project-spec
Create a project spec for AI agents to work from autonomously.
Best use case
project-spec is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Create a project spec for AI agents to work from autonomously.
Teams using project-spec should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/project-spec/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How project-spec Compares
| Feature / Agent | project-spec | 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?
Create a project spec for AI agents to work from autonomously.
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
# Project Spec What to build, how it fits together, how to keep going. ## Process 1. **Explore**: Check context—files, docs, commits, patterns. 2. **Ask**: Ask many questions (multiple choice when possible) until you can fill every section. 3. **Approaches**: If multiple valid paths exist, present 2-3 options. Lead with your recommendation. 4. **Derive**: Map conversation to spec sections: - Mission: what, who, why - Architecture: technical decisions - Components: what exists - Constraints: non-negotiables - Priorities: current focus - Standards: quality bar 5. **Write**: Output `PLAN.md` with spec and progress in one file. ## Spec Structure (under 100 lines) **Instructions**: - Read Progress section to know what's done, check git log for context - Build the next item from Priorities—do not ask what to work on - Make decisions from existing code patterns - Commit at natural breakpoints (test passing, working feature, integration complete) - Update Progress section after each commit, continue to next item - When priorities clear, surface new work - PLAN.md is a living document—update as work evolves - No clarifying questions—ship working features **Mission**: 1-3 lines. What, who, why. **Architecture**: Technical decisions stated, not debated. **Components**: What exists. One line each—name and essence. **Constraints**: Non-negotiables only. **Priorities**: Current focus. Replenishes. **Standards**: Quality bar. Improve over time. **Progress**: What's done, what's current, what's next. Update after each commit. ## Writing Principles **Concrete, not vague** - "CLI tool for rotating AWS credentials" not "developer utility" - "Postgres, Redis, S3" not "appropriate storage solutions" **No filler** - Cut: "Prefer working software over perfection", "Start simple", "Future integrations"
Related Skills
prospect-investigation
Research and investigate business prospects and leads. Gathers company information, contact details, and qualification data for sales.
project-orchestrator
Master coordinator for complete project setup from ideation to ready-to-code. Manages workflow through ideation, research, tech stack selection, documentation, and project initialization to deliver working projects in minutes.
project-domain
Capture subject matter expertise and domain knowledge that will inform all product decisions - the ubiquitous language, domain rules, and principles from the field
project-bootstrap
Bootstrap a new or existing project with stack detection and project.json generation. Use when adding a new project, setting up agent system, or generating project manifest. Triggers on: add project, new project, bootstrap project, setup project, detect stack.
magento-php-specialist
Advanced PHP development for Magento 2 following PSR-12 and Magento coding standards. Use when writing PHP code, implementing business logic, or ensuring code quality. Masters modern PHP features, object-oriented programming, design patterns, and Magento-specific PHP practices.
jekyll-specialist
Manages the samueltauil.github.io Jekyll site. Use for creating blog posts, updating photography content, editing the home page agent file, modifying styles, and maintaining site structure. Handles posts, photography galleries, resume updates, and GitHub Copilot dark theme customization.
ck:project-management
Track progress, update plan statuses, manage Claude Tasks, generate reports, coordinate docs updates. Use for project oversight, status checks, plan completion, task hydration, cross-session continuity.
awesome-copilot-root-typespec-create-agent
Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot Use when: the task directly matches typespec create agent responsibilities within plugin awesome-copilot-root. Do not use when: a more specific framework or task-focused skill is clearly a better match.
audit-and-add-project-skills
Audits project skills in .agent/skills/ and Codex skills for Cursor compatibility, then helps add compatible skills to .cursor/skills/. Use when the user wants to migrate project skills to Cursor, check if skills work with Cursor, or add existing skills to Cursor.
agent-project-manager
Expert project manager specializing in project planning, execution, and delivery. Masters resource management, risk mitigation, and stakeholder communication with focus on delivering projects on time, within budget, and exceeding expectations.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-file-specs
Contains the complete specifications for AI coding assistant customization files including agents, skills, prompts, and instructions. Works with GitHub Copilot, Claude Code, Codex, OpenCode, and other providers. Use this skill when you need to reference the correct file format, required fields, supported attributes, file locations, or VS Code settings for any customization file. Follows the Agent Skills open standard (agentskills.io).