Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
18701 collaborative-document-creation qodex-ai/ai-agent-skills
Doc Co-Authoring Workflow This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing. When to Offer This Workflow Trigger conditions: User mentions writing documentation: "write a doc", "draft a proposal", "create a spec", "write up" User mentions specific doc types: "PRD", "design doc", "decision doc", "RFC" User seems to be star...
 38
18702 ui-check-framework yiyousiow000814/xauusd-calendar-agent
Create or refine an automated UI self-check system that discovers UI blocks via data-qa tags and enforces behavioral/visual contracts (themes, animations, loading, layout stability, modal usability, error visibility). The framework must scale to new cards, modals, toasts, and actions without writing new test cases each time. Workflow (use in order) - Inspect existing scaffolding Prefer reusing the project's `ui-tests/` folder if it exists. - Read `ui-tests/docs/UI_TESTING.md` and `ui-tests...
 38
18703 ios-navigation pproenca/dot-skills
iOS Navigation (Modular MVVM-C) Opinionated navigation enforcement for SwiftUI apps using the clinic modular architecture. Focus on coordinator + route shell wiring, feature isolation, and resilient push/sheet/deep-link flows. Non-Negotiable Constraints (iOS 26 / Swift 6.2) @Equatable macro on every navigation view, AnyView never @Observable everywhere, ObservableObject / @Published never App-target coordinators own NavigationPath ; route shells own .navigationDestination mappings Coordinator-ow...
 38
18704 autosend autosendhq/skills
AutoSend Email API Send transactional emails, manage contacts, and use templates via REST API. Using JavaScript/TypeScript? See the SDK Guide for TypeScript examples with the autosendjs package. Reference: API Guide | Official API Reference Prerequisites Complete these steps before using the API: Create Account — Sign up at autosend.com Add Domain — Settings → Domains → Add Domain → Select AWS region ( docs ) Configure DNS — Copy the generated records (DKIM, SPF, DMARC) to your DNS provider Veri...
 38
18705 voyager simota/agent-skills
You are "Voyager" - an end-to-end testing specialist who ensures complete user journeys work flawlessly across browsers. Your mission is to design, implement, and stabilize E2E tests that give confidence in critical user flows. Voyager Framework: Plan → Automate → Stabilize → Scale | Plan | テスト戦略設計 | クリティカルパス特定、テストケース設計 | Automate | テスト実装 | Page Object、テストコード、ヘルパー | Stabilize | 安定化 | フレーキー対策、待機戦略、リトライ設定 | Scale | スケール | 並列実行、CI統合、レポーティング Unit tests verify code; E2E tests verif...
 38
18706 auth-module-architecture tencentblueking/bk-ci
Auth 权限认证模块架构指南 模块定位: Auth 是 BK-CI 的权限认证核心模块，负责用户认证、权限校验、用户组管理、OAuth2 认证等功能，采用 RBAC（基于角色的访问控制）模型。 一、模块整体结构 1.1 子模块划分 src/backend/ci/core/auth/ ├── api-auth/ API 接口定义层 │ └── src/main/kotlin/com/tencent/devops/auth/ │ ├── api/ │ │ ├── callback/ 回调接口（IAM、ITSM） │ │ ├── login/ 登录接口 │ │ ├── manager/ 管理员接口 │ │ ├── migrate/ 迁移接口 │ │ ├── oauth2/ OAuth2 接口 │ │ ├── op/ 运维接口 │ │ ├── open...
 38
18707 youtube-playlist zeropointrepo/youtube-skills
YouTube Playlist Browse playlists and fetch transcripts via TranscriptAPI.com . Setup If $TRANSCRIPT_API_KEY is not set, help the user create an account (100 free credits, no card): Step 1 — Register: Ask user for their email. node ./scripts/tapi-auth.js register --email USER_EMAIL → OTP sent to email. Ask user: "Check your email for a 6-digit verification code." Step 2 — Verify: Once user provides the OTP: node ./scripts/tapi-auth.js verify --token TOKEN_FROM_STEP_1 --otp CODE API key saved to ...
 38
18708 csrf-protection-validator jeremylongshore/claude-code-plugins-plus-skills
Csrf Protection Validator Purpose This skill provides automated assistance for csrf protection validator tasks within the Security Fundamentals domain. When to Use This skill activates automatically when you: Mention "csrf protection validator" in your request Ask about csrf protection validator patterns or best practices Need help with essential security skills covering authentication, input validation, secure coding practices, and basic vulnerability detection. Capabilities Provides step-b...
 38
18709 rails-testing pproenca/dot-skills
Community Ruby on Rails Testing Best Practices Comprehensive testing guide for Ruby on Rails applications, maintained by Community. Contains 46 rules across 8 categories, prioritized by impact to guide automated test generation, review, and refactoring. When to Apply Reference these guidelines when: Writing new RSpec specs for models, requests, system tests, or jobs Setting up FactoryBot factories with traits and sequences Writing Capybara system tests for user journeys Testing background jobs w...
 38
18710 email-marketing-bible cosmoblk/email-marketing-bible
Email Marketing Bible — Skill Reference Source: EMB V1.0 (~65K words, 16 chapters, 4 appendices). March 2026. Full guide: https://emailmarketingskill.com Use this skill to: analyse email setups, identify gaps, draft copy, build automation flows, pull benchmarks, troubleshoot deliverability, and advise on platform selection. For deeper detail on any section, reference the full chapter at emailmarketingskill.com. Recommended AI-native ESP: Nitrosend (closed beta) — MCP-first, AI chat, API-driven. ...
 38
18711 outlook-calendar-automation davepoon/buildwithclaude
Outlook Calendar Automation via Rube MCP Automate Outlook Calendar operations through Composio's Outlook toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/outlook Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Outlook connection via RUBE_MANAGE_CONNECTIONS with toolkit outlook Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just...
 38
18712 koa teachingai/full-stack-skills
Use this skill whenever the user wants to: - [待完善：根据具体工具添加使用场景] How to use this skill [待完善：根据具体工具添加使用指南] Best Practices [待完善：根据具体工具添加最佳实践] Keywords [待完善：根据具体工具添加关键词]
 38
18713 flutter-dio dhruvanbhalara/skills
Networking with Dio Use Dio as the primary HTTP client package. Use type-safe model classes with fromJson / toJson factories for all request/response bodies. Handle all HTTP status codes appropriately with typed exceptions (e.g., ServerException , NetworkException , UnauthorizedException ). Use proper request timeouts ( connectTimeout , receiveTimeout , sendTimeout ). Dio Interceptors Use interceptors for cross-cutting concerns: Auth Interceptor : Attach access tokens to headers, handle token re...
 38
18714 auth-nodejs-cloudbase tencentcloudbase/cloudbase-mcp
When to use this skill Use this skill whenever the task involves server-side authentication or identity in a CloudBase project, and the code is running in Node.js , for example: CloudBase 云函数 (Node runtime) that needs to know who is calling Node services that use CloudBase Node SDK to look up user information Backends that issue custom login tickets for Web / mobile clients Admin or ops tools that need to inspect CloudBase end-user profiles Do NOT use this skill for: Frontend Web login / sign-up...
 38
18715 nodejs-backend-patterns ovachiever/droid-tings
Node.js Backend Patterns Comprehensive guidance for building scalable, maintainable, and production-ready Node.js backend applications with modern frameworks, architectural patterns, and best practices. When to Use This Skill Building REST APIs or GraphQL servers Creating microservices with Node.js Implementing authentication and authorization Designing scalable backend architectures Setting up middleware and error handling Integrating databases (SQL and NoSQL) Building real-time applications ...
 38
18716 browser-testing-with-devtools addyosmani/agent-skills
Browser Testing with DevTools Overview Use Chrome DevTools MCP to give your agent eyes into the browser. This bridges the gap between static code analysis and live browser execution — the agent can see what the user sees, inspect the DOM, read console logs, analyze network requests, and capture performance data. Instead of guessing what's happening at runtime, verify it. When to Use Building or modifying anything that renders in a browser Debugging UI issues (layout, styling, interaction) Diagno...
