/ Annuaire / Playground / ai-first-toolkit
← Tous les serveurs ↗ GitHub
● Communauté techwolf-ai ⚡ Instantané

ai-first-toolkit

par techwolf-ai · techwolf-ai/ai-first-toolkit

A skills pack that audits, re-engineers, and bootstraps projects following AI-first design principles.

ai-first-toolkit is a multi-skill bundle for Claude Code and Codex that looks at your project through an AI-first lens: is the codebase easy for an agent to navigate, edit, and reason about? It includes skills for AI-readiness audits, refactoring toward clear structure, and bootstrapping new projects with the right scaffolding from day one.

▶ Voir la démo 📦 Installer 💡 Cas d'usage

Pourquoi l'utiliser

Fonctionnalités clés

Démo en direct

Aperçu en pratique

ai-first-toolkit-skill.replay ▶ prêt
0/0

Installation

Dépôt de l’auteur · Documentation officielle des Skills Claude

Cas d'usage

Usages concrets : ai-first-toolkit

How to audit a codebase for AI-agent readiness

👤 Tech leads preparing a codebase for heavy AI-assisted work ⏱ ~45 min intermediate

Quand l'utiliser : Before the team commits to doing a lot of feature work through Claude or Codex.

Déroulement
  1. Run the audit
    Audit this repo for AI-agent readiness. Score each dimension and list the top 5 friction points.✓ Copié
    → Dimension scores + specific files to fix
  2. Prioritize fixes
    Which of those fixes would give the biggest agent-effectiveness lift per hour of work?✓ Copié
    → Ranked list with effort/impact
  3. Apply the top fix
    Apply fix #1 end-to-end — edit files, update docs, add tests.✓ Copié
    → Diff + confirmation

Résultat : A concrete improvement plan and at least one applied fix making the repo friendlier to AI agents.

Pièges
  • Audit turns into a generic 'improve docs' blob — Ask for file:line level findings, not abstract advice
Combiner avec : filesystem · github

Bootstrap a new AI-friendly project

👤 Founders or ICs starting a new repo ⏱ ~30 min beginner

Quand l'utiliser : Day zero of a new project, before you pick bad defaults that will haunt you.

Déroulement
  1. State the project
    Bootstrap a new TypeScript API project using ai-first-toolkit defaults. Purpose: internal billing API.✓ Copié
    → Proposed folder structure, tsconfig, scripts, README skeleton
  2. Scaffold the files
    Create the files. Include AGENTS.md and CLAUDE.md with the relevant codebase notes.✓ Copié
    → Repo files materialized
  3. First commit
    Initialize git and make the first commit with a clean message.✓ Copié
    → Clean initial repo

Résultat : A new repo that's friendly to both humans and AI agents from commit 0.

Pièges
  • Scaffolding imports dependencies you don't want — Ask Claude to list dependencies before installing — accept each one
Combiner avec : github · filesystem

Re-engineer a messy module for AI readability

👤 Engineers paying down tech debt one module at a time ⏱ ~60 min advanced

Quand l'utiliser : You've isolated a module that Claude keeps getting wrong — usually a sign its structure isn't agent-legible.

Déroulement
  1. Diagnose the module
    Look at src/billing/. What about this code makes it hard for an agent to edit safely?✓ Copié
    → Specific red flags: indirection, hidden state, long functions
  2. Plan the refactor
    Propose a 3-step refactor that improves agent-legibility without changing public API.✓ Copié
    → Stepwise plan with diff sketches
  3. Execute step 1
    Apply step 1. Keep tests green.✓ Copié
    → PR-sized diff

Résultat : A module that Claude can actually reason about on the next iteration.

Pièges
  • Over-refactor and break behaviors you didn't mean to — Insist on public API stability and run tests after each step
Combiner avec : filesystem · github

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

ai-first-toolkit-skill + filesystem

Audit scans the repo; filesystem is needed to actually read it

Walk the repo and score AI-readiness; report findings file-by-file.✓ Copié
ai-first-toolkit-skill + github

Open a PR with the proposed AGENTS.md / CLAUDE.md additions

Apply the audit's top 3 fixes and open a PR titled 'AI-first improvements'.✓ Copié

Outils

Ce que ce MCP expose

OutilEntréesQuand appelerCoût
ai-readiness-audit repo root Pre-investment in AI-heavy workflows 0
ai-first-bootstrap project spec (lang, purpose, stack) Greenfield projects 0
re-engineer-module module path + goals When a module resists agent edits 0

Coût et limites

Coût d'exécution

Quota d'API
none beyond your LLM provider
Tokens par appel
5–20k for an audit of a medium repo
Monétaire
free, open source
Astuce
Scope audits to a subtree rather than the whole monorepo

Sécurité

Permissions, secrets, portée

Stockage des identifiants : none
Sortie de données : none beyond what filesystem/github tools do

Dépannage

Erreurs courantes et correctifs

Audit is too abstract

Re-prompt with a concrete dimension: 'evaluate just the test layout' or 'just the module boundaries'.

Bootstrap picks wrong language

Always state language+runtime+build tool in the first prompt.

Alternatives

ai-first-toolkit vs autres

AlternativeQuand l'utiliserCompromis
init (built-in)You just need a CLAUDE.md and don't care about the restNarrower scope
antivibe-skillYou want the opposite lens — critique of AI-shaped sludgeDiagnostic, not prescriptive

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills