Agent skill

Existing Repo

by alinaqi in alinaqi/maggy

Analyze existing repositories, maintain structure, setup guardrails and best practices

MITAuto-check: notesDevelopment

Install Existing Repo

skills CLI
$ npx skills add alinaqi/maggy --skill existing-repo -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install alinaqi/maggy existing-repo --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/existing-repo .claude/skills/existing-repo && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
existing-repo
GitHub stars
707
Token cost
~4k tokens
SKILL.md length
582 words
Files
1
Skills in repo
71
Repo updated
First seen
Licence
MIT

At a glance

Analyze existing repositories, maintain structure, setup guardrails and best practices

  • Works in 6 steps: Repository Analysis → Convention Detection → Guardrails Audit → …
  • Tasks that involve Linting and formatting
  • SKILL.md covers Core Principle, Phase 1: Repository Analysis, Phase 2: Convention Detection and Phase 3: Guardrails Audit, plus 5 more sections
  • Calls git, npm and npx; reaches github.com

What it does

Existing Repo is an agent skill from alinaqi/maggy. Analyze existing repositories, maintain structure, setup guardrails and best practices

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Linting and formatting and LLM guardrails. It works with ESLint. The repository describes itself as: What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center. The licence is MIT.

When your agent uses it

  • Tasks that involve Linting and formatting
  • Tasks that involve LLM guardrails

Example prompts

  • “/existing-repo”

Requirements

  • Python 3
  • Node.js
  • Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Repository Analysis
  2. Convention Detection
  3. Guardrails Audit
  4. Guardrails Setup
  5. Structure Preservation Rules
  6. Analysis Report Template

What it can do on your machine

Read from SKILL.md and the folder at commit 72a456e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • npm
    • npx
    • pip
    • vitest
    • eslint
    • prettier

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • typicode.github.io
    • pre-commit.com
    • commitlint.js.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Existing Repo loads about 4k tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 582 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Glob, Grep, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from alinaqi/maggy at commit 72a456e, republished under its MIT licence (© alinaqi). 582 words, ~3,989 tokens.

Download SKILL.mdSave it as .claude/skills/existing-repo/SKILL.md (or your agent's skills folder).
name
existing-repo
description
Analyze existing repositories, maintain structure, setup guardrails and best practices
allowed-tools
Read, Glob, Grep, Bash
when-to-use
When working with an existing codebase for the first time or adding guardrails
user-invocable
true
effort
high

Existing Repository Skill

For working with existing codebases - analyze structure, respect conventions, and set up proper guardrails without breaking anything.

Sources: Husky | lint-staged | pre-commit | commitlint


Core Principle

Understand before modifying. Existing repos have conventions, patterns, and history. Your job is to work within them, not reorganize them.


Phase 1: Repository Analysis

ALWAYS run this analysis first when joining an existing repo.

1.1 Basic Detection
bash
# Check git status
git remote -v 2>/dev/null
git branch -a 2>/dev/null
git log --oneline -5 2>/dev/null

# Check for existing configs
ls -la .* 2>/dev/null | head -20
ls *.json *.toml *.yaml *.yml 2>/dev/null
1.2 Tech Stack Detection
bash
# JavaScript/TypeScript
ls package.json tsconfig.json 2>/dev/null

# Python
ls pyproject.toml setup.py requirements*.txt 2>/dev/null

# Mobile
ls pubspec.yaml 2>/dev/null          # Flutter
ls android/build.gradle 2>/dev/null   # Android
ls ios/*.xcodeproj 2>/dev/null        # iOS

