// devtools · shadcn/improve

improve

improve est un projet de développement open source, créé par shadcn (shadcn/improve sur GitHub). Il compte 11 400 étoiles sur GitHub et 460 forks, il est publié sous la licence MIT et a été mis à jour pour la dernière fois sur GitHub le 12 septembre 2026.

The audit skill from shadcn — your best model audits the codebase, cheaper models execute the plans, MIT

★ 11,4 k étoiles⑂ 460 forksMITmis à jour sept. 2026
▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
// détails du projet

Détails du projet

Étoiles GitHub
11 400
Forks
460
Licence
MIT
Dernière mise à jour sur GitHub
12 septembre 2026
Catégorie
Développement
Type de fiche
Guide d'installation complet
// fonctionnement

Comment ça marche

  1. Install the skill

    Add it with the Skills CLI — it works in any agent that supports the Agent Skills format.

  2. Run the audit

    Open your agent in the repo and run /improve for the full audit, or /improve quick for a cheap pass.

  3. Pick what gets planned

    Reply with the findings you want — plans land in plans/, one file each, with an index and priority order.

  4. Hand a plan to a cheaper agent

    Any agent or human can execute a plan, or let the skill dispatch one and review the work.

// fonctionnalités

Pourquoi on l'adore

Nine-category audit

Correctness, security, performance, test coverage, tech debt, dependencies, DX, docs and direction — each finding with file:line evidence.

Self-vetting

The advisor re-reads every cited location itself, so false positives get dropped before you see them.

Executable plans

Self-contained specs with exact paths, code excerpts, verified commands and machine-checkable done criteria.

Cheap execution loop

execute runs a cheaper model in an isolated worktree and reviews the diff; reconcile refreshes the backlog.

Never touches your code

The skill only writes to plans/ and never runs commands that mutate your working tree.

// lancez-le

Lancez-le vous-même

  1. Step 1 — Install the skill

    Add improve with the Skills CLI.

    npx skills add shadcn/improve
  2. Step 2 — Run the audit

    Full audit with prioritised findings, or quick for hotspots only.

    /improve
  3. Step 3 — Execute a plan

    Dispatch a cheaper executor for a plan and get a verdict back.

    /improve execute 001
// cas d'usage

Ce que vous pouvez créer

  • Audit a codebase before a release or handover
  • Turn tech debt into priced, ordered plans
  • Let a cheap model implement while the best model advises
  • Review only what changed on a branch with /improve branch

Two more from the same shelf: Security Audit Skill — Cloudflare's security-audit skill, and Codex Security — OpenAI's security scanner for Codex. Browse every Dev Tools tool in the catalogue to compare the category.

// faq

Questions fréquentes

What is improve?

An agent skill that audits a codebase and writes self-contained implementation plans for other agents (or humans) to execute.

Does it change my code?

No — it only writes to plans/. Execution happens in isolated worktrees, and merging stays your decision.

Which agents does it work with?

Any agent that supports the Agent Skills format; plans are plain Markdown, so anyone can pick them up.

How is it different from a linter?

It judges what is worth doing, not just what is wrong — findings are prioritised by leverage (impact ÷ effort, weighted by confidence).

Is it free?

Yes — MIT.

// continuez l'exploration

Outils similaires

Agents IA

Security Audit Skill

Cloudflare's security-audit skill — turns your coding agent into a multi-phase auditor with independently verified findings, MIT

★ 67,6 k étoilesMIT
Voir le guide →
Développement

Codex Security

OpenAI's security scanner for Codex — find, validate and patch vulnerabilities from the CLI, SDK or GitHub Action, Apache-2.0

★ 12,2 k étoilesApache-2.0
Voir le guide →
Développement

OpenCode

The open source coding agent

★ 211,6 k étoilesMIT
Voir le guide →
Développement

claudex-loop

Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan …

★ 2,7 k étoilesUnknown
Voir le guide →
Développement

LM Evaluation Harness

LM Evaluation Harness — EleutherAI framework for few-shot evaluation of language models across many tasks, MIT

★ 14,4 k étoilesMIT
Voir le guide →
Développement

Portkey AI Gateway

Portkey AI Gateway — route to 1,600+ AI models through one fast API, with fallbacks and guardrails, MIT

★ 13,3 k étoilesMIT
Voir le guide →
// alternatives

Alternatives en Développement

Les autres projets de la catégorie Développement avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si improve ne vous convient pas.

  • OpenCode★ 211,6 k

    The open source coding agent

  • Transformers★ 166,9 k

    The model-definition framework behind modern AI — thousands of pretrained transformers for text, vision, and audio.

  • claude-code★ 149,7 k

    Anthropic's agentic coding tool that lives in your terminal and works across your whole codebase

  • cc-switch★ 141,3 k

    Cross-platform desktop all-in-one manager for Claude Code, Codex, OpenCode and other coding agents

  • codex★ 128,2 k

    OpenAI's lightweight coding agent that runs locally in your terminal

// plus en devtools

Plus en Développement

Projets de la catégorie Développement proches dans le catalogue, les plus proches en étoiles de improve — continuez à explorer de part et d'autre.

  • fastapi_mcp★ 12,0 k

    Expose your FastAPI endpoints as Model Context Protocol tools - with authentication - in a few lines of code.

  • artemis★ 10,9 k

    ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly wit…

  • Codex Security★ 12,2 k

    OpenAI's security scanner for Codex — find, validate and patch vulnerabilities from the CLI, SDK or GitHub Action, Apache-2.0

  • aichat★ 10,5 k

    One Rust CLI for every LLM: shell assistant, chat REPL, RAG, tools and agents across 20+ providers.

  • claude-context★ 12,6 k

    Code-search MCP for Claude Code: make your entire codebase the context for any coding agent.

  • Graft★ 9,8 k

    A codebase knowledge graph that makes Claude Code, Cursor, Codex and Gemini faster, cheaper and repo-aware.

Obtenir improve

Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.