Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings
/ agt Public

A modular toolkit for extending AI coding agents

Notifications You must be signed in to change notification settings

Open330/agt

Repository files navigation


agent-skills β€” Skills, personas, and hooks for AI coding agents

Stars agt Release npm License Skills Personas

Quickstart β€’ Skills β€’ Personas β€’ Hooks β€’ Install β€’ Contributing
ν•œκ΅­μ–΄

What is this?

A collection of skills, personas, and hooks for AI coding agents (Claude Code, Codex CLI, Gemini CLI). Each skill is a self-contained markdown module that gives an agent domain-specific capabilities.

CLI tool: Install and manage skills with agt β€” npm install -g @open330/agt or just npx @open330/agt

Quickstart for Agents

Install the agent-skills toolkit into this project:
1. Install the "core" profile (essential skills for every workspace):
 npx @open330/agt skill install --profile core
2. Install all available personas globally:
 npx @open330/agt persona install --global --from jiunbae/agent-skills
3. Verify installation:
 npx @open330/agt skill list
 npx @open330/agt persona list
Note: Use `npm install -g @open330/agt` first if you prefer running `agt` directly.

Slowstart for Humans

With npx (No Install)

npx @open330/agt skill install --profile core # Install core skills
npx @open330/agt skill install -g --from jiunbae/agent-skills # Browse & install from repo
npx @open330/agt persona install -g --from jiunbae/agent-skills

With agt CLI (Global Install)

npm install -g @open330/agt
agt skill install --profile core
agt skill install -g git-commit-pr # Install a skill globally
agt persona install -g --all # Install all personas globally

With install.sh

git clone https://github.com/jiunbae/agent-skills ~/.agent-skills
cd ~/.agent-skills
./install.sh --core # Core skills only
./install.sh --core --hooks # Core + hooks
./install.sh all --link-static --codex # Everything
./install.sh --list # List available options

Install Options

Option Description
--core Install core skills globally (recommended)
--link-static Symlink ~/.agents -> static/ (global context)
--codex Codex CLI support (AGENTS.md + skills symlink)
--hooks Install Claude Code hooks
--personas Install agent personas
--copy Copy instead of symlink
--dry-run Preview only
--uninstall Remove installed skills

Core Skills

Installed by default with --core:

  • development/git-commit-pr β€” Git commit & PR guide
  • context/context-manager β€” Project context auto-loader
  • context/static-index β€” Global static context index
  • security/security-auditor β€” Repository security audit
  • agents/background-implementer β€” Background parallel implementation
  • agents/background-planner β€” Background parallel planning
  • agents/background-reviewer β€” Multi-LLM parallel code review

Skills Catalog

πŸ€– agents/ β€” AI Agents

Skill Description
background-implementer Parallel multi-LLM implementation with context safety
background-planner Parallel multi-LLM planning with auto-save
background-reviewer Multi-LLM parallel code review (security/architecture/quality)

πŸ›  development/ β€” Dev Tools

Skill Description
context-worktree Auto git worktree per task
git-commit-pr Git commit & PR generation guide
iac-deploy-prep IaC deployment prep (K8s, Dockerfile, CI/CD)
multi-ai-code-review Multi-AI code review orchestrator
playwright Playwright browser automation
pr-review-loop PR review await & auto-fix loop
task-master Task Master CLI task management

πŸ“Š business/ β€” Business

Skill Description
bm-analyzer Business model analysis & monetization strategy
document-processor PDF, DOCX, XLSX, PPTX processing
proposal-analyzer Proposal / RFP analysis

πŸ”— integrations/ β€” Integrations

Skill Description
appstore-connect App Store Connect automation
discord-skill Discord REST API
google-search-console Google Search Console API
kubernetes-skill Kubernetes cluster management
notion-summary Notion page upload
obsidian-tasks Obsidian TaskManager (Kanban, Dataview)
obsidian-writer Obsidian Vault document upload
service-manager Docker container & service management
slack-skill Slack app development & API
vault-secrets Vaultwarden credentials & API key management

🧠 ml/ β€” ML/AI

Skill Description
audio-processor ffmpeg-based audio processing
ml-benchmark ML model benchmarking
model-sync Model file server sync
triton-deploy Triton Inference Server deployment

πŸ” security/ β€” Security

Skill Description
security-auditor Repository security audit

πŸ“ context/ β€” Context Management

Skill Description
context-manager Project context auto-loader
static-index Global static context index with user profile

πŸ”§ meta/ β€” Meta Skills

Skill Description
karpathy-guide LLM coding error reduction guidelines
skill-manager Skill ecosystem management
skill-recommender Skill auto-recommender

Personas

Expert identities as markdown files β€” usable with any AI agent.

Persona Role Domain
security-reviewer Senior AppSec Engineer OWASP, auth, injection
architecture-reviewer Principal Architect SOLID, API design, coupling
code-quality-reviewer Staff Engineer Readability, complexity, DRY
performance-reviewer Performance Engineer Memory, CPU, I/O, scalability
database-reviewer Senior DBA Query optimization, schema, indexing
frontend-reviewer Senior Frontend Engineer React, accessibility, performance
devops-reviewer Senior DevOps/SRE K8s, IaC, CI/CD

Using with agt CLI

agt persona review security-reviewer --codex
agt persona review security-reviewer --codex "is this architecture scalable?"
agt persona install -g --all
agt persona show security-reviewer

Using Directly

Personas are just .md files. Any agent that can read a file can adopt a persona:

cat personas/security-reviewer.md | codex -q "Review this code"
cat personas/security-reviewer.md # pipe to any AI agent
.agents/personas/security-reviewer.md ← project local (highest priority)
~/.agents/personas/security-reviewer.md ← user global
personas/security-reviewer.md ← library (bundled)

Hooks

Event-driven automation for Claude Code.

./install.sh --hooks
Hook Event Description
english-coach UserPromptSubmit Rewrites prompts in natural English with vocabulary
prompt-logger UserPromptSubmit Logs prompts to MinIO for analytics

Creating Your Own Skills Repo

You can create your own skills repository with the same structure as this one. agt will discover it automatically.

Directory Structure

my-skills/
β”œβ”€β”€ agents/ # Group: AI agent skills
β”‚ └── my-agent/
β”‚ └── SKILL.md # Required
β”œβ”€β”€ development/ # Group: dev tools
β”‚ └── my-tool/
β”‚ β”œβ”€β”€ SKILL.md # Required
β”‚ β”œβ”€β”€ scripts/ # Optional: helper scripts
β”‚ └── templates/ # Optional: templates
β”œβ”€β”€ personas/ # Personas directory
β”‚ β”œβ”€β”€ my-reviewer/
β”‚ β”‚ └── PERSONA.md
β”‚ └── my-expert.md # Single-file persona also works
β”œβ”€β”€ profiles.yml # Optional: installation profiles
└── README.md

SKILL.md Format

---
name: my-skill-name
description: "What this skill does. Use for 'keyword1', 'keyword2' requests."
trigger-keywords: keyword1, keyword2, ν‚€μ›Œλ“œ
allowed-tools: Read, Write, Edit, Bash, Grep, Glob
priority: high
tags: [category, tool-name]
---
# Skill Title
## Quick Start
\`\`\`bash
command --example
\`\`\`
## Workflow
Step-by-step instructions for the AI agent...
## Best Practices
**DO:**
- Follow this pattern
**DON'T:**
- Avoid this anti-pattern
Field Required Description
name Yes Skill identifier (kebab-case)
description Yes What the skill does + trigger keywords
trigger-keywords No Comma-separated activation keywords
allowed-tools No Tools available to the skill
priority No high / medium / low
tags No Category tags

PERSONA.md Format

---
name: my-reviewer
role: "Senior Engineer β€” Domain Expert"
domain: security
type: review
tags: [security, owasp, auth]
---
# My Reviewer
## Identity
Background, expertise, and review philosophy...
## Review Lens
When reviewing, evaluate:
1. Security vulnerabilities
2. Best practice adherence
...
## Output Format
### Findings
#### [SEVERITY] Finding Title
- **File**: path:line
- **Impact**: Description
- **Recommendation**: Fix
Field Required Description
name Yes Persona identifier (kebab-case)
role Yes Job title / expert role
domain Yes Expertise domain
type Yes Usually review
tags Yes Relevant focus areas

profiles.yml Format

core:
 description: "Essential skills for every workspace"
 skills: # Explicit skill paths
 - development/git-commit-pr
 - context/context-manager
 groups: # Include entire groups
 - agents
dev:
 description: "Development workflow tools"
 groups:
 - development

Test & Install

# Point agt to your repo
export AGT_DIR=~/my-skills
# Or clone to the default location
git clone https://github.com/you/my-skills ~/.agent-skills
agt skill list # Verify skills discovered
agt skill install my-skill -g # Install globally
agt skill install --profile core # Install a profile
agt persona install my-reviewer # Install a persona
# Others can install from your repo directly
agt skill install --from you/my-skills
agt persona install --from you/my-skills

Create with AI (Prompts)

Copy-paste these prompts to create skills and personas with any AI agent.

Create a Skill

Prompt: Create a new skill 
Create a new skill for the agent-skills repository.
Skill name: [YOUR_SKILL_NAME]
Group: [GROUP_NAME] (e.g., development, integrations, agents, ml, security)
Description: [WHAT_THE_SKILL_DOES]
Create the file at [GROUP]/[SKILL_NAME]/SKILL.md with this structure:
1. YAML frontmatter with: name, description (include trigger keywords and Korean keywords
 if applicable), trigger-keywords, allowed-tools, priority, tags
2. A "Quick Start" section with 2-3 essential commands/examples
3. A "Workflow" section with step-by-step instructions
4. A "Best Practices" section with DO/DON'T guidelines
Rules:
- Description should be third person, under 200 chars, end with trigger conditions
- Keep under 300 lines total
- Code examples should be practical and production-ready
- Include both English and Korean trigger keywords where relevant
- Focus on what the AI agent should DO, not theory
Reference this existing skill for style:
---
name: git-commit-pr
description: "Guides git commit and PR creation with security validation. Activates on
 commit, PR, pull request requests."
trigger-keywords: commit, pr, pull request, 컀밋
allowed-tools: Read, Bash, Grep, Glob
priority: high
tags: [git, commit, pr, security]
---

Create a Persona

Prompt: Create a review persona 
Create a new code review persona for the agent-skills repository.
Persona name: [YOUR_PERSONA_NAME]-reviewer
Domain: [DOMAIN] (e.g., security, architecture, performance, database, frontend, devops)
Role: [JOB_TITLE]
Create the file at personas/[PERSONA_NAME]/PERSONA.md with this structure:
1. YAML frontmatter with: name, role, domain, type (review), tags
2. "Identity" section: background, expertise (5+ bullet points), attitude (2-3 sentences)
3. "Review Lens" section: numbered list of what they evaluate
4. "Evaluation Framework" section: table with Category, Severity (CRITICAL/HIGH/MEDIUM/LOW), Criteria
5. "Output Format" section: markdown template for review output
6. "Red Flags" section: patterns that MUST always be flagged
7. "Key Principles" section: numbered guiding principles
Rules:
- The persona should be opinionated and have a clear point of view
- Include specific technologies/frameworks in their expertise
- Red flags should be concrete, not generic
- Output format should include: Summary, Findings (with severity), Positive Observations
- Keep under 200 lines
Reference this existing persona for style:
---
name: security-reviewer
role: "Senior Application Security Engineer"
domain: security
type: review
tags: [security, owasp, auth, injection, xss, ssrf]
---

