Skillget

speq-skill

agent
Security Audit
Fail
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 27 GitHub stars
Code Fail
  • rm -rf — Recursive force deletion command in install.sh
  • rm -rf — Recursive force deletion command in scripts/plugin/build.sh
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This is a spec-driven development system designed to pair with Claude Code. It includes a CLI built in Rust that adds a semantic search layer to a local library of software specifications, helping AI coding agents plan and implement features efficiently.

Security Assessment
The tool installs by piping a remote script directly to bash (`curl | bash`), which is inherently risky as it requires blind trust in the remote host. During installation and build processes, the scripts use `rm -rf` (recursive force deletion), which can be dangerous if those variables are improperly resolved or modified. Because it builds from source locally, it does not rely on downloading unverified precompiled binaries, which is a positive. There are no hardcoded secrets and no dangerous system permissions are requested. Overall risk is rated Medium due to the installation method and potentially destructive cleanup commands in the build scripts.

Quality Assessment
The project is in active development, with its most recent push happening today. It uses the highly permissive MIT license. With 27 GitHub stars, the project has a small but growing level of community trust and visibility. It is written in Rust, indicating a focus on performance and memory safety, and automatically installs its own required toolchain if missing.

Verdict
Use with caution—while the open-source Rust codebase is actively maintained and permissively licensed, you should always inspect the `install.sh` and build scripts for safety before executing them on your system.
SUMMARY

A light-weight and straightforward system for spec-driven development with Claude Code

README.md
speq-skill Logo

speq-skill

A light-weight and straightforward system for spec-driven development with Claude Code

spec|driven
Rust
CI
License: MIT

Getting Started • Why • How It Works • Documentation • Installation

Getting Started

curl -fsSL https://raw.githubusercontent.com/marconae/speq-skill/main/install.sh | bash

[!NOTE]
The installer builds speq from source using the Rust toolchain (installed automatically if missing). There is no binary distribution. See Installation for details.

Then run claude and type /speq:mission to start.

What does the installer do?
  • Downloads the latest release source from GitHub
  • Installs the Rust toolchain if missing (via rustup)
  • Builds the speq CLI from source
  • Installs the CLI to ~/.local/bin/speq
  • Installs plugin files to ~/.speq-skill/
  • Registers the plugin with Claude Code

To uninstall, see Installation — Uninstall.

Why I Built It

I want to leverage Claude Code as an effective tool to write software.

There are many other spec-driven development tools out there: OpenSpec, BMAD, SpecKit...

...but I was missing the following:

  1. A system that is not primped on one language or framework (e.g., Python or TypeScript)
  2. A straightforward repeatable workflow (plan → implement → record)
  3. A permanent and growing spec-library
  4. A system that keeps the specs small to avoid context cluttering
  5. A system that keeps asking me instead of making assumptions
  6. Semantic anchors that ground AI behavior in established methodologies

So I built speq-skill.

It combines skills with a simple CLI called speq that adds a semantical search layer to the permanent spec library. The search empowers the coding agent to find the right feature or scenarios during planning, but also during the implementation. This avoids reading unnecessary specs into the context window.

New to spec-driven development? Read "Spec-driven development: an introduction" and "Writing specs for AI coding agents" on my blog.

Each skill is grounded in semantic anchors — named references to established methodologies (like London School TDD, BLUF, ADR) that steer AI behavior toward well-documented practices.

Who should use it?

Vibe Coding does not scale. speq-skill adds the missing workflow and guardrails.

If you want to describe what you want and have a coding agent generate the code for you, then you should give speq-skill a try!

It introduces a lightweight workflow for spec-driven development. It adds a CLI to enable the coding agent to search the permanent spec library.

How Does it Work?

/speq:mission → specs/mission.md (once per project)
                       │
      ┌────────────────┼────────────────┐
      ▼                ▼                ▼
/speq:plan  →  /speq:implement  →  /speq:record  (repeat)
  1. Mission — Do it once. The coding agent explores your codebase (or interviews you for a greenfield project) and generates specs/mission.md.
  2. Plan — Describe what you want. The coding agent searches existing specs, asks clarifying questions, and creates a plan with spec deltas.
  3. Implement — The coding agent implements the plan, guided by guardrails for code quality, testing and more.
  4. Record — The coding agent merges implemented spec deltas into the permanent spec library.

Specs live in specs/<domain>/<feature>/spec.md. Plans stage in specs/_plans/<plan-name>/. The separation keeps your spec library clean while work is in progress.

Documentation

Guide Description
Installation Setup CLI and plugin
Workflow One-time mission setup, then Plan → Implement → Record cycle
CLI Reference All CLI commands
MCP Servers Serena and Context7
Semantic Anchors Named methodologies grounding each skill

Important

speq-skill is a plugin for Claude Code and other compatible AI coding agents. This tool provides workflow structure and spec management only—the AI / coding agent (such as Claude Code) generates all code, specs, or other artifacts.

Dependencies

This plugin uses Serena and Context7 MCP servers. The installer sets them up as a convenience — they are standard open-source servers installed from their respective repositories. Their behavior, limitations, and conditions are governed by their own documentation. Context7's MCP server connects to a cloud service with a free tier — see Context7.

The speq CLI downloads the snowflake-arctic-embed-xs embeddings model (~23MB) on first run for semantic search.

License

MIT

Build with Rust 🦀 and made with ❤️ by marconae.

Reviews (0)

No results found