# Other
ls Cargo.toml 2>/dev/null             # Rust
ls go.mod 2>/dev/null                 # Go
ls Gemfile 2>/dev/null                # Ruby
1.3 Repo Structure Type
PatternDetectionMeaning
Monorepopackages/, apps/, workspaces in package.jsonMultiple projects, shared tooling
Full-Stack Monolithfrontend/ + backend/ in same repoSingle team, tightly coupled
Separate ConcernsOnly frontend OR backend codeSplit repos, separate deploys
MicroservicesMultiple service-* or domain dirsDistributed architecture
bash
# Detect repo structure type
if [ -d "packages" ] || [ -d "apps" ]; then
    echo "MONOREPO detected"
elif [ -d "frontend" ] && [ -d "backend" ]; then
    echo "FULL-STACK MONOLITH detected"
elif [ -d "src" ] || [ -d "app" ]; then
    # Check if it's frontend or backend
    grep -q "react\|vue\|angular" package.json 2>/dev/null && echo "FRONTEND detected"
    grep -q "fastapi\|express\|django" package.json pyproject.toml 2>/dev/null && echo "BACKEND detected"
fi
1.4 Directory Mapping
bash
# Get directory structure (max 3 levels)
find . -type d -maxdepth 3 \
    -not -path "*/node_modules/*" \
    -not -path "*/.git/*" \
    -not -path "*/venv/*" \
    -not -path "*/__pycache__/*" \
    -not -path "*/dist/*" \
    -not -path "*/build/*" \
    2>/dev/null | head -50

# Identify key directories
for dir in src app lib core services api routes components pages hooks utils models; do
    [ -d "$dir" ] && echo "Found: $dir/"
done
1.5 Entry Points
bash
# Find main entry points
ls index.ts index.js main.ts main.py app.py server.ts server.js 2>/dev/null
cat package.json 2>/dev/null | grep -A1 '"main"'
cat pyproject.toml 2>/dev/null | grep -A1 'scripts'

Phase 2: Convention Detection

Identify and document existing patterns before making changes.

2.1 Code Style
bash
# Check for formatters
ls .prettierrc* .editorconfig .eslintrc* biome.json 2>/dev/null  # JS/TS
ls pyproject.toml | xargs grep -l "ruff\|black\|isort" 2>/dev/null  # Python

# Check indent style from existing files
head -20 src/**/*.ts 2>/dev/null | grep "^\s" | head -1  # tabs vs spaces
2.2 Testing Setup
bash
# JS/TS testing
grep -l "jest\|vitest\|mocha\|playwright" package.json 2>/dev/null
ls jest.config.* vitest.config.* playwright.config.* 2>/dev/null

# Python testing
grep -l "pytest\|unittest" pyproject.toml 2>/dev/null
ls pytest.ini conftest.py 2>/dev/null

# Test directories
ls -d tests/ test/ __tests__/ spec/ 2>/dev/null
2.3 CI/CD Setup
bash
# Check existing workflows
ls -la .github/workflows/ 2>/dev/null
ls .gitlab-ci.yml Jenkinsfile .circleci/ 2>/dev/null

# Check deploy configs
ls vercel.json render.yaml fly.toml railway.json Dockerfile 2>/dev/null
2.4 Documentation Style
bash
# Find README pattern
head -30 README.md 2>/dev/null

# Find existing docs
ls -la docs/ documentation/ wiki/ 2>/dev/null
ls CONTRIBUTING.md CHANGELOG.md 2>/dev/null

Phase 3: Guardrails Audit

Check what guardrails exist and what's missing.

3.1 Pre-commit Hooks Status
bash
# Check for hook managers
ls .husky/ 2>/dev/null && echo "Husky installed"
ls .pre-commit-config.yaml 2>/dev/null && echo "pre-commit framework installed"
ls .git/hooks/pre-commit 2>/dev/null && echo "Manual pre-commit hook exists"

# Check what hooks run
cat .husky/pre-commit 2>/dev/null
cat .pre-commit-config.yaml 2>/dev/null
3.2 Linting Status
bash
# JS/TS linting
grep -q "eslint" package.json && echo "ESLint configured"
grep -q "biome" package.json && echo "Biome configured"
ls .eslintrc* biome.json 2>/dev/null

# Python linting
grep -q "ruff" pyproject.toml && echo "Ruff configured"
grep -q "flake8" pyproject.toml setup.cfg && echo "Flake8 configured"
3.3 Type Checking Status
bash
# TypeScript
ls tsconfig.json 2>/dev/null && echo "TypeScript configured"
grep "strict" tsconfig.json 2>/dev/null

