speckit-install
Install the Specify CLI on the host machine (uv tool install or uvx one-time); supports multiple OS, persistent or one-time install, and corporate or restricted-network environments. Use when the user says "install Spec Kit", "install Specify CLI", or "specify command not found".
Best use case
speckit-install is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Install the Specify CLI on the host machine (uv tool install or uvx one-time); supports multiple OS, persistent or one-time install, and corporate or restricted-network environments. Use when the user says "install Spec Kit", "install Specify CLI", or "specify command not found".
Install the Specify CLI on the host machine (uv tool install or uvx one-time); supports multiple OS, persistent or one-time install, and corporate or restricted-network environments. Use when the user says "install Spec Kit", "install Specify CLI", or "specify command not found".
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "speckit-install" skill to help with this workflow task. Context: Install the Specify CLI on the host machine (uv tool install or uvx one-time); supports multiple OS, persistent or one-time install, and corporate or restricted-network environments. Use when the user says "install Spec Kit", "install Specify CLI", or "specify command not found".
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/speckit-install/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How speckit-install Compares
| Feature / Agent | speckit-install | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Install the Specify CLI on the host machine (uv tool install or uvx one-time); supports multiple OS, persistent or one-time install, and corporate or restricted-network environments. Use when the user says "install Spec Kit", "install Specify CLI", or "specify command not found".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Spec Kit Install Skill
Install the [Specify CLI](https://github.com/github/spec-kit) so that `specify` is available in PATH (or use one-time `uvx`). This skill covers only **installing the CLI**; it does not run `specify init`. For project initialization after install, use **speckit-initial**.
## When to Use
- First-time Spec Kit setup ("install Spec Kit", "install Specify CLI").
- CI or scripts that need to pre-install the CLI.
- Upgrading the CLI (`uv tool install --force`).
- User reports "specify command not found" or "specify: command not found".
## Prerequisites
- **uv**: [Astral uv](https://docs.astral.sh/uv/) for installing the CLI. If uv is not installed, guide the user to install it first (e.g. `curl -LsSf https://astral.sh/uv/install.sh | sh` on Linux/macOS, or see uv docs for Windows).
- **Python 3.11+** when using uv (uv typically bundles or uses system Python).
- **Git** (optional for install; required later for `specify init` with git).
## Workflow
1. **Check if already installed**
- Suggest running `specify --version` or `specify check`. If the command succeeds, the CLI is already installed; suggest **speckit-initial** for project init or **speckit-check** for environment verification.
2. **Persistent install (recommended)**
- Run: `uv tool install specify-cli --from git+https://github.com/github/spec-kit.git`
- This makes `specify` available in PATH for all projects.
- **Upgrade**: `uv tool install specify-cli --force --from git+https://github.com/github/spec-kit.git`
3. **One-time usage (no PATH install)**
- Run: `uvx --from git+https://github.com/github/spec-kit.git specify init <project_name_or_.> --ai <agent>`
- Use when the user does not want to install the tool permanently (e.g. quick try, CI one-off). Document that subsequent `specify init` or `specify check` in the same session can reuse the same `uvx` prefix or require re-running with full `uvx --from ...` if not installed.
4. **Corporate or restricted network**
- Set `GH_TOKEN` or `GITHUB_TOKEN` for GitHub API access if needed.
- For `specify init` (handled in **speckit-initial**): `--github-token <token>` or env var. For install, uv may need network access to clone the repo; if TLS issues occur, document that uv/spec-kit may support `--skip-tls` or similar only where explicitly documented (avoid recommending insecure options unless user is in a controlled environment).
## Outputs
- **Persistent install**: `specify` is available in PATH; user can run `specify init`, `specify check` in any directory.
- **One-time**: No change to PATH; user runs `uvx --from git+https://github.com/github/spec-kit.git specify ...` for each use.
## Next Steps
- After install: use **speckit-initial** to run `specify init` in a project, or **speckit-check** to verify the environment.
## Different Environments
| Environment | Notes |
|-------------|--------|
| **Linux** | Install uv if needed; then `uv tool install specify-cli --from git+https://github.com/github/spec-kit.git`. WSL: same as Linux. |
| **macOS** | Same as Linux; ensure Python 3.11+ available for uv if required. |
| **Windows** | Install uv (see uv docs); use PowerShell or cmd. For project init, **speckit-initial** will use `--script ps` when needed. |
| **Corporate / proxy** | Use GH_TOKEN/GITHUB_TOKEN if GitHub API is restricted; ensure uv can reach GitHub. |
| **CI** | Prefer persistent install in a cacheable step: `uv tool install specify-cli --from git+https://github.com/github/spec-kit.git`; then run `specify init` or `specify check` in the same runner. |
## Troubleshooting
- **uv not found**: Direct user to install [uv](https://docs.astral.sh/uv/).
- **Python version**: uv usually manages Python; if errors mention Python, ensure 3.11+ is available.
- **Network / SSL**: Check firewall, proxy, and GitHub access; avoid disabling TLS unless necessary and documented.
- **Permission errors**: On Linux/macOS, user install with uv typically does not need sudo; if using system Python, consider user-level uv install.
## References
- [GitHub spec-kit](https://github.com/github/spec-kit) — Get Started: Install Specify CLI
- [uv documentation](https://docs.astral.sh/uv/)Related Skills
skill-installer
Discovers, installs, and manages AI skills from the PartMe marketplace. Acts as the local package manager for Knowledge-as-a-Service (KaaS) and Tool-as-a-Service (TaaS) skills. Use when the user wants to search for available skills, install a new skill into their environment, or list currently installed skills.
tui-install
Generate and render a pixel-precise ASCII TUI Install Guide component with complete output blocks (TUI_RENDER, COMPONENT_SPEC, PENCIL_SPEC, PENCIL_BATCH_DESIGN) for Pencil MCP drawing workflows. Use when the user asks to create an install in a terminal UI, text-based interface, or Pencil MCP project.
speckit-taskstoissues
Convert tasks.md entries into GitHub issues in the matching remote repository using gh issue create, preserving task IDs for traceability. Use when the user wants to create GitHub issues from an existing tasks.md, needs issue tracking for implementation tasks, or wants to sync task progress with GitHub project boards.
speckit-tasks
Generate a dependency-ordered tasks.md organized by user story, with phased execution (Setup, Foundational, User Stories, Polish), parallel markers, and strict checklist format (checkbox, TaskID, Story label, file path). Use when the implementation plan is ready and the user needs an executable task breakdown before coding.
speckit-specify
Create or update a feature specification from a natural language description by generating a branch, filling the spec template with user stories, functional requirements, success criteria, and running quality validation. Use when the user provides a feature idea and needs a structured, technology-agnostic spec ready for planning.
speckit-plan
Generate a technical implementation plan from a feature spec by filling the plan template, resolving unknowns via research, producing data-model.md, API contracts, and quickstart.md artifacts. Use when the feature spec is ready and the user needs architecture decisions, data models, API schemas, or a structured plan before task generation.
speckit-initial
Run `specify init` in the current or target directory to bootstrap a Spec Kit project (pull .specify/ and slash commands); supports multiple AI agents and --script sh/ps. Use when the user says "initialize Spec Kit project", "specify init", or "set up Spec Kit in this repo".
speckit-implement
Execute the implementation plan by processing tasks from tasks.md phase-by-phase, following TDD order, respecting task dependencies and parallel markers, setting up ignore files, and marking completed tasks. Use when the plan and tasks are ready and the user wants to begin coding, or when resuming implementation after a pause.
speckit-constitution
Create or update the project constitution at .specify/memory/constitution.md by collecting governance principles, filling template placeholders, versioning with semver, and propagating changes to dependent templates and agent config files. Use when setting up initial project governance, amending principles, or syncing constitution changes across spec/plan/tasks templates.
speckit-clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
speckit-checklist
Generate a requirements-quality checklist ('unit tests for English') that validates completeness, clarity, consistency, and measurability of spec/plan/tasks artifacts. Use when the user needs a quality gate before implementation, wants to audit requirement coverage, or needs domain-specific checklists (UX, API, security, performance).
speckit-analyze
Perform a read-only cross-artifact consistency analysis across spec.md, plan.md, and tasks.md, detecting duplications, ambiguities, coverage gaps, and constitution violations with severity ratings. Use when the user has all three artifacts and needs a quality check before implementation, or wants to identify inconsistencies across specifications.