trim-long-context SKILL.md skillA

trim-long-context from lucasmartins-ai/lcc is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lucasmartins-ai/lcc/trim-long-context@git:20261001.851d28a

Pins git:20261001.851d28a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lucasmartins-ai/lcc
Path
plugins/chatgpt/skills/trim-long-context/SKILL.md
Versions recorded
1
Latest version
git:20261001.851d28a, committed Oct 1, 2026
Size
2,541 bytes
Repository stars
19
License
MIT

Cut a long document, transcript, meeting recording, support thread, or server log down to only the parts that matter for a stated goal. Use when the user pastes a lot of text and asks to shorten it, find the relevant part, cut the noise, or answer a question from a long transcript. Returns the kept text verbatim rather than a summary, so quotes stay exact.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

Use this skill when the user has more text than fits comfortably in a conversation and
wants only the part that matters for a specific goal.

## What the user gives you

- **A goal**, in their words: "find the refund issue", "what decided the launch date",
  "why did it 500".
- **A body of text**: a transcript, document, log, or thread.

If the goal is missing or vague, ask what they are trying to find out. Do not guess the
goal — a wrong goal silently returns the wrong blocks.

## Workflow

1. Identify the goal and the text. If the text is enormous, work on the portion the user
   pointed at.
2. Call `compact` with the text and the goal. The default `mechanical` provider is fully
   offline and needs no API key; use it unless the user asks for deeper semantic judging.
3. Read the report. It names every block that was kept, trimmed, or dropped, with the
   score and reason for each.
4. Answer from the kept text, quoting it exactly. Cite where in the source each fact came
   from when the user needs to check it.

## Output

- The relevant passages, verbatim, with the dropped material accounted for.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add lucasmartins-ai/lcc/trim-long-context@sha256:04fefa521108779a

The line at the top of this page pins the label git:20261001.851d28a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_xhhhqena5k3k37vb.svg)](https://markdownregistry.com/a/art_xhhhqena5k3k37vb)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 1, 2026.

versioncommittedcommitsizeaudit
git:20261001.851d28a latest2026-10-01 851d28a 2,541 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2541 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

lucasmartins-ai/lcc · 19 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_xhhhqena5k3k37vb
GET https://markdownregistry.com/api/v1/resolve?ref=lucasmartins-ai/lcc/trim-long-context
GET https://markdownregistry.com/api/v1/blob/04fefa521108779a6db1993396cd1826ef6d7d437e25952fc16ec373c5b04406

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.