Create a Profile

Prompt: Create an installation profile 
Create a new installation profile for the agent-skills repository.
Profile name: [PROFILE_NAME]
Purpose: [WHO_IS_THIS_FOR]
Available groups: agents, development, business, integrations, ml, security, context, meta
Add the profile to profiles.yml with:
- description: one-line description of the profile
- skills: list of specific group/skill-name paths to include (optional)
- groups: list of group names to include all skills from (optional)
You can mix both "skills" (specific picks) and "groups" (entire categories).
Example:
```yaml
backend:
 description: "Backend development essentials"
 skills:
 - context/context-manager
 - security/security-auditor
 groups:
 - development
 - integrations

Keep profiles focused β€” a profile with everything is just "full" or "all".


</details>
### Create a Complete Skills Repo
<details>
<summary><b>Prompt: Bootstrap a new skills repository</b></summary>

Create a new agent-skills repository with the following structure. This repo will be discoverable by the agt CLI tool (https://github.com/open330/agt).

Repository purpose: [YOUR_PURPOSE] Skills to include: [LIST_OF_SKILLS] Personas to include: [LIST_OF_PERSONAS]

Create the following structure:

  1. Group directories (e.g., development/, integrations/) containing skill subdirectories
  2. Each skill has a SKILL.md with YAML frontmatter (name, description, trigger-keywords, allowed-tools, priority, tags) and markdown content (Quick Start, Workflow, Best Practices)
  3. A personas/ directory with PERSONA.md files for each persona
  4. A profiles.yml defining installation profiles (core, dev, full at minimum)
  5. A README.md documenting the repository

Requirements:

  • Skills are organized by group: each group is a directory, each skill is a subdirectory
  • A valid skill must have SKILL.md in its directory
  • A valid persona must have PERSONA.md (in a directory or as a standalone .md file)
  • profiles.yml uses "skills" (explicit paths) and/or "groups" (entire categories)
  • The "all" profile is built-in to agt, no need to define it

Users install with: git clone https://github.com/you/repo ~/.agent-skills agt skill install --profile core -g agt persona install --all -g


</details>
---
## Architecture

agent-skills/ open330/agt (CLI tool) β”œβ”€β”€ agents/ AI agent skills β”œβ”€β”€ agt/ Rust CLI β”œβ”€β”€ development/ Dev tool skills β”œβ”€β”€ npm/ npm packaging β”œβ”€β”€ business/ Business skills β”œβ”€β”€ setup.sh Installer β”œβ”€β”€ integrations/ Integration skills └── assets/ Branding β”œβ”€β”€ ml/ ML/AI skills β”œβ”€β”€ security/ Security skills β”œβ”€β”€ context/ Context management β”œβ”€β”€ meta/ Meta skills β”œβ”€β”€ personas/ Expert personas β”œβ”€β”€ hooks/ Claude Code hooks β”œβ”€β”€ static/ Global context β”œβ”€β”€ install.sh Local installer └── codex-support/ Codex CLI


---
## Contributing
1. **Add a skill** β€” Create a new skill in the appropriate category
2. **Add a persona** β€” Create a domain expert persona
3. **Improve docs** β€” Fix typos, add examples, translate
4. **Report issues** β€” Bug reports and feature requests welcome
```bash
git clone https://github.com/jiunbae/agent-skills ~/.agent-skills
cd ~/.agent-skills
./install.sh --core

For CLI tool contributions, see open330/agt.

License

MIT License.

33 skills | 7 personas | 2 hooks
CLI tool: open330/agt

AltStyle γ«γ‚ˆγ£γ¦ε€‰ζ›γ•γ‚ŒγŸγƒšγƒΌγ‚Έ (->γ‚ͺγƒͺγ‚ΈγƒŠγƒ«) /