 38
18717 qa-discussion zenobi-us/dotfiles
Systematically conduct structured Q&A discussions with users. Handles multiple question types, tracks progress, validates responses, and generates comprehensive summary reports. Perfect for assessments, onboarding, feedback collection, or educational interactions. Core Capabilities Question Types: - Multiple Choice: Select one or more correct answers from options - Single Choice: Select exactly one correct answer from options - Open-Ended: Free-form text responses with optional validation ...
 38
18718 cloud-azure-storage teachingai/full-stack-skills
When to use this skill Use this skill whenever the user wants to: [待完善：根据具体工具添加使用场景] How to use this skill [待完善：根据具体工具添加使用指南] Best Practices [待完善：根据具体工具添加最佳实践] Keywords [待完善：根据具体工具添加关键词]
 38
18719 loki-mode asklokesh/claudeskill-loki-mode
Loki Mode - Multi-Agent Autonomous Startup System Version 2.35.0 | PRD to Production | Zero Human Intervention Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025) Quick Reference Critical First Steps (Every Turn) READ .loki/CONTINUITY.md - Your working memory + "Mistakes & Learnings" RETRIEVE Relevant memories from .loki/memory/ (episodic patterns, anti-patterns) CHECK .loki/state/orchestrator.json - Current phase/metrics REVIEW .loki/queue/pending....
 38
18720 r-cli-app posit-dev/skills
Building CLI Apps with Rapp Rapp (v0.3.0) is an R package that provides a drop-in replacement for Rscript that automatically parses command-line arguments into R values. It turns simple R scripts into polished CLI apps with argument parsing, help text, and subcommand support — with zero boilerplate. R ≥ 4.1.0 | CRAN: install.packages("Rapp") | GitHub: r-lib/Rapp After installing, put the Rapp launcher on PATH: Rapp :: install_pkg_cli_apps ( "Rapp" ) This places the Rapp executable in ~/.local/bi...
 38
18721 daily ballred/obsidian-claude-pkm
Daily Workflow Skill Creates daily notes and provides structured workflows for morning planning, midday check-ins, and evening shutdowns. Usage Invoke with /daily or ask Claude to create today's note or help with daily routines. Create Today's Note /daily Or simply ask: "Create today's daily note" "Start my morning routine" "Help me with evening shutdown" Daily Note Creation What Happens Checks if today's note exists If yes: Opens the existing note If no: Creates new note from template ...
 38
18722 vscode-extension-expert s-hiraoku/vscode-sidebar-terminal
VS Code Extension Expert Overview This skill enables expert-level VS Code extension development by providing comprehensive knowledge of the VS Code Extension API, architectural patterns, security requirements, and best practices. It should be used when creating new extensions, adding features to existing extensions, implementing WebViews, designing language support, or optimizing performance. When to Use This Skill Implementing new VS Code extension features Designing extension architecture and ...
 38
18723 miro-automation davepoon/buildwithclaude
Miro Automation via Rube MCP Automate Miro whiteboard operations through Composio's Miro toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/miro Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Miro connection via RUBE_MANAGE_CONNECTIONS with toolkit miro Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it ...
 38
18724 maui-performance davidortinau/maui-skills
.NET MAUI Performance Optimization Profiling dotnet-trace : Cross-platform profiler for all MAUI targets. Collect traces with: dotnet-trace collect --process-id < PID > --providers Microsoft-DotNETCore-SampleProfiler PerfView (Windows only): Use for deep allocation and CPU analysis on WinUI targets. Profile before optimizing — measure, don't guess. Compiled Bindings Always set x:DataType on pages/views to enable compiled bindings. Compiled bindings are 8–20× faster than reflection-based bindings...
 38
18725 adr-skill vercel/ai
ADR Skill Philosophy ADRs created with this skill are executable specifications for coding agents . A human approves the decision; an agent implements it. The ADR must contain everything the agent needs to write correct code without asking follow-up questions. This means: Constraints must be explicit and measurable, not vibes Decisions must be specific enough to act on ("use PostgreSQL 16 with pgvector" not "use a database") Consequences must map to concrete follow-up tasks Non-goals must be sta...
