Lissom Auto
Runs the full dev cycle (research → plan → impl → review + fix loop) given an explicit task_id.
Install
npx skills add cuzfrog/lissom-skills --skill lissom-autogit clone --depth 1 https://github.com/cuzfrog/lissom-skills.git /tmp/lissom-skills
mkdir -p ~/.claude/skills
cp -r /tmp/lissom-skills/src/skills/lissom-auto ~/.claude/skills/lissom-autoPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
## Inputs
- `args` = $ARGUMENTS
- `task_id` = args[0]
- `extra_info` = args[1..] (optional)
## Preference resolution
1. Load `.lissom/settings.local.json` from the project root. It may be absent or empty — treat either as no preferences set.
2. Load `<skill_dir>/user_preference_questions.json` from this skill's directory. Each entry has a `preference_arg` key (the preference name).
3. For each preference, check if it is present in `settings.local.json`. If set, use it.
4. For any preference not found in `settings.local.json`:
- Inform user: "Preferences can be set in `.lissom/settings.local.json`, see README."
- If the user answers `user_attention`=`auto` or `extra_info` demands auto processing, skip all rest questions and set `fix_threshold`=`critical`, `spec_review_required`=`false`.
- If the user answers `spec_review_required`=`true`, set `research_required`=`true` and skip that question.
- Use Tool `AskUserQuestion` to prompt the user using the entry's question/options. The first option in each question is the default one.
### Preference variables (first options are defaults):
- `user_attention` = `default`, `auto`, `focused`
- `fix_threshold` = `warning`, `critical`, `suggestion`
- `spec_review_required` = `false`, `true`
- `research_required` = `true`, `false`
- `impl_delegation` = `single`, `multiple` (do not ask question)
## Task Directory Resolution
1. `task_dir` = `.lissom/tasks/<task_id>` or `.lissom/tasks/backlog/<task_id>`Details
- Skill name
lissom-auto- Repository
- cuzfrog/lissom-skills
- Path
src/skills/lissom-auto/SKILL.md- License
- MIT
- Repo updated
- 24 August 2026
FAQ
What does the Lissom Auto skill do?
Runs the full dev cycle (research → plan → impl → review + fix loop) given an explicit task_id.
How do I install the Lissom Auto skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add cuzfrog/lissom-skills --skill lissom-auto. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Lissom Auto popular?
It lives in cuzfrog/lissom-skills, which has 54 GitHub stars and 6 forks.
Related skills
Lissom Impl
54cuzfrog/lissom-skills
Dispatch to lissom-implementer agent to execute the implementation given an explicit task_dir, which contains the plan.
Lissom Plan
54cuzfrog/lissom-skills
Dispatches to lissom-planner agent to produce an implementation plan given an explicit task_dir, which contains a specification or research document.
Lissom Research
54cuzfrog/lissom-skills
Dispatches lissom-specs-reviewer and then lissom-researcher agents optionally to refine the specification and produce the research document given an explicit task_dir, which contains the original specification.
Paper Write 4ss
43JingYangYuan/paper-write-4ss
中文社会科学论文写作系统。先通过 research_router.md 完成研究方法协议与发表范式双层路由,再按章节标准和范文提示词完成写作、润色和检查。支持规范研究、实证研究、阐释研究、混合研究四类方法协议,以及社会学研究范式和管理世界案例研究范式两类发表风格。配备 writing_scanner.py 与 complexity_analyzer.py,用于语言反模式扫描和文本复杂度诊断。
Deep Research
70alexdcd/Mafia-Claude-Skills
This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API. It automates prompt enhancement through interactive clarifying questions, saves research parameters, and executes deep research with web search capabilities. Use when the user asks for in-depth analysis, investigation, research summaries, or topic exploration.
Alterlab Abm Mesa
87AlterLab-IEU/AlterLab-Academic-Skills
Builds agent-based models of social systems with Mesa 3 — the current AgentSet API (model.agents.shuffle_do('step'), auto-assigned unique_id, mandatory super().__init__(rng=...)), cell spaces (mesa.discrete_space OrthogonalMooreGrid / classic mesa.space grids), the DataCollector, batch_run parameter sweeps, and SolaraViz — for emergence, segregation, diffusion, opinion dynamics, and cooperation models. It uses the Mesa 3.x API (the old mesa.time schedulers like RandomActivation are removed) and treats the model as a generative theory to be validated, not just run. Use when the request mentions
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.