Browse Skills

addyosmani/using-agent-skills

Verified by SkillsAuth

development

Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.

glittercowboy/create-agent-skills

Verified by SkillsAuth

development

Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

langgraph4j/.agent/skills/make_readme

Verified by SkillsAuth

documentation

--- name: make_readme description: create or update a meaningful readme # What is a README README.md files are for humans: * quick starts, * project descriptions * contribution guidelines. # Structure a README.md must be structured in, at least, the following paragraphs * Getting started * Introduction * Core Features & Benefits * Core Concepts Explained * Project Structure * Installation * A Simple Example * References

brycewang-stanford/legal-agent-skills-guide

Verified by SkillsAuth

tools

Agent skills collection for legal research and automation

bankrbot/skills/bankr-twitter-agent

Verified by SkillsAuth

development

# Skill: twitter-agent > Build and run one or more Twitter/X agents, each with a distinct personality, storyline, and post-image library. # Twitter Agent Skill This skill provides a framework for creating, managing, and automating Twitter/X agents with persistent personalities and voices. It supports running multiple agents side-by-side, each with its own files and (optionally) its own X account. ## Prerequisites ### X Account Setup (REQUIRED — Do This First, Per Agent) Every agent's X acco

agentworkforce/creating-agent-skills-skill

Verified by SkillsAuth

tools

Use when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rules

noizefield/.agent/skills/skill_troubleshooting

Verified by SkillsAuth

testing

# SKILL: TROUBLESHOOTING & ISSUE RESOLUTION ## STEP 1: CHECK KNOWN ISSUES FIRST **Before trying random solutions:** ```powershell # Search known issues database $errorPattern = "duplicate target juce" $knownIssues = Get-Content ...agent\troubleshooting\known-issues.yaml | ConvertFrom-Yaml $matches = $knownIssues.issues | Where-Object { $_.error_patterns -match $errorPattern } if ($matches) { Write-Host "✓ Known issue found: $($matches.title)" Write-Host "Resolution: $($matches.re

noizefield/.agent/skills/skill_testing

Verified by SkillsAuth

tools

# SKILL: TESTING **Goal:** Stability Check. ## TASKS 1. **Pluginval:** Run validation script. 2. **Crash Analysis:** If crash reported, read Documents/APC_CRASH_REPORT.txt. 3. **Manual Check:** Ask user to load in DAW and move knobs.

noizefield/.agent/skills/skill_planning

Verified by SkillsAuth

tools

# SKILL: ARCHITECTURE & PLANNING **Goal:** Define DSP architecture, complexity assessment, and implementation strategy **Trigger:** `/plan [Name]` **Input:** Reads `plugins/[Name]/.ideas/creative-brief.md` and `parameter-spec.md` **Output Location:** `plugins/[Name]/.ideas/` --- ## 🎯 PHASE 2: PLAN (Architecture & Strategy) **Prerequisites:** - `plugins/[Name]/.ideas/creative-brief.md` exists - `plugins/[Name]/.ideas/parameter-spec.md` exists - Phase 1 (DREAM) complete **Output Files:** - `p

noizefield/.agent/skills/skill_packaging

Verified by SkillsAuth

tools

# SKILL: PACKAGING (Cross-Platform) **Goal:** Create professional, cross-platform plugin installers for Windows, macOS, and Linux **Trigger:** `/ship [Name]` or "Ship [Name]" **Prerequisites:** Phase 4 (CODE) complete, audio engine working, all tests passed **Output Location:** `dist/[Name]_v[version]/` --- ## Overview This skill handles the complete packaging and distribution process for APC plugins. It supports: - **Local builds** (current platform only) - **GitHub Actions builds** (cross

noizefield/.agent/skills/skill_implementation

Verified by SkillsAuth

tools

# SKILL: DSP IMPLEMENTATION **Goal:** Implement audio processing where parameters control DSP **Focus:** PluginProcessor.h, PluginProcessor.cpp **Output Location:** `plugins/[Name]/Source/` --- ## 📊 PHASE 4: CODE (DSP Implementation) **Trigger:** `/impl [Name]` (after DESIGN phase complete) **Input:** Reads `plugins/[Name]/status.json` and `.ideas/parameter-spec.md` **Prerequisites:** Architecture plan complete, UI framework selected **State Validation:** ```powershell # Import state manage