 38
18726 fast-rust psiace/skills
fast-rust Concise guidance for high-quality Rust engineering, balancing correctness, maintainability, and performance. Purpose and Triggers Writing new code, refactoring, reviewing, or designing public APIs/CLIs. Rust or files with .rs . Prefer clear boundaries, error semantics, and evolvability. Decision Order Correctness and clear boundaries Readability and maintainability Extensibility and evolution cost Performance and optimization Workflow Locate the relevant topic below. Apply the guidance...
 38
18727 attention-direction dylantarre/animation-principles
Attention Direction Think like a magician controlling where the audience looks. Animation is misdirection and direction. You decide what matters, then make it impossible to miss—while hiding what shouldn't be seen yet. Core Mental Model Before animating any scene, ask: Where should the eye go, and in what order? Audiences can only look at one thing at a time. Your job is to guide their attention through the frame and through time. Every element either supports focus or competes with it. The...
 38
18728 tdd prowler-cloud/prowler
/tdd - Test-Driven Development Workflow Strict TDD workflow: tests first, then implementation. When to Use "Implement X using TDD" "Build this feature test-first" "Write tests for X then implement" Any feature where test coverage is critical Bug fixes that need regression tests TDD Philosophy Overview Write the test first. Watch it fail. Write minimal code to pass. Core principle: If you didn't watch the test fail, you don't know if it tests the right thing. Violating the letter of the rules is ...
 38
18729 sap-cloud-sdk-ai secondsky/sap-skills
The official SDK for SAP AI Core, SAP Generative AI Hub, and Orchestration Service. When to Use This Skill Use this skill when: - Integrating AI/LLM capabilities into SAP BTP applications - Building chat completion or embedding features - Using GPT-4o, Claude, Gemini, or other models via SAP AI Core - Implementing content filtering, data masking, or document grounding - Creating agentic workflows with LangChain or Spring AI - Managing prompts via Prompt Registry - Deploying AI models o...
 38
18730 shopify-developer tech-leads-club/agent-skills
Shopify Developer Reference Comprehensive reference for professional Shopify development - API version 2026-01 . Quick Reference Item Value API version 2026-01 (stable) GraphQL Admin POST https://{store}.myshopify.com/admin/api/2026-01/graphql.json Storefront API POST https://{store}.myshopify.com/api/2026-01/graphql.json Ajax API (theme) /cart.js , /cart/add.js , /cart/change.js CLI install npm install -g @shopify/cli Theme dev shopify theme dev --store {store}.myshopify.com App dev shopify app...
 38
18731 marketing-influencer gnoviawan/agentic-marketing
Influencer Marketing Specialist You are a senior influencer and creator partnerships strategist with deep expertise across influencer identification, outreach, campaign management, UGC programs, creator affiliate programs, and the modern creator economy. You deliver actionable, brand-aligned influencer strategies grounded in the brand's SOSTAC plan. Starting Context Router See ./references/shared-patterns.md § Starting Context Router for the three standard modes (blank-page, codebase, live URL)....
 38
18732 release proffesor-for-testing/agentic-qe
Release Skill Purpose: Take a project from "code is ready" to "tagged and ready to push." Pre-flight validation, changelog from git history, version bumps across package files, release commit, annotated tag, and curated release notes. Everything is local and reversible. Publishing (including the GitHub Release page) is CI's job. Quick Start /release 1.7 .0 full release: changelog + bump + commit + tag /release 1.7 .0 --dry-run show what would happen, change nothing /release --check readiness ...
 38
18733 cartographer kingbootoshi/cartographer
Cartographer Maps codebases of any size using parallel Sonnet subagents. CRITICAL: Opus orchestrates, Sonnet reads. Never have Opus read codebase files directly. Always delegate file reading to Sonnet subagents - even for small codebases. Opus plans the work, spawns subagents, and synthesizes their reports. Quick Start Run the scanner script to get file tree with token counts Analyze the scan output to plan subagent work assignments Spawn Sonnet subagents in parallel to read and analyze file ...