# Python type checking
grep -q "mypy" pyproject.toml && echo "mypy configured"
grep -q "pyright" pyproject.toml && echo "pyright configured"
ls py.typed 2>/dev/null
3.4 Commit Message Enforcement
bash
# commitlint
ls commitlint.config.* 2>/dev/null && echo "commitlint configured"
cat .husky/commit-msg 2>/dev/null
grep "conventional" package.json 2>/dev/null
3.5 Security Scanning
bash
# Check for security tools
grep -q "detect-secrets\|trufflehog" .pre-commit-config.yaml package.json 2>/dev/null
ls .github/workflows/*.yml | xargs grep -l "security\|audit" 2>/dev/null

Phase 4: Guardrails Setup

Only add missing guardrails. Never overwrite existing configurations.

4.1 JavaScript/TypeScript Projects
Husky + lint-staged (if not present)
bash
# Check if already installed
if [ ! -d ".husky" ]; then
    # Install Husky
    npm install -D husky lint-staged
    npx husky init

    # Create pre-commit hook
    echo 'npx lint-staged' > .husky/pre-commit
    chmod +x .husky/pre-commit
fi

lint-staged config (add to package.json if missing):

json
{
  "lint-staged": {
    "*.{ts,tsx,js,jsx}": [
      "eslint --fix",
      "prettier --write"
    ],
    "*.{json,md,yml,yaml}": [
      "prettier --write"
    ]
  }
}
ESLint (if not present)
bash
# Check if eslint exists
if ! grep -q "eslint" package.json; then
    npm install -D eslint @typescript-eslint/parser @typescript-eslint/eslint-plugin
fi

eslint.config.js (ESLint 9+ flat config):

javascript
import eslint from '@eslint/js'
import tseslint from 'typescript-eslint'

export default tseslint.config(
  eslint.configs.recommended,
  ...tseslint.configs.recommended,
  {
    rules: {
      '@typescript-eslint/no-unused-vars': ['error', { argsIgnorePattern: '^_' }],
      '@typescript-eslint/explicit-function-return-type': 'off',
      'no-console': ['warn', { allow: ['warn', 'error'] }]
    }
  },
  {
    ignores: ['dist/', 'node_modules/', 'coverage/']
  }
)
Prettier (if not present)
bash
if ! grep -q "prettier" package.json; then
    npm install -D prettier
fi

.prettierrc (respect existing style or use sensible defaults):

json
{
  "semi": false,
  "singleQuote": true,
  "trailingComma": "es5",
  "tabWidth": 2,
  "printWidth": 100
}
commitlint (if not present)
bash
if [ ! -f "commitlint.config.js" ]; then
    npm install -D @commitlint/cli @commitlint/config-conventional
    echo "npx commitlint --edit \$1" > .husky/commit-msg
    chmod +x .husky/commit-msg
fi

commitlint.config.js:

javascript
export default {
  extends: ['@commitlint/config-conventional'],
  rules: {
    'type-enum': [
      2,
      'always',
      ['feat', 'fix', 'docs', 'style', 'refactor', 'test', 'chore', 'ci', 'perf', 'revert']
    ],
    'subject-case': [2, 'always', 'lower-case'],
    'subject-max-length': [2, 'always', 72]
  }
}
4.2 Python Projects
pre-commit framework (if not present)
bash
# Install pre-commit
if [ ! -f ".pre-commit-config.yaml" ]; then
    pip install pre-commit
    pre-commit install
fi

.pre-commit-config.yaml:

yaml
repos:
  # Ruff - linting and formatting (replaces black, isort, flake8)
  - repo: https://github.com/astral-sh/ruff-pre-commit
    rev: v0.14.13
    hooks:
      - id: ruff
        args: [--fix, --exit-non-zero-on-fix]
      - id: ruff-format

  # Type checking
  - repo: https://github.com/pre-commit/mirrors-mypy
    rev: v1.16.0
    hooks:
      - id: mypy
        additional_dependencies: [types-requests]
        args: [--ignore-missing-imports]

