Is the Recursive Decomposition skill free?

Yes. The skill itself is free from massimodeluisa/recursive-decomposition-skill. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Recursive Decomposition SkillProof Score?

7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Recursive Decomposition?

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 Recursive Decomposition 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.

Recursive Decomposition

Large-context tactics: grep-first, chunk, recurse via sub-agents

by massimodeluisa · massimodeluisa/recursive-decomposition-skill

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · d6ce414

A pure-prose guidance skill (no scripts) that codifies large-context tactics: grep before read, wc -l before opening files, partition lists over 10, recurse via sub-agents. On a representative multi-file analysis task the recommended method and the final answer were identical to the no-skill baseline, because a capable agent already does exactly this, so no measurable delta was demonstrated. The four reference files (677 lines) are well written and accurately reflect the RLM paper concept, and the install runs clean from a bare HOME. Useful as a reminder or for weaker agents, but it did not beat the baseline here.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Recursive Decomposition does

A prose-only guidance skill that codifies strategies for tasks exceeding comfortable context limits: filter with grep/glob before reading, check file size with wc -l first, partition lists over 10 items, and recurse through sub-agents. Triggers on requests like 'analyze all files', 'process this large document', 'aggregate information from', or 'search across the codebase', and on tasks spanning 10+ files or 50k+ tokens.

How to install Recursive Decomposition

git clone https://github.com/massimodeluisa/recursive-decomposition-skill.git
mkdir -p ~/.claude/skills
cd recursive-decomposition-skill && cp -r plugins/recursive-decomposition/skills/recursive-decomposition ~/.claude/skills/recursive-decomposition

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Recursive Decomposition

/recursive-decomposition Large-context tactics: grep-first, chunk, recurse via sub-agents

It also activates on plain-language prompts like these:

analyze every file in this huge repo without blowing up context
aggregate the key findings from these forty PDFs into one summary
search across the whole codebase for every authentication pattern

Frequently asked questions

Is the Recursive Decomposition skill free?: Yes. The skill itself is free from massimodeluisa/recursive-decomposition-skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does Recursive Decomposition work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. A pure-prose guidance skill (no scripts) that codifies large-context tactics: grep before read, wc -l before opening files, partition lists over 10, recurse via sub-agents. On a representative multi-file analysis task the recommended method and the final answer were identical to the no-skill baseline, because a capable agent already does exactly this, so no measurable delta was demonstrated. The four reference files (677 lines) are well written and accurately reflect the RLM paper concept, and the install runs clean from a bare HOME. Useful as a reminder or for weaker agents, but it did not beat the baseline here.
What is the Recursive Decomposition SkillProof Score?: 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Recursive Decomposition?: 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 Recursive Decomposition 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.