Lissom Auto
Slash-command orchestrator for a research-plan-impl-review dev cycle with fix loop
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 21c813c
The curl|bash installer ran clean and dropped lissom-auto plus its four sibling sub-skills, five agent definitions, and a sample T1 task into the project's .claude/ — note it installs project-local, not into ~/.claude, and only works as a bundle. It is a genuine orchestrator (lissom-review really spawns a lissom-reviewer Agent, etc.), but its payoff is long-run context protection across a multi-agent dev loop, which cannot be benchmarked against a no-skill baseline in a single session, so the output delta here is unmeasured rather than demonstrated.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 4/5
- Output vs. baseline 5/10
- Docs & honesty 4/5
What Lissom Auto does
A thin dispatcher that runs a full dev cycle for one task_id by delegating to lissom-research, lissom-plan, lissom-impl, and lissom-review sub-agents, then looping fixes up to 3 times. Invoked explicitly as /lissom-auto <task_id> (model auto-invocation is disabled); intended for scoped, non-trivial tasks, not quick edits.
How to install Lissom Auto
# Устанавливается в .claude/ ТЕКУЩЕГО проекта (не глобально). Запускать из корня проекта:
curl -fsSL https://raw.githubusercontent.com/cuzfrog/lissom-skills/main/scripts/install.sh | bash
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Lissom Auto
-
/lissom-autoSlash-command orchestrator for a research-plan-impl-review dev cycle with fix loop
It also activates on plain-language prompts like these:
-
Run the full research-plan-implement-review cycle on task T-104 for me -
Delegate this bug fix through the research, plan, and review pipeline -
Kick off the automated dev cycle with the fix loop for this feature task
Frequently asked questions
- Is the Lissom Auto skill free?
- Yes. The skill itself is free from cuzfrog/lissom-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Lissom Auto work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. The curl|bash installer ran clean and dropped lissom-auto plus its four sibling sub-skills, five agent definitions, and a sample T1 task into the project's .claude/ — note it installs project-local, not into ~/.claude, and only works as a bundle. It is a genuine orchestrator (lissom-review really spawns a lissom-reviewer Agent, etc.), but its payoff is long-run context protection across a multi-agent dev loop, which cannot be benchmarked against a no-skill baseline in a single session, so the output delta here is unmeasured rather than demonstrated.
- What is the Lissom Auto SkillProof Score?
- 6.8/10 — installs cleanly 4/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 4/5.
- How do I install Lissom Auto?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Lissom Auto with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.