaction erases everything mid-session. This skill fixes that — no external tools required.
    567 repo stars
82. ▌
    Agent Steering · majiayu000 bundle

    Universal agent configuration patterns for any AI coding environment. Use when configuring steering, specs, or context assembly for Kiro, Claude Code, Codex, Charm, or other agents.
    567 repo stars
83. ▌
    Cc Agent Audit · majiayu000 bundle

    Claude Code 專案配置審計。觸發：review/優化 CLAUDE.md、skills、settings、定期清洗累積內容、新專案上線前檢查。
    567 repo stars
84. ▌
    Claude Consult · majiayu000 bundle

    Consult Claude specialist agents during implementation for codebase understanding, pattern checking, security review, debugging help, and more. Use this skill whenever you're unsure about conventions, stuck on a failure, or need expert input before writing code. Does not replace the formal review gates in agent-loops — this is for mid-implementation consultation.
    567 repo stars
85. ▌
    Copilot Studio · majiayu000 bundle

    Expert guidance for Microsoft Copilot Studio development including custom copilots, topic design, trigger phrases, actions, knowledge sources, generative AI answers, and channel publishing. Use when building conversational agents, designing topic flows, connecting knowledge bases, or publishing copilots to Teams and websites.
    567 repo stars
86. ▌
    Create Mission · majiayu000 bundle

    Create a new proactive background mission for the Nexus agent. A mission is a scheduled, autonomous task that the agent executes on a cron schedule without user interaction. Use this skill when the user asks to monitor something automatically, run a recurring check, or set up a background task. Keywords: mission, create, schedule, monitor, background, recurring, automatic, proactive, cron, periodic.
    567 repo stars
87. ▌
    Damage Control · majiayu000 bundle

    Recovers broken agent state via crash recovery, context overflow, and merge conflict protocols. Use when an agent session fails or a worktree is corrupted.
    567 repo stars
88. ▌
    Deepagents CLI · majiayu000 bundle

    Deep Agents CLI — the LangGraph-based terminal coding agent. Use this skill whenever the user mentions deepagents, deep agents, the deep agents CLI, terminal coding agent, LangGraph agent, or asks about agent memory, agent skills, AGENTS.md, coding assistants in the terminal, or building scripted/CI agent workflows. Covers: interactive and non-interactive sessions, 20+ LLM providers, model configuration, skills, persistent memory, sandboxed execution, subagents, streaming, and the Agent Client Protocol.
    567 repo stars
89. ▌
    Forge Behavior · majiayu000 bundle

    Manage dotforge v3 behavior governance — view status, toggle behaviors, adjust strictness. Use when the user asks about active behaviors, wants to disable one for the current session, or adjust escalation thresholds.
    567 repo stars
90. ▌
    Plotting Agent · majiayu000 bundle

    Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
    567 repo stars
91. ▌
    Polecat Worker · majiayu000 bundle

    ALU execution pattern for ephemeral autonomous work. Detects hooked work, enters GUPP autonomous mode, executes the assigned bead, commits and pushes results, then self-terminates. Never coordinates other agents.
    567 repo stars
92. ▌
    Runtime Logger · majiayu000 bundle

    Emit info-level logs to file during task execution, similar to logger.info() calls in code
    567 repo stars
93. ▌
    Self Customize · majiayu000 bundle

    Customize your own agent — add capabilities, install packages, add MCP servers, edit code or CLAUDE.md. Use when the user asks you to add a feature, install a tool, or modify how you work. For non-trivial code changes, delegate to a builder agent via create_agent.
    567 repo stars
94. ▌
    Strands Agents · majiayu000 bundle

    Build AI agents with the Strands Agents SDK, an open-source framework from AWS. Use when building autonomous agents, creating custom tools with @tool decorator, orchestrating multi-agent systems (swarm, graph, agents-as-tools), integrating MCP servers, or deploying agents to production. Supports Amazon Bedrock, Anthropic API, OpenAI, Ollama, and other model providers.
    567 repo stars
95. ▌
    Write Subagent · majiayu000 bundle

    CRITICAL: Before deploying any subagent, spawn a reviewer agent with REVIEW.md to audit tools. Overly permissive tool access can cause data loss or leak secrets.
    567 repo stars
96. ▌
    Agent Harness · majiayu000 bundle

    Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets. Use when agent quality is vibe-checked, before shipping a prompt or model change, or when evals drift.
    567 repo stars
97. ▌
    AI Specialist · majiayu000 bundle

    提供 AI 应用开发、MCP 服务器工程、提示词工程与智能体框架集成能力。当需要构建或优化基于大模型的功能、工作流或平台集成时使用。
    567 repo stars
98. ▌
    API AI Ollama · majiayu000 bundle

    Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint
    567 repo stars
99. ▌
    Better Prompt · majiayu000 bundle

    当用户明确要求"优化 prompt"、"改进提示词"、"润色指令"或"将简陋 prompt 转换为最佳实践版本"时使用。基于 OpenAI 和 Anthropic 官方最佳实践，对用户提供的简陋 prompt 进行结构化优化，输出符合社区标准的高质量版本。
    567 repo stars
100. ▌
     Claude Orator · majiayu000 bundle

     Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
     567 repo stars