  # Security
  - repo: https://github.com/Yelp/detect-secrets
    rev: v1.5.0
    hooks:
      - id: detect-secrets
        args: ['--baseline', '.secrets.baseline']

  # General
  - repo: https://github.com/pre-commit/pre-commit-hooks
    rev: v5.0.0
    hooks:
      - id: trailing-whitespace
      - id: end-of-file-fixer
      - id: check-yaml
      - id: check-added-large-files
      - id: check-merge-conflict

  # Commit messages
  - repo: https://github.com/compilerla/conventional-pre-commit
    rev: v4.0.0
    hooks:
      - id: conventional-pre-commit
        stages: [commit-msg]
pyproject.toml additions (if not present)
toml
[tool.ruff]
target-version = "py312"
line-length = 100

[tool.ruff.lint]
select = [
    "E",   # pycodestyle errors
    "F",   # pyflakes
    "I",   # isort
    "B",   # flake8-bugbear
    "UP",  # pyupgrade
    "S",   # flake8-bandit (security)
]
ignore = ["E501"]  # line length handled by formatter

[tool.mypy]
python_version = "3.12"
strict = true
ignore_missing_imports = true

[tool.pytest.ini_options]
testpaths = ["tests"]
addopts = "-v --cov=src --cov-report=term-missing --cov-fail-under=80"
4.3 Branch Protection (Document for User)

Recommend these GitHub branch protection rules:

markdown
## Recommended Branch Protection (main branch)

1. **Require pull request before merging**
   - Require 1 approval
   - Dismiss stale reviews on new commits

2. **Require status checks**
   - Lint
   - Type check
   - Tests
   - Security scan

3. **Require signed commits** (optional but recommended)

4. **Do not allow bypassing above settings**

Phase 5: Structure Preservation Rules

NEVER Do These
  • Don't reorganize directory structure - Work within existing patterns
  • Don't rename files for "consistency" - Match existing naming conventions
  • Don't add new patterns - Use patterns already in the codebase
  • Don't change import styles - Match existing (relative vs absolute, etc.)
  • Don't change formatting - Match existing style or use existing formatter config
  • Don't add new dependencies lightly - Check if equivalent exists
ALWAYS Do These
  • Read existing code first - Understand patterns before writing new code
  • Match existing conventions - Naming, structure, error handling
  • Use existing utilities - Don't reinvent what exists
  • Follow existing test patterns - Match test file naming and structure
  • Preserve existing configs - Only add, don't modify unless fixing bugs
Show full SKILL.md (217 more words)Show less
Convention Detection Checklist

Before writing any code, identify:

ConventionExampleWhere to Check
NamingcamelCase vs snake_caseExisting file names
File structurefeature/ vs type/Directory layout
Export styledefault vs namedExisting modules
Error handlingthrow vs return ErrorExisting functions
Loggingconsole vs loggerExisting code
Testingdescribe/it vs test()Existing tests
CommentsJSDoc vs inlineExisting code

Phase 6: Analysis Report Template

After running analysis, generate this report:

markdown
# Repository Analysis Report

## Overview
- **Repo Type**: [Monorepo | Full-Stack | Frontend | Backend | Microservices]
- **Primary Language**: [TypeScript | Python | ...]
- **Framework**: [React | FastAPI | ...]
- **Age**: [X commits, Y contributors]

## Directory Structure

[tree output]


## Tech Stack
| Category | Technology | Config File |
|----------|------------|-------------|
| Language | TypeScript | tsconfig.json |
| Framework | React | - |
| Testing | Vitest | vitest.config.ts |
| Linting | ESLint | eslint.config.js |
| Formatting | Prettier | .prettierrc |

## Guardrails Status

### Present
- [x] ESLint configured
- [x] Prettier configured
- [x] TypeScript strict mode

### Missing (Recommended)
- [ ] Pre-commit hooks (Husky + lint-staged)
- [ ] Commit message validation (commitlint)
- [ ] Security scanning in CI

