recursive-decomposition SKILL.md skillA
recursive-decomposition from massimodeluisa/recursive-decomposition-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add massimodeluisa/recursive-decomposition-skill/recursive-decomposition@v1.2.0Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- massimodeluisa/recursive-decomposition-skill
- Path
skills/recursive-decomposition/SKILL.md- Versions recorded
- 3
- Latest version
- v1.2.0, committed Sep 11, 2026
- First version recorded
- Aug 28, 2026
- Size
- 8,684 bytes
- Repository stars
- 54
- License
- MIT
Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered sources. Skip one file, one function, a single needle, or a one-page PDF conversion. Triggers: long context, context rot, large codebase, many files, all files, big document…
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
# Recursive Decomposition Long inputs rot. Details get missed, distant parts get glued together by guesswork, and the reasoning drifts. The RLM paper calls it context rot. Do not load the whole input into the window. Treat it as an environment you query: size it, narrow it, split it, hand independent parts to sub-agents, verify on a small window, synthesise in code. Based on [Recursive Language Models](https://arxiv.org/abs/2512.24601) (Zhang, Kraska, Khattab, 2025). ## How to use - `/recursive-decomposition`: apply the protocol below to the current task. - `/recursive-decomposition <path or question>`: size that input first, then run the protocol on it. ## When it applies Fit is not the test. Dense work can rot inside a million-token window. In the paper, OOLONG-Pairs is 32k tokens and GPT-5 scores 0.1% F1; RLM(depth=1) reaches 58.0% (arXiv:2512.24601, Table 1). 30k and 50k below are harness caps. | Situation | Approach | |-----------|----------| | One file, one function, or a single needle | Read directly | | Linear aggregate or list-everything, and completeness matters | Decompose (this skill) | …
Read the whole file at its exact version.
How to install
mdr add massimodeluisa/recursive-decomposition-skill/recursive-decomposition@sha256:5fd29fab49e9477dThe line at the top of this page pins the label v1.2.0, 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.
[](https://markdownregistry.com/a/art_ugrm4lglbnjxgwbk)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Aug 28, 2026 and Sep 11, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.2.0 latest | 2026-09-11 | e0a8b04 | 8,684 B | A | view · diff |
| v1.1.0 | 2026-08-28 | ef0d9f1 | 6,455 B | A | view · diff |
| git:20260828.efb84bc | 2026-08-28 | efb84bc | 7,417 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8684 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
massimodeluisa/recursive-decomposition-skill · 54 stars · license MIT · pushed 2026-09-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ugrm4lglbnjxgwbk GET https://markdownregistry.com/api/v1/resolve?ref=massimodeluisa/recursive-decomposition-skill/recursive-decomposition GET https://markdownregistry.com/api/v1/blob/5fd29fab49e9477d60228efe8b4af3ed6a5566b1187c1700efece6897f47278a
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.