Skillget

lissom-skills

agent
Security Audit
Pass
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 12 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This project provides a collection of lightweight skills and prompt dispatchers designed to extend AI coding agents (such as Claude Code, OpenCode, and Gemini CLI) for everyday software development automation and context management.

Security Assessment
Overall Risk: Medium. The lightweight source code itself is clean; a light scan of 12 files found no dangerous patterns, hardcoded secrets, or excessive permissions. However, the recommended installation method pipes a remote shell script directly into bash (`curl ... | bash`). While standard in many developer tools, this practice requires implicitly trusting the repository maintainer and prevents easily reviewing the script before it executes on your local machine.

Quality Assessment
The project is in excellent health. It is actively maintained with recent commits made just today, uses the permissive MIT license, and has passing CI pipelines. It currently has 12 GitHub stars, indicating an early-stage but functional community presence. The documentation is clear, multilingual, and outlines a well-structured, predictable workflow.

Verdict
Safe to use, though developers should always inspect the `install.sh` script via their browser before running the provided curl command.
SUMMARY

Light weight Claude Skills and Agents for every day tasks.

README.md

Lissom Skills

License: MIT
GitHub stars
GitHub last commit
GitHub repo size
CI

English · 简体中文 · 日本語

┌─┐
│L│░ LISSOM  —  Simple, reliable Claude Code skills & agents
└─┘  SKILLS     for daily dev automation and context protection.

Why? What's the difference from GSD, SuperPower?

  • Zero Dependency — just plain files.
  • Thin Skill Dispatchers — relentless context protection.
  • Idempotency — hussle-free resume with minimal state.
  • Hammered Specs — no surprise dev experience.
/gsd-autonomous /lissom-auto
GSD context LISSOM context
(Context after a 10m task on a small local model with Qwen Code)

When to use?

  • I have an idea, help me refine the specs and automate the implementation.

When not to use?

  • Trivial tasks — do it in one agent.
  • Exploratory tasks — use /explore.

Basic Workflow

           ┌─ interview ─┐
           │             /
 research ─┘ auto ──►   +   ──► plan ──► impl ──► review ──► done
  Specs.md    Research.md /    Plan.md         Review.md     │
   ▲                     /                                   │ critical?
   │                     └──────────── fix cycle (max 3)  ◄──┘
   │                                          │
   └──────────────── fix cycles exhausted ────┘

Installation

Install into your project's directory with:

curl -fsSL https://raw.githubusercontent.com/cuzfrog/lissom-skills/main/scripts/install.sh | bash

Supported:

Uninstallation

Remove all installed files from both .claude/ and .opencode/ directories in the current project:

curl -fsSL https://raw.githubusercontent.com/cuzfrog/lissom-skills/main/scripts/uninstall.sh | bash

Only files originally installed by this bundle are removed — any custom files you added are left untouched. Empty directories are cleaned up automatically.

Here We Go!

Run /lissom-auto <task_id> — get interviewed and wait for the job done!

  1. It looks for the task in .lissom/tasks/<task_id>/Specs.md
  2. If not found, it tries to locate with tools (e.g. JIRA MCP)

Best practices

  • Reference to project documentation in your Specs.md. This saves exploration.
  • Define test methods clearly (e.g. in CLAUDE.md)

Configuration

Set preferences in .lissom/settings.local.json to avoid being asked each run:

{
  "user_attention": "default",
  "fix_threshold": "warning",
  "spec_review_required": "yes"
}
Key Options
user_attention default — Interview for major concerns; auto — Best effort auto pilot; focused — Exhaustive questioning
fix_threshold warning — Fix critical & warnings; critical — Critical only; suggestion — All issues
spec_review_required yes — Review and refine specs before research; no — Skip spec review

Links

  • GitHub — source code and releases
  • Issues — bug reports and feature requests
  • License — MIT

Author

Cause Chung [email protected]

Reviews (0)

No results found