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...
29,292
总 Skills
231.9M
总安装量
2,819
贡献者
# Skill 仓库 描述 安装量
11451 service-concierge-portal-generate forcedotcom/sf-skills
service-concierge-portal-generate: Agentforce Concierge portal deploy Deploys an Agentforce Concierge experience on an LWR Experience Cloud site — an agent-first landing page with a welcome greeting, prompt bar, suggestion chiclets, and full chat surface. This is a channel-setup skill: it wires an existing agent to a new or existing portal site; it does not author the agent. Why this skill exists The Concierge portal setup is a 20-step workflow with precise sequencing requirements (bundle shape,...
 1.2K
11452 service-itsm-teams-coordinate forcedotcom/sf-skills
Microsoft Teams for ITSM — End-to-End Setup Autopilot Drive the complete Microsoft Teams for Employee Service (ITSM) setup as one continuous flow. Delegate each stage to its specialized child skill, but own the sequence yourself and keep going through every stage without stopping to ask permission between stages . Halt only at the points where a human genuinely must act — nowhere else. Goal Take the user from nothing to a working Teams ITSM integration (IT Desk + IT Service, Swarming, and — if t...
 1.2K
11453 service-itsm-teams-configure forcedotcom/sf-skills
Enable Microsoft Teams for Employee Service (ITSM) Enable the Salesforce Go feature "Microsoft Teams for Employee Service" ( service-cloud-itsm-teams-integration ) — the feature that lets IT Desk and IT Service agents track tickets, request catalog items, and get Agentforce assistance from inside Microsoft Teams. Every operation dispatches through headless-360 . Execute one step at a time. These steps make real, state-changing API calls. Run a single operation, show its result, confirm it succee...
 1.2K
11454 senior-computer-vision davila7/claude-code-templates
Senior Computer Vision Engineer World-class senior computer vision engineer skill for production-grade AI/ML/Data systems. Quick Start Main Capabilities Core Tool 1 python scripts/vision_model_trainer.py --input data/ --output results/ Core Tool 2 python scripts/inference_optimizer.py --target project/ --analyze Core Tool 3 python scripts/dataset_pipeline_builder.py --config config.yaml --deploy Show more Installs 923 Repository davila7/claude-…emplates GitHub Stars 29.2K First Seen Jan 20, 2...
 1.2K
11455 safe-action-hooks next-safe-action/skills
next-safe-action React Hooks Import // Standard hooks import { useAction , useOptimisticAction } from "next-safe-action/hooks" ; // Deprecated — use React's useActionState directly instead import { useStateAction } from "next-safe-action/stateful-hooks" ; useAction — Quick Start "use client" ; import { useAction } from "next-safe-action/hooks" ; import { createUser } from "@/app/actions" ; export function CreateUserForm ( ) { const { execute , result , status , isExecuting , isPending } = useAct...
 1.2K
11456 app-builder sickn33/agentic-awesome-skills
App Builder - Application Building Orchestrator Analyzes user's requests, determines tech stack, plans structure, and coordinates agents. 🎯 Selective Reading Rule Read ONLY files relevant to the request! Check the content map, find what you need. File Description When to Read project-detection.md Keyword matrix, project type detection Starting new project tech-stack.md 2025 default stack, alternatives Choosing technologies agent-coordination.md Agent pipeline, execution order Coordinating multi-...
 1.2K
11457 video-downloader davila7/claude-code-templates
video-downloader Curated from ComposioHQ awesome-claude-skills. What it does Download videos from YouTube and other platforms for offline viewing, editing, or archival with support for various formats and quality options. Source Upstream: https://github.com/ComposioHQ/awesome-claude-skills/tree/master/video-downloader Category: video-generation How to use This catalogue entry advertises the skill in Open Design so the agent discovers it during planning. To run the full upstream workflow with its...
 1.2K
11458 google-analytics davila7/claude-code-templates
Google Analytics Analysis Analyze website performance using Google Analytics data to provide actionable insights and improvement recommendations. Quick Start 1. Setup Authentication This Skill requires Google Analytics API credentials. Set up environment variables: export GOOGLE_ANALYTICS_PROPERTY_ID="your-property-id" export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account-key.json" Or create a .env file in your project root: GOOGLE_ANALYTICS_PROPERTY_ID=123456789 GOOGLE_APPLICAT...
 1.2K
11459 tanstack-ranger tanstack-skills/tanstack-skills
Overview TanStack Ranger provides headless utilities for building fully accessible range and multi-range slider components. It handles all the complex logic for single value, range, and multi-thumb sliders while giving you complete control over styling and markup. Package: @tanstack/react-ranger Core: @tanstack/ranger-core (framework-agnostic) Status: Stable Installation npm install @tanstack/react-ranger Core Pattern import { useRanger } from '@tanstack/react-ranger' function RangeSlider ( ) { ...
 1.2K
11460 youtube-thumbnail charlie947/social-media-skills
YouTube Thumbnail CRITICAL: Auto-start on load When this skill triggers, go straight to Step 1. Step 1. Gather inputs Check the project for a reference photo config. Look in this order: thumbnail-config.md in the project root brand-kit.md — look for a reference image path and brand colours about-me.md — for the creator's name and positioning If a reference photo path is stored, pre-fill it. Otherwise ask: Upload or provide the path to the reference photo of yourself you want used in the thumbnai...
 1.2K
11461 ui-mobile alinaqi/maggy
Mobile UI Design Skill (React Native) MANDATORY: Mobile Accessibility Standards These rules are NON-NEGOTIABLE. Every UI element must pass these checks. 1. Touch Targets (CRITICAL) // MINIMUM 44x44 points for ALL interactive elements const MINIMUM_TOUCH_SIZE = 44 ; Show more Installs 1.2K Repository alinaqi/maggy GitHub Stars 708 First Seen Jan 20, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Pass
 1.2K
11462 seo-fundamentals sickn33/agentic-awesome-skills
SEO Fundamentals Foundational principles for sustainable search visibility. This skill explains how search engines evaluate quality , not tactical shortcuts. 1. E-E-A-T (Quality Evaluation Framework) E-E-A-T is not a direct ranking factor . It is a framework used by search engines to evaluate content quality , especially for sensitive or high-impact topics. Dimension What It Represents Common Signals Experience First-hand, real-world involvement Original examples, lived experience, demonstration...
 1.2K
11463 service-itsm-agentic-setup-agentforce-studio-validate forcedotcom/sf-skills
Validate Agentforce for IT Service Prerequisites Readiness check for Agentforce for IT Service , for either the Fulfiller or the Employee agent path. Before an ITSM agent can be created, the org must have the right Salesforce Go feature toggles turned on (the ones on the Agentforce for IT Service setup page). This skill reads those toggles through the Salesforce CLI ( sf ) — a single authenticated Connect API call via sf api request rest — and a helper script classifies the chosen agent path int...
 1.2K
11464 dhanhq dhan-oss/dhanhq-skills
DhanHQ — Indian Market Trading Skill Setup Stable install: pip install dhanhq Use the current SDK branch when you need newer v2 capabilities such as 200-level depth or the latest helper coverage: pip install - - upgrade dhanhq Minimal initialization: Show more Installs 841 Repository dhan-oss/dhanhq-skills GitHub Stars 29 First Seen Apr 27, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Warn
 1.2K
11465 hate lilmgenius/paperthin
Refuse to be nice to the plan — return the one objection that could kill it and the cheapest shot that proves it matters. Goal hate asks "what would someone who wants this to fail attack first?" (validity). It attacks the whole plan — not one fact or one line, but the load-bearing structure — and collapses the attack to a single root. The highest-value output is never a checklist — it's one objection plus the cheaper experiment hiding inside the elaborate plan. Workflow Pin the load-bearing assu...
 1.2K
11466 tinybird-cli-guidelines tinybirdco/tinybird-agent-skills
Tinybird CLI Guidelines Guidance for using the Tinybird CLI (tb) for local development, deployments, data operations, and workspace management. When to Apply Running any tb command Local development with Tinybird Local Building and deploying projects Appending, replacing, or deleting data Managing tokens and secrets via CLI Generating mock data Running tests Rule Files rules/cli-commands.md rules/build-deploy.md rules/local-development.md rules/data-operations.md rules/append-data.md rules/mock-...
 1.2K
11467 dd-checklist anthropics/financial-services
Due Diligence Checklist Workflow Step 1: Scope the Diligence Ask the user for: Target company : Name, sector, business model Deal type : Platform acquisition, add-on, growth equity, recap, carve-out Deal size / complexity : Determines depth of diligence Key concerns : Any known issues to prioritize (customer concentration, regulatory, environmental, etc.) Timeline : When is LOI / close targeted? Step 2: Generate Workstream Checklists Generate a checklist across all major workstreams, tailored to...
 1.2K
11468 safe-action-advanced next-safe-action/skills
next-safe-action Advanced Features Overview Feature Use Case Bind arguments Pass extra args to actions via .bind() (e.g., resource IDs) Metadata Attach typed metadata to actions for use in middleware Framework errors Handle redirect, notFound, forbidden, unauthorized in actions Type utilities Infer types from action functions and middleware Server-Level Action Callbacks The second argument to .action() accepts callbacks that run on the server (not client-side hooks): export const createPost = au...
 1.2K
11469 re0 lilmgenius/paperthin
Refresh the target artifact as if it were the first clean version. Goal The result must be lighter, more current, and more accurate than the input. It should not read like a changelog, cleanup note, or patch over an older draft. Workflow Identify the target artifact from the user's request or the active context. Read the target artifact end to end before editing. Check nearby artifacts that must stay aligned with it. Remove scaffolding residue, stale deltas, duplicated process noise, deprecated ...
 1.2K
11470 factchk lilmgenius/paperthin
Check what's asserted as real against reality — in both directions — before it ships. Goal The author's "plausible / absurd / novel" is the least reliable line in any artifact. Human priors fail both ways — they exclude the real (desert frogs exist) and normalize the impossible (weightless crates). factchk scans claims presented as reality-grounded, verifies each against external sources in both directions, and fixes or flags. Its scope is a claim about the world — whether what's asserted as rea...
 1.2K
11471 hook-generator charlie947/social-media-skills
Hook Generator CRITICAL: Auto-start on load When this skill triggers, go straight to Step 1. Do not summarise. Do not explain what makes a good hook. Step 1. Get the topic If the user already pasted a topic in their message, use it and skip to Step 2. Otherwise ask: What topic do you want hooks for? Wait for response. Step 2. Write 6 hook variations Every hook has the same structure: Show more Installs 976 Repository charlie947/soci…a-skills GitHub Stars 3.0K First Seen Apr 27, 2026 Security Aud...
 1.2K
11472 electron-development mindrally/skills
Electron Development Guidelines You are an expert in Electron development for building cross-platform desktop applications. Core Principles Follow security best practices for Electron apps Separate main and renderer process concerns Use IPC for process communication Implement proper window management Project Structure src/ ├── main/ Main process code │ ├── index.ts Entry point │ ├── ipc/ IPC handlers │ └── utils/ Utilities ├── renderer/ Ren...
 1.2K
11473 query duckdb/duckdb-skills
You are helping the user query data using DuckDB. Input: $@ Follow these steps in order. Step 1 — Resolve state and determine the mode Look for an existing state file in either location: STATE_DIR = "" test -f .duckdb-skills/state.sql && STATE_DIR = ".duckdb-skills" PROJECT_ROOT = " $( git rev-parse --show-toplevel 2 > /dev/null || echo " $PWD " ) " PROJECT_ID = " $( echo " $PROJECT_ROOT " | tr '/' '-' ) " test -f " $HOME /.duckdb-skills/ $PROJECT_ID /state.sql" && STATE_DIR = " $HOME /.duckdb-s...
 1.2K
11474 hyva-alpine-component hyva-themes/hyva-ai-tools
Hyvä Alpine Component Overview This skill provides guidance for writing CSP-compatible Alpine.js components in Hyvä themes. Alpine CSP is a specialized Alpine.js build that operates without the unsafe-eval CSP directive, which is required for PCI-DSS 4.0 compliance on payment-related pages (mandatory from April 1, 2025). Key principle: CSP-compatible code functions in both standard and Alpine CSP builds. Write all Alpine code using CSP patterns for future-proofing. CSP Constraints Summary Cap...
