Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

lossless-claw — Claude Code skill: what it does, how to install

Guides configuration and diagnostics for the lossless-claw OpenClaw plugin, focusing on summary health and recall tools.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add Martian-Engineering/lossless-claw --skill lossless-claw -a claude-code
Open on GitHub

What lossless-claw does

This skill guides coding agents through managing and troubleshooting the lossless-claw plugin in OpenClaw. It outlines health check workflows via /lossless (or the /lcm alias), detects summary truncation through /lossless doctor, and handles cleanup preparation with /lossless doctor clean.

When tracking errors, the skill checks the independent Lossless log before looking into the shared OpenClaw gateway log. It directs users toward recall tools when exact facts are needed from compacted history, rather than guessing from summaries. It also clarifies that /lossless covers LCM frontier metrics, while /status inspects the runtime prompt snapshot.

The instructions warn not to assume the Go TUI is installed. Advanced internals like rewriting, backfilling, or dissolving remain untouched unless requested directly.

What it helps with

  • diagnose summary corruption with /lossless doctor
  • prepare session cleanup using /lossless doctor clean
  • configure lossless-claw plugin settings in OpenClaw
  • pull exact facts from compacted history using recall tools

Example prompts for the agent

  • Help me configure lossless-claw in OpenClaw
  • How do I check summary health using /lossless doctor?
  • What is the difference between /lossless and /status outputs?

How to install lossless-claw

1Skills CLI (Vercel)

npx skills add Martian-Engineering/lossless-claw --skill lossless-claw -a claude-code

2Manually: put the files in place

~/.claude/skills/lossless-claw/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/lossless-claw/

Similar

modlens liustack A skill that gives text-only models eyes: it sends the image through a CLI and returns JSON with transcribed text, layout regions and semantic notes. Claude Code CX Codex Cursor +1 896installs autopilot nick-vels Turns a dictated idea into a finished app, site, bot or feature in one dialogue: requirements, spec, tickets, subagents and blind acceptance, no per-stage approval. Claude Code CX Codex Cursor +1 5,200installs langgraph-cli langchain-ai Gives the agent a reference for the langgraph CLI: scaffold a project, run it locally, build an image, deploy it. Claude Code CX Codex Cursor +1 8,900installs reducing-entropy softaworks A skill that measures success by the size of the codebase afterwards, not by the effort spent. It runs only when you ask, and it deletes. Claude Code CX Codex Cursor +1 4,000installs company-research deanpeters Builds a company brief from public sources: quotes from leaders, product strategy, how the org works. Useful before an interview, a partner meeting or a competitor review. Claude Code CX Codex Cursor +1 3,400installs swarm langchain-ai Fans out independent items across subagents in parallel and aggregates the results. Useful for batch file reviews, labeling, and data extraction. Claude Code CX Codex Cursor +1 8,700installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about lossless-claw

How to install lossless-claw in Claude Code?

Run npx skills add Martian-Engineering/lossless-claw --skill lossless-claw -a claude-code.

What does lossless-claw do?

It instructs AI assistants on configuring the lossless-claw plugin, reading standalone logs, and resolving summary issues in OpenClaw.

Which log should be checked first when debugging?

Check the independent Lossless log before reviewing the shared OpenClaw gateway log.

Source text

SKILL.md · MIT 
---
name: lossless-claw
description: Configure, diagnose, and use lossless-claw effectively in OpenClaw, with emphasis on key settings, summary health, and recall-tool usage.
---

# Lossless Claw

Use this skill when the task is about operating, tuning, or debugging the `lossless-claw` OpenClaw plugin.

Start here:

1. Confirm whether the user needs configuration help, diagnostics, recall-tool guidance, or session-lifecycle guidance.
2. If they need a quick health check, tell them to run `/lossless` (`/lcm` is the shorter alias).
3. If they are debugging lossless-claw behavior or failures, check the independent Lossless log before the shared OpenClaw gateway log.
4. If they suspect summary corruption or truncation, use `/lossless doctor`.
5. If they want high-confidence junk/session cleanup guidance, use `/lossless doctor clean` before recommending any deletes.
6. If they ask how `/new` or `/reset` interacts with LCM, read the session-lifecycle reference before answering.
7. Load the relevant reference file instead of improvising details from memory.

Reference map:

- Configuration (complete config surface on current main): `references/config.md`
- Internal model and data flow: `references/architecture.md`
- Diagnostics and summary-health workflow: `references/diagnostics.md`
- Recall tools and when to use them: `references/recall-tools.md`
- `/new` and `/reset` behavior with current lossless-claw session mapping: `references/session-lifecycle.md`

Working rules:

- Prioritize explaining why a setting matters, not just what it does.
- Prefer the native plugin command surface for MVP workflows (`/lossless`, with `/lcm` as alias).
- Do not assume the Go TUI is installed.
- Do not recommend advanced rewrite/backfill/transplant/dissolve flows unless the user explicitly asks for non-MVP internals.
- For exact evidence retrieval from compacted history, guide the user toward recall tools instead of guessing from summaries.
- When users compare `/lossless` to `/status`, explain that they report different layers: `/lossless` shows LCM-side frontier/summary metrics, while `/status` shows the last assembled runtime prompt snapshot.

© Martian-Engineering · MIT · Martian-Engineering/lossless-claw

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor