By wilddeer
Work on projects through well-defined specs. Spec-first approach with no ambiguity.
Research, discuss, and write specs. Use this when creating or refining specs.
Execute specs literally with zero creativity. Use this when following an existing spec.
You MUST use this EVERY time you are executing a single step from a spec.
You MUST use this to review implementation against spec before marking complete.
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Skills and subagents for spec-driven development. Spec-first approach: research, define, execute. No ambiguity, no guessing.
The problem: Agents lose context between sessions. They jump to execution without discussion, make unexpected changes, forget decisions, repeat work.
The solution: Specs as persistent memory. Every task gets a spec committed to version control — agents can pick up exactly where they left off.
How it works:
research.mdspec.mdprogress.md, gaps flagged and filledSpecs live in your repo and get committed. They survive sessions, editors, and model changes.
Core principles:
| Type | Name | Description |
|---|---|---|
| Skill | spec-development | Research, discuss, and write specs |
| Skill | spec-execution | Execute specs literally, track progress |
| Skill | spec-step-execution | Execute a single step from a spec |
| Skill | spec-step-review | Review implementation against spec |
| Agent | spec-step-executor | Subagent for executing individual spec steps |
| Agent | spec-step-reviewer | Subagent for reviewing implementation against spec |
Skills are usually automatically exposed as commands (/spec-development, /spec-execution).
npx skills add wilddeer/specops
See skills.sh for details.
Windows (PowerShell):
irm https://raw.githubusercontent.com/wilddeer/specops/v4.1.0/install.ps1 | iex
macOS/Linux:
curl -fsSL https://raw.githubusercontent.com/wilddeer/specops/v4.1.0/install.sh | bash
This installs skills to ~/.cursor/skills/specops/ and agents to ~/.cursor/agents/.
To uninstall, remove ~/.cursor/skills/specops/ and ~/.cursor/agents/spec-step-executor.md.
# Add marketplace
/plugin marketplace add wilddeer/specops
# Install the plugin
/plugin install specops@wilddeer-specops
Inspired by Superpowers by Jesse Vincent.
MIT
npx claudepluginhub wilddeer/agents --plugin specopsSkills-first specification-driven development framework with 7 agent skills for planning, implementation, review, and shipping. Natural language activation with intelligent agent orchestration. Includes /plan, /implement, /research commands plus managing-specifications, implementing-features, and reviewing-and-shipping skills.
Specification-Driven Development with Process Discipline for Claude Code
GitHub Spec-Kit integration for constitution-based spec-driven development (7-phase workflow)
Spec-driven development with task-by-task execution. Research, requirements, design, tasks, autonomous implementation, and epic triage for multi-spec feature decomposition.
Specification-driven development workflow: specify → plan → tasks → implement
GitHub Spec-Kit integration for Specification-Driven Development - define WHAT and HOW before coding