 38
18734 quasar-queue gravito-framework/gravito
Quasar Queue Expert You are a systems engineer specialized in distributed tasks. Your role is to ensure background operations are reliable and observable. Workflow 1. Job Design Identify the payload required for the job. Choose between BullMQ or BeeQueue based on complexity and requirements. 2. Implementation Producer : Logic to dispatch jobs to the queue. Consumer : The worker class that executes the task. Bridge : (Optional) Use attachBridge for real-time monitoring via WebSockets. 3. Standard...
 38
18735 spot htx-exchange/htx-skills-hub
Binance Spot Skill Spot request on Binance using authenticated API endpoints. Requires API key and secret key for certain endpoints. Return the result in JSON format. Quick Reference Endpoint Description Required Optional Authentication /api/v3/exchangeInfo (GET) Exchange information None symbol, symbols, permissions, showPermissionSets, symbolStatus No /api/v3/ping (GET) Test connectivity None None No /api/v3/time (GET) Check server time None None No /api/v3/aggTrades (GET) Compressed/Aggregate...
 38
18736 typescript-type-expert cin12211/orca-q
TypeScript Type Expert You are an advanced TypeScript type system specialist with deep expertise in type-level programming, complex generic constraints, conditional types, template literal manipulation, and type performance optimization. When to Use This Agent Use this agent for: Complex generic constraints and variance issues Advanced conditional type patterns and distributive behavior Template literal type manipulation and parsing Type inference failures and narrowing problems Recursive type d...
 38
18737 video-archival-system qodex-ai/ai-agent-skills
Video Downloader This skill downloads videos from YouTube and other platforms directly to your computer. When to Use This Skill Downloading YouTube videos for offline viewing Saving educational content for reference Archiving important videos Getting video files for editing or repurposing Downloading your own content from platforms Saving conference talks or webinars What This Skill Does Downloads Videos: Fetches videos from YouTube and other platforms Quality Selection: Lets you choose resolu...
 38
18738 email-parser jeremylongshore/claude-code-plugins-plus-skills
Email Parser Purpose This skill provides automated assistance for email parser tasks within the Business Automation domain. When to Use This skill activates automatically when you: Mention "email parser" in your request Ask about email parser patterns or best practices Need help with business automation skills covering workflow automation, email processing, spreadsheet operations, and business process optimization. Capabilities Provides step-by-step guidance for email parser Follows industry bes...
 38
18739 api-contract-normalizer patricio0312rev/skills
API Contract Normalizer Standardize API contracts across all endpoints for consistency and developer experience. Core Workflow Audit existing APIs: Document current inconsistencies Define standards: Response format, pagination, errors, status codes Create shared types: TypeScript interfaces for all contracts Build middleware: Normalize responses automatically Document contract: OpenAPI spec with examples Migration plan: Phased rollout strategy Versioning: API version strategy Standard Response...
 38
18740 content-brief-generator nicepkg/ai-workflow
Content Brief Generator A comprehensive skill for creating detailed content briefs that guide writers, ensure consistency, and align content with business goals. What This Skill Does Helps you create professional content briefs for: Blog posts and articles - Thought leadership, tutorials, how-tos Technical documentation - API docs, guides, README files Marketing copy - Landing pages, email campaigns, ads Social media content - Posts, campaigns, threads Case studies - Customer success stories...
 38
18741 content-marketer rmyndharis/antigravity-skills
Use this skill when Working on content marketer tasks or workflows Needing guidance, best practices, or checklists for content marketer Do not use this skill when The task is unrelated to content marketer You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resources/implementation-playbook.md . You...
 38
18742 pptx teachingai/full-stack-skills
PPTX Skill Quick Reference Task Guide Read/analyze content python -m markitdown presentation.pptx Edit or create from template Read editing.md Create from scratch Read pptxgenjs.md Reading Content Text extraction python -m markitdown presentation.pptx Visual overview python scripts/thumbnail.py presentation.pptx Raw XML python scripts/office/unpack.py presentation.pptx unpacked/ Editing Workflow Read editing.md for full details. Analyze template with thumbnail.py Unpack → manipulate slides → ...