noizefield/.agent/skills/skill_ideation

Verified by SkillsAuth

tools

# SKILL: IDEATION & DREAMING **Goal:** Define the plugin concept and initialize the project state. **Trigger:** `/dream [Name]` **Output Location:** `plugins/[Name]/` ## ⛔ OUTPUT RESTRICTIONS (MANDATORY) * **NO C++ Code.** * **NO Build Scripts.** * **NO CMake configurations.** ## STEP 1: THE INTERVIEW **Do NOT generate files yet.** If the user prompt is vague, ask 3 clarifying questions: 1. **Sonic Goal:** What is the character? (e.g., "Dirty Tape Delay", "Clean EQ") 2. **Controls:**

noizefield/.agent/skills/skill_debug

Verified by SkillsAuth

tools

--- name: skill_debug description: Autonomous Debugging Instructions for Visual Studio Code: for [plugin]. --- ## Purpose This document defines a **self-directed debugging workflow** for a Large Language Model (LLM) operating inside or alongside **Visual Studio Code: (VS Code:)**. The goal is for the LLM to: 1. Inspect a codebase without human intervention 2. Identify likely failure points 3. Insert breakpoints programmatically 4. Generate a valid VS Code: `launch.json` debugging configuratio

orinachum/qq/.agent/skills/test-on-finish

Verified by SkillsAuth

tools

## Updated Skill Protocol ### name: call-qq **Description:** Calls qq agent from cli. --- ### Code Review Skill When you need to ask the device a question, use **call-qq**. #### Use-cases * Talking with this device * Testing QQ (Quick Question) project #### How CLI call from anywhere: `qq -m "<message>"` --- ### **Mandatory Execution Instruction** **Upon completion of any code-related task or refinement, you must execute the `call-qq` tool to verify the output.** > **Note:** Do not

wentorai/legal-agent-skills-guide

Verified by SkillsAuth

tools

Agent skills collection for legal research and automation

ahastudio/_agent/skills/analyze-article

Verified by SkillsAuth

development

--- name: analyze-article description: Read a web source — an article OR a non-article (GitHub repo, project homepage, service site) — and write a TIL document (in Korean) with analysis, critique, and insights. The H1 title is written in Korean. Published pieces (articles, posts, papers, tweets, videos) get a `원문: [원문 제목](URL)` titled-link source line and a `## 요약` section; non-articles get bare `<URL>` line(s) with NO `원문:` label, no titled link, and a fitting first heading like `

jaktestowac/testing-agent-skills

Verified by SkillsAuth

testing

Tests the customization assets themselves - skills, prompts, custom agents, instructions - the way a product is tested: activation cases that check an asset fires when it should and stays quiet when it should not, output-contract cases, safety cases, collision cases between assets competing for the same trigger, a weighted rubric scored blind, and a baseline-versus-candidate gate before an edit ships. Use when a skill is edited and nobody knows whether behaviour changed, when two skills fight over the same request, when a description is being tuned for discoverability, when a collection has grown past manual spot-checking, or when the request mentions skill evals, prompt regression, or "does this skill actually work".

jaktestowac/testing-agent-skills

Verified by SkillsAuth

testing

Tests the customization assets themselves - skills, prompts, custom agents, instructions - the way a product is tested: activation cases that check an asset fires when it should and stays quiet when it should not, output-contract cases, safety cases, collision cases between assets competing for the same trigger, a weighted rubric scored blind, and a baseline-versus-candidate gate before an edit ships. Use when a skill is edited and nobody knows whether behaviour changed, when two skills fight over the same request, when a description is being tuned for discoverability, when a collection has grown past manual spot-checking, or when the request mentions skill evals, prompt regression, or "does this skill actually work".

seaworld008/using-agent-skills

Verified by SkillsAuth

development

Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.

FrancoStino/effective-agent-skills

Verified by SkillsAuth

development

Author and review high-quality agent skills with triggers, progressive disclosure, and safety notes.