## Conventions Detected
| Pattern | Observed | Example |
|---------|----------|---------|
| Naming | camelCase | `getUserById.ts` |
| Imports | Absolute | `@/components/Button` |
| Testing | Colocated | `Button.test.tsx` |
| Exports | Named | `export { Button }` |

## Recommendations
1. Add Husky + lint-staged for pre-commit hooks
2. Add commitlint for conventional commits
3. Add security workflow to GitHub Actions

## Files to Review First
- `src/index.ts` - Main entry point
- `src/utils/` - Shared utilities
- `tests/setup.ts` - Test configuration

Gradual Implementation Strategy

Don't add all guardrails at once. Follow this timeline:

WeekFocusWhy
1Formatting (Prettier/Ruff)Non-breaking, easy wins
2Linting (ESLint/Ruff)Catches obvious issues
3Pre-commit hooksAutomates week 1-2
4Commit message validationTeam consistency
5Type checking strictnessCatches runtime errors
6Security scanningCatches vulnerabilities

Working with Separate Repos

When frontend and backend are in separate repos:

Frontend Repo Setup
bash
# Clone and analyze
git clone [frontend-repo]
cd frontend

# Run analysis
# Expect: React/Vue/Angular, no backend code

# Add frontend-specific guardrails
# - Husky + lint-staged
# - ESLint + Prettier
# - Component testing (Vitest/Jest)
Backend Repo Setup
bash
# Clone and analyze
git clone [backend-repo]
cd backend

# Run analysis
# Expect: FastAPI/Express/Django, no frontend code

# Add backend-specific guardrails
# - pre-commit framework
# - Ruff + mypy
# - API testing (pytest/Jest)
Cross-Repo Coordination
ConcernSolution
Shared typesGenerate from OpenAPI spec
API contractsContract testing (Pact)
DeploymentsCoordinate via CI/CD triggers
VersioningSemantic versioning on both

Anti-Patterns

  • Adding unused guardrails - Only add what the team will use
  • Strict rules on day 1 - Introduce gradually
  • Blocking on warnings - Start permissive, tighten over time
  • Ignoring existing patterns - Work with what exists
  • Over-engineering - Simple rules > complex systems
  • Skipping the analysis phase - Always understand before changing

Quick Reference: Detection Commands

bash
# One-liner repo analysis
echo "=== Repo Type ===" && \
ls -d packages apps frontend backend 2>/dev/null || echo "Standard repo" && \
echo "=== Tech Stack ===" && \
ls *.json *.toml *.yaml 2>/dev/null && \
echo "=== Existing Guardrails ===" && \
ls .husky .pre-commit-config.yaml .eslintrc* 2>/dev/null || echo "None detected" && \
echo "=== Entry Points ===" && \
ls index.* main.* app.* server.* 2>/dev/null

© alinaqi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/existing-repo of alinaqi/maggy.

Open the folder on GitHubat commit 72a456e

Compare with similar skills

Existing Repo next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Existing Repo compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Existing Repo this skillalinaqi/maggy707—~4kAutomated safety check: NotesMIT
Figma Policy Guardrailsjeremylongshore/tons-of-skills-marketplace2.8k—~2kAutomated safety check: NotesMIT
Vercel Policy Guardrailsjeremylongshore/tons-of-skills-marketplace2.8k—~2.7kAutomated safety check: PassMIT
Shopify Policy Guardrailsjeremylongshore/tons-of-skills-marketplace2.8k—~1kAutomated safety check: NotesMIT
LobeHub Alint Rule Set Maintenancelobehub/lobehub83k—~1.9kAutomated safety check: PassCustom licence
Auto HarnessPacificStudio/openase268—~1.2kAutomated safety check: PassApache-2.0

Similar skills

  • Figma Policy Guardrails

    jeremylongshore/tons-of-skills-marketplace

    Enforce security policies and coding standards for Figma API integrations.

    2.8k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Vercel Policy Guardrails

    jeremylongshore/tons-of-skills-marketplace

    Implement lint rules, CI policy checks, and automated guardrails for Vercel projects.

    2.8k GitHub stars~2.7k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Shopify Policy Guardrails

    jeremylongshore/tons-of-skills-marketplace

    Implement Shopify app policy enforcement with ESLint rules for API key detection, query cost budgets, and App Store compliance checks.

