53 boosters for "ai-skills" — open source, verified from GitHub, ready to install
"schemaVersion": "1.0.0", "id": "seo-geo-claude-skills", "name": "seo-geo-claude-skills",
LLM-first SEO analysis skill with 16 specialized sub-skills, 10 specialist agents, and 33 scripts for website, blog, and GitHub repository optimization. For prompt reliability in Codex/agent IDEs, map common user wording to a fixed workflow: When the user requests SEO analysis, follow this routing:
"name": "antigravity-skills", "description": "Professional Agent Skills collection for full-stack development, logic planning, and multimedia processing.", "email": "guanyangsunlight@gmail.com",
Provides Flutter developers with structured guidance on integrating Firebase In-App Messaging, including setup, message triggering, privacy controls, and campaign testing to enhance user engagement.
This skill provides the K6 and K10 psychological distress scales. Use K6 for brief screening and K10 for more detailed monitoring. Use this mode when the clinician says "start" or "administer" the K6/K10. 1. Confirm readiness and explain the past 30 days time frame plus the 5-point response scale.
Guide the configuration and management of GitHub Actions workflows, release automation, and CI/CD pipelines for the Saleor Configurator project. 1. Check workflow logs in GitHub Actions UI 2. Reproduce failure locally
This skill provides automated assistance for pinia store setup tasks within the Frontend Development domain. This skill activates automatically when you: Part of the Frontend Development skill category.
Be sure all database fields are snakecase Be sure all sub structs that are in jsonb collumns are also snakecase Be sure to not use booleans for fields, use smallint 0/1
Check codebases against common compliance frameworks and generate audit reports. 3. Report Generation All commands output structured JSON with:
1. Initialize predictive-persona-performance operational context 2. Execute primary protocol actions 3. Validate results and generate output
name: sona-learning-optimizer description: SONA-powered self-optimizing agent with LoRA fine-tuning and EWC++ memory preservation type: adaptive-learning
Generate images using Google's Nano Banana model via BlockRun's x402 API. Pay-per-request with USDC on Base - no API keys needed. 2. Get USDC on Base network:
Unified guide for working with MongoDB (document-oriented) and PostgreSQL (relational) databases. Choose the right database for your use case and master both systems. Database utility scripts in :
PR'i olusturmaktan merge'e kadar tum sureci otonom yonet. CI basarisiz olursa duzelt, review feedback gelirse uygula, butce asarsa dur.
Predict metagenome functional content from 16S rRNA marker gene data using PICRUSt2. Infer KEGG, MetaCyc, and EC abundances from ASV tables. Use when functional profiling is needed from 16S data without shotgun metagenomics sequencing.
Pulse Radar uses LLM pipeline to transform raw Telegram messages into structured knowledge. Core philosophy: Messages individually are noise; batched extraction reveals patterns. 1. JSON-only output — explicitly state "respond with ONLY JSON"
This skill provides web application security testing capabilities with Burp Suite and OWASP ZAP integration. This skill is essential for:
현재 열린 채팅방에 메시지를 보냅니다. 이 스킬은 로 설정되어 있어 Claude가 자동으로 메시지를 보낼 수 없습니다. 반드시 사용자가 를 직접 입력해야 합니다. 자동화된 메시지 전송은 카카오톡 이용약관 위반 가능성이 있으며 계정 정지 위험이 있습니다. 개인 용도로만 책임감 있게 사용하세요.
Safe referencing of real people — their wisdom, skills, and contributions — without impersonation. K-lines, not cosplay. LLMs can impersonate anyone. This is: A Hero-Story card activates a conceptual cluster associated with a person:
provides cross-platform abstractions for: Persistent key-value storage: 1. Use Schema validation - Validate all external data
Diseño de productos y entornos que sean utilizables por todas las personas, en la mayor medida posible, sin necesidad de adaptación o diseño especializado.
Create a comprehensive step-by-step checklist document for Java system prompts by following the embedded section template and deriving rows from . Follow the template sections exactly and use as the single source of truth for skill rows. 1. Read the template and inventory source
実装タスクは200行以下のIssueを対象とすることを推奨する。 大きなIssueは事前に で分解してから実行すること。 プロジェクトで以下のラベルを使用することを推奨:
Comprehensive guide for managing Dokploy instances via CLI, API, and production deployment patterns. This skill includes two CLI options: Or with direct API call:
