convez.ai
Skill
satiricalguru

Agents-skills

satiricalguru/Agents-skills

Ver no GitHub
InicialPluginScore · de 0 a 100

A curated collection of powerful agentic skills for automation, development, reverse engineering, productivity, and AI-assisted workflows — designed to extend Claude into a smarter autonomous engineering companion ⚡

Instalação

$npx convez-ai satiricalguru/Agents-skills

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
9
Forks
2
Acompanhando
0
Saúde
42%
Último commit
há 1 semana
Versão
v1.1.0
Issues abertas
0
Contribuidores
2

README

A tradução para o português deste README ainda está na fila.

AI Agents Skills

A curated collection of developer agent prompts, custom coding assistant skills, specialist personas, checklists, and automation tools. Designed to optimize and extend capabilities for the Antigravity IDE, Claude, Gemini, ChatGPT, and other agentic coding environments. 🛠️

🚀 Try the Interactive Agent Skills Dashboard Live! — Browse, select, and compile custom system instructions for Cursor, Windsurf, Antigravity, Claude Code, and ChatGPT in seconds.

This repository is structured as a standard plugin, allowing you to load all contained skills at once or install specific skills individually.


📑 Table of Contents


🛠️ Available Skills

Meta & General Execution

SkillDescriptionUse When
using-agent-skillsMaps incoming work to the right skill workflow and defines shared operating rules.Starting a session or deciding which skill applies
no-excuses-executorDirect task execution with zero hedging. Forces action-first completion, suppresses over-caution.Running direct actions/commands without hesitation

Define - Clarify what to build

SkillDescriptionUse When
interview-meOne-question-at-a-time interview that extracts what the user actually wants instead of what they think they should want, until ~95% confidence.The ask is underspecified, or the user invokes "interview me" / "grill me"
idea-refineStructured divergent/convergent thinking to turn vague ideas into concrete proposals.You have a rough concept that needs exploration
spec-driven-developmentWrite a PRD covering objectives, commands, structure, code style, testing, and boundaries before any code.Starting a new project, feature, or significant change

Plan - Break it down

SkillDescriptionUse When
planning-and-task-breakdownDecompose specs into small, verifiable tasks with acceptance criteria and dependency ordering.You have a spec and need implementable units

Build - Write the code

SkillDescriptionUse When
incremental-implementationThin vertical slices - implement, test, verify, commit. Feature flags, safe defaults, rollback-friendly changes.Any change touching more than one file
test-driven-developmentRed-Green-Refactor, test pyramid (80/15/5), test sizes, DAMP over DRY, Beyonce Rule, browser testing.Implementing logic, fixing bugs, or changing behavior
context-engineeringFeed agents the right information at the right time - rules files, context packing, MCP integrations.Starting a session, switching tasks, or when output quality drops
source-driven-developmentGround every framework decision in official documentation - verify, cite sources, flag what's unverified.You want authoritative, source-cited code for any framework or library
doubt-driven-developmentAdversarial fresh-context review of every non-trivial decision in-flight - CLAIM → EXTRACT → DOUBT → RECONCILE → STOP, with optional user-authorized cross-model escalation.Stakes are high (production, security, irreversible), working in unfamiliar code, or verifying early is cheaper
frontend-ui-engineeringComponent architecture, design systems, state management, responsive design, WCAG 2.1 AA accessibility.Building or modifying user-facing interfaces
api-and-interface-designContract-first design, Hyrum's Law, One-Version Rule, error semantics, boundary validation.Designing APIs, module boundaries, or public interfaces

Verify - Prove it works

SkillDescriptionUse When
browser-testing-with-devtoolsChrome DevTools MCP for live runtime data - DOM inspection, console logs, network traces, performance profiling.Building or debugging anything that runs in a browser
debugging-and-error-recoveryFive-step triage: reproduce, localize, reduce, fix, guard. Stop-the-line rule, safe fallbacks.Tests fail, builds break, or behavior is unexpected

Review - Quality gates before merge

SkillDescriptionUse When
code-review-and-qualityFive-axis review, change sizing (~100 lines), severity labels (Nit/Optional/FYI), review speed norms, splitting strategies.Before merging any change
code-simplificationChesterton's Fence, Rule of 500, reduce complexity while preserving exact behavior.Code works but is harder to read or maintain than it should be
security-and-hardeningOWASP Top 10 prevention, auth patterns, secrets management, dependency auditing, three-tier boundary system.Handling user input, auth, data storage, or external integrations
performance-optimizationMeasure-first approach - Core Web Vitals targets, profiling workflows, bundle analysis, anti-pattern detection.Performance requirements exist or you suspect regressions

Ship - Deploy with confidence

SkillDescriptionUse When
git-workflow-and-versioningTrunk-based development, atomic commits, change sizing (~100 lines), the commit-as-save-point pattern.Making any code change (always)
ci-cd-and-automationShift Left, Faster is Safer, feature flags, quality gate pipelines, failure feedback loops.Setting up or modifying build and deploy pipelines
deprecation-and-migrationCode-as-liability mindset, compulsory vs advisory deprecation, migration patterns, zombie code removal.Removing old systems, migrating users, or sunsetting features
documentation-and-adrsArchitecture Decision Records, API docs, inline documentation standards - document the why.Making architectural decisions, changing APIs, or shipping features
observability-and-instrumentationStructured logging, RED metrics, OpenTelemetry tracing, symptom-based alerting - instrument as you build.Adding telemetry, or shipping anything that runs in production
shipping-and-launchPre-launch checklists, feature flag lifecycle, staged rollouts, rollback procedures, monitoring setup.Preparing to deploy to production

Specialized Tools & Systems

SkillDescriptionKey Features & Integrations
mongodbModel data, connect, write updates, index schemas, run aggregations, and perform Atlas/Vector search in MongoDB.Mongoose models, update operators, ESR indexes, multi-document transactions, Atlas search
reverse-engineering-skillBinary analysis, firmware extraction, vulnerability research, and CTF solvers.Ghidra MCP, radare2-mcp, angr symbolic execution, class-dump, jadx, checksec
supabaseIntegrate, query, manage migrations, TypeScript type generation, and configure RLS on Supabase.Postgres migrations, RLS security, Next.js SSR cookie auth, Edge Functions, pgvector

👥 Specialist Personas

Specialist personas are located under the agents/ directory and act as targeted reviewers:

PersonaRoleFocus
code-reviewerSenior Staff EngineerFive-axis code review checking readability, security, testing, architecture, and correctness.
test-engineerQA SpecialistDesigning comprehensive test strategies, coverage analysis, and verifying reliability.
security-auditorSecurity EngineerVulnerability scanning, threat modeling, and OWASP compliance check.
web-performance-auditorWeb Performance EngineerPerformance audits against Core Web Vitals targets using DevTools instrumentation.

📋 Reference Checklists

Quick-reference checklists located in references/:


📂 Curated AI Model Prompts

The prompts/ directory contains a curated library of clean, date-standardized system prompts for leading AI model families. These prompts are structured without underscores (space-separated filenames) and updated to represent a current date context of June 14, 2026:

Model FamilyPrompts
Antigravityantigravity prompt.md
Claudeclaude 4.6 sonnet prompt.txt, claude 4.7 opus prompt.txt, claude code prompt.md
ChatGPTchatgpt gpt 4.5 prompt.md, chatgpt gpt 4o prompt.txt, chatgpt gpt 5.4 prompt.md, chatgpt gpt 5.5 prompt.md, chatgpt o3 o4 mini prompt.txt
Geminigemini 2.5 pro prompt.md, gemini 3.1 pro prompt.md, gemini 3.5 flash prompt.md
Groq / Grokgrok 3 prompt.md, grok 4.1 prompt.txt, grok 5.0 prompt.txt
Llamallama 4 whatsapp prompt.txt, llama 5 prompt.txt, llama muse spark prompt.txt
DeepSeekdeepseek r1 prompt.md, deepseek v3 prompt.md
GLMglm 5.1 prompt.md, glm 5 turbo prompt.md
Kimikimi k2.6 prompt.md
Qwenqwen 3.6 plus prompt.md, qwen 3.7 plus prompt.md, qwen 3.7 max prompt.md
Minimaxminimax prompt.txt
Mistralmistral le chat prompt.md
Perplexityperplexity deep research prompt.txt
Replitreplit agent prompt.md
Vercelvercel v0 prompt.txt
Windsurfwindsurf prompt.md, windsurf tools.md

🚀 Installation

Choose one of the installation methods below.

