SkillFoxx

Type a name, a task or a service

Spec Kit

GitHub toolkit for spec-driven development: the specify CLI adds agent commands and skills to a project, from principles to implementation

CLIEditors’ pickMedium risk

github/spec-kitAuthor: GitHub

Install

uv tool install specify-cli

Install from PyPI. For a specific release: uv tool install specify-cli --from git+https://github.com/github/spec-kit.git@vX.Y.Z

This is third-party code. Review the repository files before installing.

What it does

The specify CLI sets up templates and commands for the chosen agent in a project. Work then goes step by step: /speckit.constitution records project principles, /speckit.specify describes what to build, /speckit.plan picks stack and architecture, /speckit.tasks breaks the plan into tasks, /speckit.implement executes them, and /speckit-converge checks the result against the spec. Extensions add separate processes such as bug assessment and fixing or idea evaluation. For agents with skills support the commands can be installed as skills.

Who it is for. For teams and developers who want the agent to code from an agreed spec rather than a one-off prompt.

Good fit when

  • You start a feature and want requirements and a plan first
  • You need a repeatable agent workflow for the whole team
  • You want bug fixes with a validated diagnosis and a test afterwards

Not a fit when

  • A tiny edit where a spec is overkill
  • You cannot add service files and templates to the repository

Example request

/speckit.specify An app that organizes photos into albums grouped by date with drag and drop

Limitations

Requires uv to install the CLI. The process adds many artifacts to the project: specs, plans, tasks. Output quality depends on the agent and model you use. Community extensions come from third parties and should be reviewed before installing.

How to disable. Remove the CLI with uv tool uninstall specify-cli and delete the template and command folders it created in the project.

Security check

  • Creates files and commands in the repository
  • The implement command lets the agent write code from the plan

README in short

The README explains spec-driven development and gives three quickstarts: the core flow, bug fixing and idea assessment. CLI install is covered from git by release tag or from PyPI, with non-interactive flags for CI. It lists core commands, extensions, presets and role bundles, plus links to community resources on the docs site.

FAQ

Which agents does it support?

The README cites over 30 integrations including GitHub Copilot, Claude Code and Codex. specify integration list shows them all.

How do I update the CLI?

Run specify self upgrade; specify self check only reports whether a newer version exists.

Editors’ pick

A skills library that gives coding agents a development process: brainstorming, planning, TDD, subagents and code review

PluginMedium risk286.6K
Editors’ pick

Small composable skills for engineering with agents: plan grilling, TDD, bug diagnosis, code review and architecture

SkillLow risk262K

Reference MCP servers

Model Context Protocol servers

Editors’ pick

Official reference MCP servers: Filesystem, Fetch, Git, Memory, Sequential Thinking, Time and Everything

MCP serverMedium risk90.3K
Editors’ pick

Up-to-date, version-specific library docs and code examples in your agent's context, via MCP or a CLI plus skill

MCP serverMedium risk62K