    2.8k GitHub stars~1k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes
  • Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.

    83k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Auto Harness

    PacificStudio/openase

    Diagnose and strengthen a repository's harness layer: AGENTS.md rules, knowledge layout, architecture boundaries, lint and type gates, API and generated-client contracts, test scaffolding…

    268 GitHub stars~1.2k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Common Agent Guardrails

    HoangNguyen0403/agent-skills-standard

    Define deterministic guardrails for agent tool calls — protected paths, test-file locks during bug fixes, post-edit formatters, production approval gates, secret deny rules.

    572 GitHub stars~1k tokensUpdated yesterday
    DevelopmentAuto-check: notes

More from alinaqi/maggy

All 71 skills in this repo
  • Aeo Optimization

    alinaqi/maggy

    AI Engine Optimization - semantic triples, page templates, content clusters for AI citations

    707 GitHub stars~3.7k tokensUpdated 17 days ago
    Auto-check passed
  • Agent Teams

    alinaqi/maggy

    Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement

    707 GitHub stars~5k tokensUpdated 17 days ago
    Auto-check: notes
  • AI Models

    alinaqi/maggy

    Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate

    707 GitHub stars~4.1k tokensUpdated 17 days ago
    Auto-check passed
  • Android Java

    alinaqi/maggy

    Android Java development with MVVM, ViewBinding, and Espresso testing

    707 GitHub stars~3.9k tokensUpdated 17 days ago
    Auto-check: notes
  • Android Kotlin

    alinaqi/maggy

    Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing

    707 GitHub stars~3k tokensUpdated 17 days ago
    Auto-check passed
  • Autonomous Testing

    alinaqi/maggy

    AI-driven testing agent that auto-discovers, generates, executes, evaluates, and fixes tests for any project type

    707 GitHub stars~1.1k tokensUpdated 17 days ago
    Auto-check passed

Works with

Questions about Existing Repo

What does Existing Repo do?

Analyze existing repositories, maintain structure, setup guardrails and best practices. Existing Repo is an agent skill from alinaqi/maggy.

When should I use Existing Repo?

Existing Repo fits situations like: tasks that involve Linting and formatting; tasks that involve LLM guardrails.

How do I install Existing Repo in Claude Code?

Run `npx skills add alinaqi/maggy --skill existing-repo -a claude-code`. Or copy the skill folder (skills/existing-repo in alinaqi/maggy) into .claude/skills/existing-repo in your project. Claude Code loads it when a task matches its description.

How do I install Existing Repo in Codex?

Run `npx skills add alinaqi/maggy --skill existing-repo -a codex`. Or copy the skill folder (skills/existing-repo in alinaqi/maggy) into .agents/skills/existing-repo in your project. Codex loads it when a task matches its description.

Can I use Existing Repo in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alinaqi/maggy --skill existing-repo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/existing-repo, .gemini/skills/existing-repo, .github/skills/existing-repo and .opencode/skills/existing-repo in your project.

What does Existing Repo need to run?

Going by SKILL.md and its folder, Existing Repo needs the command-line tools its instructions call (git, npm, npx, pip, vitest and eslint). Our summary lists: Python 3; Node.js. Its frontmatter pre-approves these tools: Read, Glob, Grep, Bash.

Does Existing Repo access the network?

SKILL.md names 4 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: typicode.github.io, pre-commit.com and commitlint.js.org. This is read from the text; nothing was executed.

Is Existing Repo safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Existing Repo use?

Existing Repo is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Existing Repo use?

About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Existing Repo?

Skills that share tags, products or a category with Existing Repo: Figma Policy Guardrails (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Vercel Policy Guardrails (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Shopify Policy Guardrails (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and LobeHub Alint Rule Set Maintenance (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Existing Repo?

alinaqi (a GitHub user) maintains it in alinaqi/maggy, which has 707 GitHub stars. The repository holds 71 skills in this directory. The repository was last updated on September 24, 2026.

Source: alinaqi/maggy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.