Agent skill
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".
Install this agent skill to your Project
npx add-skill https://github.com/partme-ai/full-stack-skills/tree/main/skills/speckit-skills/speckit-initial
SKILL.md
Spec Kit Initial Skill
Run specify init to initialize a Spec Kit project: pull .specify/ (memory, scripts, templates, specs) and register /speckit.* slash commands with the chosen AI Agent. This skill assumes the Specify CLI is already installed; if not, direct the user to speckit-install first.
When to Use
- First time enabling Spec Kit in a project ("initialize Spec Kit", "set up Spec Kit here").
- Switching AI Agent (e.g. from Claude to Cursor or Gemini).
- Initializing in a new or existing directory.
- Need PowerShell scripts on Windows (
--script ps).
Prerequisites
- Specify CLI installed (see speckit-install). If
specifyis not in PATH, guide the user to run speckit-install before proceeding. - Git (optional; use
--no-gitif the project is not a git repo or you want to skip git-related setup).
Workflow
-
Verify CLI
- If the user reports "specify command not found" or has not installed the CLI, direct them to speckit-install first. Otherwise proceed.
-
Choose parameters
- --ai (required for slash commands):
claude|cursor-agent|gemini|copilot|windsurf|qwen|opencode|codex|qoder|amp|shai|bob|kilocode|auggie|roo|codebuddy— pick the agent the user will use in this project. - --script:
sh(default, Bash) orps(PowerShell). Usepson Windows when the user needs PowerShell scripts. - Target:
specify init .orspecify init --herefor current directory; orspecify init <project_name>for a new subdirectory. - --force: Overwrite existing
.specify/if present (use with care). - --no-git: Skip git-related setup.
- --ignore-agent-tools: Do not install or check agent-specific tools; only pull templates and
.specify/structure. - --github-token or
GITHUB_TOKEN: For private repos or rate-limited access.
- --ai (required for slash commands):
-
Run the command
- Give a concrete command for the user's OS and chosen agent. Examples:
- Current dir, Cursor:
specify init . --ai cursor-agent - Current dir, Claude:
specify init . --ai claude - Windows, Copilot, PowerShell scripts:
specify init . --ai copilot --script ps - New subdir:
specify init my-app --ai gemini
- Current dir, Cursor:
- Give a concrete command for the user's OS and chosen agent. Examples:
-
Confirm outputs
- After success: project contains
.specify/(memory, scripts, templates, specs) and the Agent has/speckit.*slash commands available.
- After success: project contains
Outputs
- Project:
.specify/directory with memory, scripts, templates, and specs. - Agent: Slash commands (e.g.
/speckit.constitution,/speckit.specify,/speckit.plan) available in the chosen AI Agent.
Next Steps
- Run speckit-check to verify the environment (optional but recommended).
- Then use speckit-constitution or speckit-specify to start the Spec Kit workflow.
Different Environments
| Environment | Example |
|---|---|
| Linux / macOS, Cursor | specify init . --ai cursor-agent |
| Linux / macOS, Claude | specify init . --ai claude |
| Windows, Copilot, PowerShell | specify init . --ai copilot --script ps |
| New subdirectory | specify init my-project --ai gemini |
| Overwrite existing .specify | specify init . --ai claude --force |
| No git | specify init . --ai claude --no-git |
| Templates only (no agent tools) | specify init . --ai claude --ignore-agent-tools |
Troubleshooting
- "specify: command not found": Use speckit-install first.
- Windows slash commands not appearing: Ensure you used
--script psif the agent expects PowerShell, and that the agent is configured to load commands from the project. - Private repo / rate limit: Set
GITHUB_TOKENor pass--github-token <token>as documented by spec-kit.
References
- GitHub spec-kit — Get Started: Initialize your project
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ocrmypdf-batch
OCRmyPDF batch processing skill — process multiple PDFs, Docker automation, shell scripting, and CI/CD integration. Use when the user needs to OCR many PDFs, set up automated OCR pipelines, or integrate OCR into workflows.
ocrmypdf-optimize
OCRmyPDF optimization skill — compress PDFs, configure PDF/A output, JBIG2 encoding, and lossless optimization. Use when the user needs to reduce PDF file size, create archival PDF/A files, or optimize OCR output.
ocrmypdf-image
OCRmyPDF image processing skill — deskew, rotate, clean, despeckle, remove border from scanned documents. Use when the user needs to improve scanned PDF quality, fix skewed pages, remove noise, or clean up scanned documents before OCR.
ocrmypdf-api
OCRmyPDF Python API and plugin skill — use OCRmyPDF programmatically from Python, integrate with applications, and extend with plugins (EasyOCR, PaddleOCR, AppleOCR). Use when the user needs to call OCRmyPDF from Python code, build OCR pipelines, or use alternative OCR engines.
ocrmypdf
OCRmyPDF core skill — add searchable OCR text layer to scanned PDFs, convert images to searchable PDFs, support 100+ languages via Tesseract. Use when the user needs to OCR a PDF, make a scanned PDF searchable, or extract text from scanned documents.
svelte
Guides Svelte and SvelteKit development including reactive components, stores, transitions, lifecycle hooks, SSR, file-based routing, and deployment. Use when the user needs to build Svelte components, create SvelteKit applications, implement reactivity patterns, or configure Svelte with Vite.
Didn't find tool you were looking for?