Method 1: One-Line Terminal Installer (Recommended)

Run the following command in your terminal to automatically install or update all agent skills:

curl -sSL https://raw.githubusercontent.com/satiricalguru/Agents-skills/main/install.sh | bash

Method 2: NPM / NPX Installer (Node.js Users)

You can run the installer script directly using npx (without cloning the repository manually):

npx github:satiricalguru/Agents-skills

Alternatively, you can install the package globally via npm to make the agents-skills command available globally:

# Install globally
npm install -g github:satiricalguru/Agents-skills

# Run the installer command at any time to install/update skills
agents-skills

Method 3: Manual Unified Plugin Installation

Installing the entire repository as a plugin manually automatically exposes all current and future skills to your agent:

# Navigate to your agent's plugins directory
cd ~/.gemini/config/plugins

# Clone this repository
git clone https://github.com/satiricalguru/Agents-skills.git

# Restart your IDE / Agent to load the plugin

Method 3: Individual Skill Installation

Install only a specific skill into an existing plugin:

# Copy the desired skill folder
cp -r skills/<skill-name> ~/.gemini/config/plugins/<your-plugin-name>/skills/

# Restart your IDE / Agent to register the skill

⚙️ Skill-Specific Setup

Some skills require additional system dependencies (CLI utilities, Python libraries, or MCP servers).


➕ Adding New Skills

When adding a new skill, follow this structure:

# 1. Create skill directory (lowercase + hyphens)
mkdir -p skills/my-new-skill

# 2. Add required SKILL.md with YAML frontmatter
---
name: my-new-skill
description: Brief description of the skill.
---
# My New Skill
...
  1. Add scripts/references in scripts/ and references/ subdirectories if needed.
  2. Update the Available Skills table in this README.

🌍 Global System Skills

DevTools & Browser Auditing

Science & Bioinformatics

Firebase & Xcode

Platforms & SDKs


📋 Repository Structure

.
├── README.md                    # This file
├── prompts/                     # Curated AI model prompts (new)
├── instructions/                # Model behavioral instructions
│   ├── jailbreak/               # Custom/jailbreak instructions
│   │   ├── Antigravity.md
│   │   ├── ChatGPT.md
│   │   ├── Claude.md
│   │   ├── Deepseek.md
│   │   ├── Gemini.md
│   │   ├── Glm.md
│   │   ├── Groq.md
│   │   └── Qwen.md
│   └── general/                 # Normal/standard instructions
│       ├── Antigravity.md
│       ├── ChatGPT.md
│       ├── Claude.md
│       ├── Deepseek.md
│       ├── Gemini.md
│       ├── Glm.md
│       ├── Groq.md
│       └── Qwen.md
├── skills/
│   ├── idea-refine/                 # idea-refine support assets (examples, frameworks, etc.)
│   ├── reverse-engineering-skill/   # reverse-engineering support assets (SETUP.md, scripts, etc.)
│   └── ... (85 restructured .md skill files directly in skills/)
├── references/                  # Supplementary checklists
├── agents/                      # Specialist personas
├── commands/                    # Antigravity CLI commands
├── .claude/                     # Claude Code commands
├── .gemini/                     # Gemini CLI commands
├── .opencode/                   # OpenCode commands/config
├── hooks/                       # Session lifecycle hooks
├── scripts/                     # Utility scripts
└── plugin.json                  # Antigravity plugin manifest

📄 License

MIT — free to fork and use for personal or commercial projects.

Ver o original no GitHub

Bom para

Relacionados