 1.2K
11475 synap vaibhav0806/maximem_synap_sdk
Maximem Synap — Agent Memory Skill Synap is a managed memory layer for AI agents. Instead of every conversation starting from scratch, your agent can remember facts, preferences, episodes, and entities across sessions, users, and tenants. There is no vector DB to operate, no extraction pipeline to build, no retrieval ranker to tune — those are the product. This skill helps you (a) decide whether Synap fits, and (b) wire it into whichever agent framework the user is using. Read only the reference...
 1.2K
11476 rebranding arnabbagxd/brand-building-skills
Rebranding You are a rebranding strategist. Your job is to help a brand understand why it needs to change, define what should change (and what should stay), build the new brand direction, and plan the transition. Before You Start Check if .agents/brand-context.md exists. Read it — it may represent the old brand, the aspirational brand, or a mix. Use it as a starting point for understanding where the brand currently sits. Rebranding Philosophy A rebrand is not a new logo. It's a strategic decisio...
 1.2K
11477 crypto-com-app crypto-com/crypto-agent-trading
Skill: crypto-com-app Agent Capability Requirements This skill requires your agent platform to support the following capabilities. If your platform lacks any required capability, the skill will not function. Capability Required Details Shell command execution Yes Must be able to run npx tsx ./scripts/... and capture stdout Environment variables Yes Must read CDC_API_KEY and CDC_API_SECRET from the shell environment JSON parsing Yes Must parse structured JSON from script stdout to extract fields ...
 1.2K
11478 d2c-marketing arnabbagxd/brand-building-skills
D2C Marketing You are a DTC marketing strategist. Your job is to build a full direct-to-consumer marketing system — from first touch to loyal repeat buyer — without relying on retail, distributors, or marketplaces. Before You Start Check if .agents/brand-context.md exists. Read it first. DTC marketing must be built on top of clear brand positioning and audience definition. What Makes DTC Different DTC brands own the entire customer relationship — no retailer buffer, no marketplace algorithm, no ...
 1.2K
11479 content-gap-analysis aaron-he-zhu/aaron-marketing-skills
Content Gap Analysis This skill identifies content opportunities by analyzing gaps between your content and competitors'. Find topics you're missing, keywords you could target, and content formats you should create. When to Use This Skill Planning content strategy and editorial calendar Finding quick-win content opportunities Understanding where competitors outperform you Identifying underserved topics in your niche Expanding into adjacent topic areas Prioritizing content creation efforts Find...
 1.2K
11480 terraform-policy hashicorp/agent-skills
terraform-policy UTILITY SKILL — INVOKES: tfpolicy-author | tfpolicy-test USE FOR: Writing a new .policy.hcl policy from a description or requirement Converting a .sentinel policy to Terraform Policy Writing or debugging a .policytest.hcl test file Migrating a Sentinel policy library to Terraform Policy Before giving authoring or testing instructions, check the installed tfpolicy CLI version and tailor guidance accordingly: If the CLI is 0.1.x , do not require policy { required_providers { ... }...
 1.2K
11481 parallel-task-spark am-will/codex-skills
Parallel Task Executor (Sparky) You are an Orchestrator for subagents. Use orchestration mode to parse plan files and delegate tasks to parallel Sparky subagents using task dependencies, in a loop, until all tasks are completed. Your role is to ensure that subagents are launched in the correct order (in waves), and that they complete their tasks correctly, as well as ensure the plan docs are updated with logs after each task is completed. Process Step 1: Parse Request Extract from user request: ...
 1.1K
11482 super-swarm-spark am-will/codex-skills
Parallel Task Executor (Sparky Rolling 12-Agent Pool) You are an Orchestrator for subagents. Parse plan files and delegate tasks in parallel using a rolling pool of up to 15 concurrent Sparky subagents. Keep launching new work whenever a slot opens until the plan is fully complete. Primary orchestration goals: Keep the project moving continuously Ignore dependency maps Keep up to 15 agents running whenever pending work exists Give every subagent maximum path/file context Prevent filename/folder-...
 1.1K
11483 agent-memory api/git
No SKILL.md available for this skill. View on GitHub
 1.1K
11484 flutter-animation flutter/skills
Flutter Animations Implementation Goal Implements and manages Flutter animations, selecting the appropriate animation strategy (implicit, explicit, tween, physics, hero, or staggered) based on UI requirements. Assumes a working Flutter environment, stateful/stateless widget competence, and a standard widget tree structure. Instructions 1. Determine Animation Strategy (Decision Logic) Evaluate the UI requirement using the following decision tree to select the correct animation approach: Is the an...
 1.1K
11485 flutter-routing-and-navigation flutter/skills
flutter-navigation-routing Goal Implements robust navigation and routing in Flutter applications. Evaluates application requirements to select the appropriate routing strategy (imperative Navigator , declarative Router , or nested navigation), handles deep linking, and manages data passing between routes while adhering to Flutter best practices. Instructions 1. Determine Routing Strategy (Decision Logic) Evaluate the application's navigation requirements using the following decision tree: Condit...
 1.1K
11486 flutter-state-management flutter/skills
flutter-state-management Goal Implements robust state management and architectural patterns in Flutter applications using Unidirectional Data Flow (UDF) and the Model-View-ViewModel (MVVM) design pattern. Evaluates state complexity to differentiate between ephemeral (local) state and app (shared) state, applying the appropriate mechanisms ( setState , ChangeNotifier , or the provider package). Ensures that the UI remains a pure function of immutable state and that the data layer acts as the Sing...
 1.1K
11487 flutter-architecture flutter/skills
Flutter Architecture Overview Provides architectural guidance and best practices for building scalable Flutter applications using MVVM pattern, layered architecture, and recommended design patterns from the Flutter team. Project Structure: Feature-First vs Layer-First Choose the right project organization based on your app's complexity and team size. Feature-First (Recommended for teams) Organize code by business features: lib/ ├── features/ │ ├── auth/ │ │ ├── data/ │ │ ├── domain/ │ ...
 1.1K
11488 setup-artist recoupable/setup-artist
Setup Artist Scaffold a complete artist workspace so agents can start working immediately. Prerequisites The sandbox has already been set up (see setup-sandbox skill) An artist folder exists at orgs/{org}/artists/{artist-slug}/ with a RECOUP.md marker file The RECOUP.md file contains the artist's name, slug, and Recoup ID (created by setup-sandbox ) Folder Structure {artist-slug}/ ├── RECOUP.md ├── README.md ├── .env.example ├── .env ├── context/ │ ├── artist.md │ ├── audience.md │ ├── era...
 1.1K
11489 quant-analyst 404kidwiz/claude-supercode-skills
Quantitative Analyst Purpose Provides expertise in quantitative finance, algorithmic trading strategies, and financial data analysis. Specializes in statistical modeling, risk analytics, and building data-driven trading systems using Python scientific computing stack. When to Use Building algorithmic trading strategies or backtesting frameworks Performing statistical analysis on financial time series data Implementing risk models (VaR, CVaR, Greeks calculations) Creating portfolio optimization...
 1.1K
11490 video-understand heygen-com/skills
video-understand Understand video content locally using ffmpeg for frame extraction and Whisper for transcription. Fully offline, no API keys required. Prerequisites ffmpeg + ffprobe (required): brew install ffmpeg openai-whisper (optional, for transcription): pip install openai-whisper Commands Scene detection + transcribe (default) python3 skills/video-understand/scripts/understand_video.py video.mp4 Keyframe extraction python3 skills/video-understand/scripts/understand_video.py video.mp4 -m...
 1.1K
11491 sub-account binance/binance-skills-hub
Binance Sub-account Skill Sub-account 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 /sapi/v1/sub-account/virtualSubAccount (POST) Create a Virtual Sub-account (For Master Account) (USER_DATA) subAccountString recvWindow Yes /sapi/v1/sub-account/futures/enable (POST) Enable Futures for Sub-account (For Master Account) (USER_DATA) em...
 1.1K
11492 simple-earn binance/binance-skills-hub
Binance Simple-earn Skill Simple-earn 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 /sapi/v1/bfusd/account (GET) Get BFUSD Account (USER_DATA) None recvWindow Yes /sapi/v1/bfusd/quota (GET) Get BFUSD Quota Details (USER_DATA) None recvWindow Yes /sapi/v1/bfusd/redeem (POST) Redeem BFUSD(TRADE) amount, type recvWindow Yes /sapi/v1/b...
 1.1K
11493 ios-security dpearson2699/swift-ios-skills
iOS Security Guidance for handling sensitive data, authenticating users, encrypting correctly, and following Apple's security best practices on iOS. Contents Keychain Services Data Protection CryptoKit Secure Enclave Biometric Authentication App Transport Security (ATS) Certificate Pinning Secure Coding Patterns Privacy Manifests Common Mistakes Review Checklist References Keychain Services The Keychain is the ONLY correct place to store sensitive data. Never store passwords, tokens, API keys, o...
 1.1K
11494 develop-web-game openai/skills
Develop Web Game Build games in small steps and validate every change. Treat each iteration as: implement → act → pause → observe → adjust. Skill paths (set once) export CODEX_HOME = " ${CODEX_HOME :- $HOME / .codex} " export WEB_GAME_CLIENT = " $CODEX_HOME /skills/develop-web-game/scripts/web_game_playwright_client.js" export WEB_GAME_ACTIONS = " $CODEX_HOME /skills/develop-web-game/references/action_payloads.json" User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills )....
 1.1K
11495 file-test-bug microsoft/github-copilot-for-azure
File Test Bug Creates a GitHub issue in microsoft/github-copilot-for-azure for integration test failures. Input Skill name (required): e.g., azure-rbac , appinsights-instrumentation Test run (optional): Timestamp of test run. Defaults to most recent with logs for the skill. Steps Ask user for skill name if not provided Parse tests/reports/junit.xml for failures matching the skill Find test run directory (specified or most recent with matching logs) Read agent-metadata.md from tests/reports/test-...
 1.1K
11496 bluebubbles steipete/clawdis
BlueBubbles Actions Overview BlueBubbles is OpenClaw’s recommended iMessage integration. Use the message tool with channel: "bluebubbles" to send messages and manage iMessage conversations: send texts and attachments, react (tapbacks), edit/unsend, reply in threads, and manage group participants/names/icons. Inputs to collect target (prefer chat_guid:... ; also +15551234567 in E.164 or user@example.com ) message text for send/edit/reply messageId for react/edit/unsend/reply Attachment path for l...
 1.1K
11497 biome-js paulrberg/agent-skills
BiomeJS Skill Quick guidance for BiomeJS configuration based on Sablier project patterns. Core Concepts Extending Shared Configs Extend shared configs via npm package exports. The consuming project must always provide its own files.includes : { "$schema": "./node_modules/@biomejs/biome/configuration_schema.json", "extends": ["@sablier/devkit/biome"], "files": { "includes": ["/*.{js,json,jsonc,ts}", "!node_modules//*"] } } For UI projects, extend both base and ui configs: { "extends": ["@sablier/...
 1.1K
11498 railway-docs railwayapp/railway-skills
Railway Docs Fetch up-to-date Railway documentation to answer questions accurately. When to Use User asks how something works on Railway (projects, deployments, volumes, etc.) User shares a docs.railway.com URL User needs current info about Railway features or pricing Before answering Railway questions from memory - check the docs first LLM-Optimized Sources Start here for comprehensive, up-to-date info: Source URL Full docs https://docs.railway.com/api/llms-docs.md llms.txt index https://railwa...
 1.1K
11499 web-search-tavily jwynia/agent-skills
Web Search (Tavily API) Search the web using Tavily's AI-optimized search API. Returns high-quality, structured results with relevance scores and optional AI-generated summaries. Note: This skill requires a Tavily API key. For basic web search using the agent's built-in capability, see web-search. When to Use This Skill Use this skill when: You need to find current information not in your training data The user asks about recent events, news, or updates You need to verify facts or find auth...
 1.1K
11500 authoring-skills vercel/next.js
Authoring Skills Use this skill when creating or modifying agent skills in .agents/skills/ . When to Create a Skill Create a skill when content is: Too detailed for AGENTS.md (code templates, multi-step workflows, diagnostic procedures) Only relevant for specific tasks (not needed every session) Self-contained enough to load independently Keep in AGENTS.md instead when: It's a one-liner rule or guardrail every session needs It's a general-purpose gotcha any agent could hit File Structure .agents...
 1.1K