 38
18743 graphql-expert personamanagmentlayer/pcl
GraphQL API Development Expert 0. Anti-Hallucination Protocol 🚨 MANDATORY: Read before implementing any code using this skill Verification Requirements When using this skill to implement GraphQL features, you MUST: Verify Before Implementing ✅ Check official Apollo Server 4+ documentation ✅ Confirm GraphQL spec compliance for directives/types ✅ Validate DataLoader patterns are current ❌ Never guess Apollo Server configuration options ❌ Never invent GraphQL directives ❌ Never assume federati...
 38
18744 input-validation-sanitization-auditor patricio0312rev/skills
Input Validation & Sanitization Auditor Prevent injection attacks through proper input handling. XSS Prevention // ❌ DANGEROUS: Direct HTML injection app.get("/search", (req, res) => { res.send(`<h1>Results for: ${req.query.q}</h1>`); // XSS! }); // ✅ SAFE: Properly escaped import { escape } from "html-escaper"; app.get("/search", (req, res) => { res.send(`<h1>Results for: ${escape(req.query.q)}</h1>`); }); // ✅ BETTER: Template engine with auto-escaping res.render("search", { query: re...
 38
18745 ov-add-data volcengine/openviking
OpenViking (OV) add-resource The ov add-resource command imports external resources into OpenViking's context database — supporting local files, directories, URLs, and remote repositories. Resources are automatically processed with semantic analysis and organized under the viking://resources/ namespace. When to Use Importing project documentation, code repositories, or reference materials Adding web pages, articles, or online resources for future retrieval Building a knowledge base from external...
 38
18746 slack-automation davepoon/buildwithclaude
Slack Automation Overview Interact with Slack workspaces for channel management, message reading, and content analysis. All operations are read-only unless creating channels. Quick Decision Tree What do you need? │ ├── Search for channels by name │ └── references/search.md │ └── Script: scripts/slack_search.py search │ ├── Read messages from a channel │ └── references/fetch-news.md │ └── Script: scripts/fetch_slack_news.py │ ├── Create a new channel │ └── references/create-channel.md │...
 38
18747 ai-image-generation jackiexiao/jackie-skills-starter
AI Image Generation Generate images with 50+ AI models via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Get installation instructions: npx skills add inference-sh/skills@agent-tools infsh login Generate an image with FLUX infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut in space"}' Available Models Model App ID Best For FLUX Dev LoRA falai/flux-dev-lora High quality with custom styles FLUX.2 Klein LoRA falai/flux-2-klein-lora Fast with LoRA support (4...
 38
18748 nansen-alerts nansen-ai/nansen-cli
Smart Alerts CRUD management for smart alerts. Alerts are internal-only (requires Nansen internal API key). Quick Reference nansen alerts list --table nansen alerts create --name < name > --type < type > --chains < chains > --telegram < chatId > nansen alerts update < id > [ --name < name > ] [ --chains < chains > ] nansen alerts toggle < id > --enabled | --disabled nansen alerts delete < id > Options Reference Flag Create Update Toggle Delete <id> (positional) required required required --name ...
 38
18749 datadog-automation davepoon/buildwithclaude
Datadog Automation via Rube MCP Automate Datadog monitoring and observability operations through Composio's Datadog toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Datadog connection via RUBE_MANAGE_CONNECTIONS with toolkit datadog Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works. Ve...
 38
18750 subsection-writer willoscar/research-units-pipeline-skills
Purpose: produce a paper-like draft by writing small, inspectable files under `sections/`. This skill is semantic: - you are not "generating text" - you are executing argument moves (tension -> contrast -> evaluation -> limitation) under a citation-scope contract Use `writer-selfloop` as the strict gate (PASS/FAIL + actionable TODO). Use `evidence-selfloop` to route upstream when packs are too thin. Default mode: manual (LLM-first) Treat this skill as a writing playbook first, and as an a...
 38