recursive-decomposition agent skill by massimodeluisa
Decomposes dense codebase-wide, multi-document, and large PDF analysis, following Recursive Language Models research, to aggregate or reason across many scattered sources.
At a glance
| Publisher | massimodeluisa |
|---|---|
| Repository | github.com/massimodeluisa/recursive-decomposition-skill |
| Category | AI Agents and LLM Engineering |
| License | MIT |
| Last commit | September 11, 2026 (repository) |
| SKILL.md | 106 lines, 1,189 words |
| Bundled files | 9 files, including references |
| Quality score | 78/100 · C Passes all seven graded checks |
| Security scan | Not scanned |
| README badge | Get the listing badge and raise the score |
Before you install
Read from the skill's files at the directory's October 19, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.
- Bundled scripts: none.
- License: MIT, an open-source or open-content license.
Install recursive-decomposition
The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.
npx skills add https://github.com/massimodeluisa/recursive-decomposition-skill/tree/main/skills/recursive-decompositiontmp="$(mktemp -d)"
git clone --depth 1 https://github.com/massimodeluisa/recursive-decomposition-skill.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/recursive-decomposition .claude/skills/
rm -rf "$tmp"python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo massimodeluisa/recursive-decomposition-skill \
--path skills/recursive-decompositionmassimodeluisa/recursive-decomposition-skill is third-party code. Read SKILL.md and any bundled scripts before you install it.
How the author describes it
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, multi-document, PDF, aggregate, summarize everything, codebase-wide, multi-hop, recursive, sub-agents, map-reduce.
From the description field of SKILL.md. Agents read this line to decide when to load the skill.
Sections in SKILL.md
- How to use
- When it applies
- Protocol
- Rules
- Tools, agent-agnostic
- Patterns
- Codebase analysis
- Multi-document question answering
- Aggregation
- Large PDFs
- Long output
- Cost and quality
- Anti-patterns
- References
Files in the skill folder
SKILL.mdevals/README.mdevals/evals.jsonevals/gold/pdf-corpus.jsonevals/trigger-queries.jsonreferences/codebase-analysis.mdreferences/cost-analysis.mdreferences/document-aggregation.mdreferences/rlm-strategies.md
Suede Skill Check: 78/100 · C
Report snapshot · · graded-v2
The rubric totals 100 points; published scores are capped at 99. Security scan: not scanned.
Source revision: e0a8b0418a1e. Report version c2a0b4acde78. Badge URLs follow the latest listing; save the report to keep this version.
Download report · Request a fresh review
What to review next
- Boundary clause: 0 of 4 points. 4 when the description says when not to use the skill (“Not for …”, “Do not use …”, “Use … instead”).
- Example request: 0 of 3 points. 3 when the description quotes an example request (3–60 characters in quotation marks).
- Recent maintenance: 6 of 9 points. 9 for a repository commit within 30 days of the snapshot; 6 within 90; 3 within 180; 1 within 365.
Add declarations and bundled files when they describe the skill’s actual needs. Update the source, then request a fresh review with the changed commit or PR.
recursive-decomposition passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.
See the checks and points
| Check | Result |
|---|---|
| Frontmatter parses and declares a name and a description | Pass |
| Name uses lowercase letters, digits and hyphens, 64 characters or fewer | Pass |
| Name matches the skill's folder name | Pass |
| Description is between 50 and 1,024 characters | Pass |
| Description says when an agent should use the skill | Pass |
| SKILL.md body is 500 lines or fewer | Pass |
| A license is declared in the frontmatter or the repository | Pass |
| Repository has a commit in the last 12 months | Pass |
| Score component | Points |
|---|---|
| Structural checks | 56 of 56 |
| Description length | 3 of 5 |
| Boundary clause | 0 of 4 |
| Example request | 0 of 3 |
| Instruction depth | 7 of 7 |
| Reference files | 3 of 3 |
| Bundled scripts | 0 of 2 |
| Recent maintenance | 6 of 9 |
| Curated-list citations | 3 of 7 |
| Tool permissions declared | 0 of 2 |
| Compatibility declared | 0 of 2 |
Show the listing and raise the score
recursive-decomposition is listed with 78/100 · C. This badge links to its Suede listing. Skills scoring 80–99 add a numeric and a letter quality shield; the largest open points for recursive-decomposition are boundary clause (4), example request (3) and recent maintenance (3). Send your repository and the points you want to raise, then request a fresh review after updating the skill.
[](https://skills.suedeai.ai/directory/massimodeluisa/recursive-decomposition-skill/recursive-decomposition/)<a href="https://skills.suedeai.ai/directory/massimodeluisa/recursive-decomposition-skill/recursive-decomposition/"><img src="https://skills.suedeai.ai/directory/badge.svg" alt="Suede Skills Directory: listed" height="20"></a>Where this skill is cited
massimodeluisa/recursive-decomposition-skill appears in 2 curated lists: VoltAgent/awesome-agent-skills, heilcheng/awesome-agent-skills.