---
title: "Headroom Labs (@headroomlabs-ai) skills · skilld"
description: "1 agent skill published by Headroom Labs on skilld."
canonical_url: "https://skilld.dev/gh/headroomlabs-ai"
meta:
  "og:description": "1 agent skills published by Headroom Labs."
  "og:image": "https://skilld.dev/_og/d/a_Headroom%2BLabs%2Bskill%2Bprofile%2Bon%2Bskilld%2Cc_Curator.takumi%2Chandle_headroomlabs-ai%2CdisplayName_Headroom%2BLabs%2Cdescription_Make%2Bevery%2Btoken%2Bcount%2Cavatar_~aHR0cHM6Ly9naXRodWIuY29tL2hlYWRyb29tbGFicy1haS5wbmc%2CcollectionCount_1%2CskillCount_1%2Cprops_eyJza2lsbHMiOlsiaGVhZHJvb20iXX0%2Cp_Ii9naC9oZWFkcm9vbWxhYnMtYWki%2Cs_4TTVL0UP7Gj-f_43.png"
  "og:image:alt": "Headroom Labs skill profile on skilld"
  "og:image:height": "600"
  "og:image:type": image/png
  "og:image:width": "1200"
  "og:title": "Headroom Labs on skilld"
  "twitter:image": "https://skilld.dev/_og/d/a_Headroom%2BLabs%2Bskill%2Bprofile%2Bon%2Bskilld%2Cc_Curator.takumi%2Chandle_headroomlabs-ai%2CdisplayName_Headroom%2BLabs%2Cdescription_Make%2Bevery%2Btoken%2Bcount%2Cavatar_~aHR0cHM6Ly9naXRodWIuY29tL2hlYWRyb29tbGFicy1haS5wbmc%2CcollectionCount_1%2CskillCount_1%2Cprops_eyJza2lsbHMiOlsiaGVhZHJvb20iXX0%2Cp_Ii9naC9oZWFkcm9vbWxhYnMtYWki%2Cs_4TTVL0UP7Gj-f_43.png"
  "twitter:image:alt": "Headroom Labs skill profile on skilld"
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

![Avatar for Headroom Labs](https://skilld.dev/_img/avatar?url=https%3A%2F%2Fgithub.com%2Fheadroomlabs-ai.png)

# **Headroom Labs**

[@headroomlabs-ai](https://github.com/headroomlabs-ai)org

Make every token count

1 skill 80k Synced 1 day ago

[GitHub](https://github.com/headroomlabs-ai) [Website](https://headroomlabs.ai)

## Skills

### [headroomlabs-ai/headroom](https://skilld.dev/gh/headroomlabs-ai/headroom)

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

1 skill 80k

`npx skilld add headroomlabs-ai/headroom --all`

- [/headroom](https://skilld.dev/gh/headroomlabs-ai/headroom)

  Use when a Python or TypeScript app sends large tool outputs, logs, JSON, search results or long chat history to an LLM and the task is to cut input tokens, reduce token cost, fit a context window, or trim tool results without losing errors. Adds the headroom-ai compress() call; in-process, no API key, no model download.

Skills published by Headroom Labs. Checked GitHub just now

```json
{"@context":"https://schema.org","@graph":[{"@id":"https://skilld.dev/#website","@type":"WebSite","description":"Curated agent skills by humans, written by real maintainers in their own GitHub repos","name":"skilld","url":"https://skilld.dev/"},{"@id":"https://skilld.dev/gh/headroomlabs-ai#webpage","@type":"WebPage","description":"1 agent skill published by Headroom Labs on skilld.","name":"Headroom Labs (@headroomlabs-ai) skills","url":"https://skilld.dev/gh/headroomlabs-ai","isPartOf":{"@id":"https://skilld.dev/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://skilld.dev/gh/headroomlabs-ai"]}]},{"@id":"https://skilld.dev/gh/headroomlabs-ai#owner","@type":"Organization","alternateName":"@headroomlabs-ai","description":"Make every token count","name":"Headroom Labs","url":"https://skilld.dev/gh/headroomlabs-ai","image":{"@type":"ImageObject","@id":"https://skilld.dev/gh/headroomlabs-ai#avatar","url":"https://github.com/headroomlabs-ai.png","width":460,"height":460,"contentUrl":"https://github.com/headroomlabs-ai.png"},"sameAs":["https://github.com/headroomlabs-ai","https://headroomlabs.ai"]},{"@id":"https://skilld.dev/gh/headroomlabs-ai#page","@type":"CollectionPage","name":"Headroom Labs skills on skilld","url":"https://skilld.dev/gh/headroomlabs-ai","about":{"@id":"https://skilld.dev/gh/headroomlabs-ai#owner"},"hasPart":[{"@type":"SoftwareApplication","name":"headroom","url":"https://skilld.dev/gh/headroomlabs-ai/headroom","applicationCategory":"DeveloperApplication","operatingSystem":"Any"}]}]}
```