Atomic Decomposition
Breaks down research papers into atomic concepts where each piece gets both a math formula and a working code implementation. You trace every definition to specific papers and repos, creating a structured knowledge base that maps theory to practice bidirectionally. Useful when you're reading complex systems papers and need to verify that every mathematical concept actually has corresponding code, or vice versa. The workflow is thorough but rigid: decompose, survey papers for formulas, survey codebases for implementations, then compile everything with explicit gap analysis. Works well for formal methods research where you need rigorous grounding, less so for exploratory work where the mapping isn't clean.
- skills.sh installs
- 1.6K
- GitHub stars
- 459
- last updated
- Aug 21, 2026
Install
$ npx -y skills add lingzhi227/agent-research-skills --skill atomic-decomposition --agent claude-codeInstalls into .claude/skills of the current project.
Files
Atomic Decomposition
Decompose research ideas into atomic concepts with math formula <-> code implementation mapping.
Input
$0— Research idea, paper, or method description
References
- Decomposition prompts and workflow:
~/.claude/skills/atomic-decomposition/references/decomposition-prompts.md
Workflow (from AI-Researcher Survey Agent)
Step 1: Break Down into Atomic Definitions
Analyze the research idea and decompose into atomic, self-contained concepts:
- Each atom should be a single concept
- Must have clear mathematical foundations
- Must be implementable in code
- Must be traceable to specific papers
Step 2: For Each Atomic Definition
A. Paper Survey (Math Formula)
- Search papers for the mathematical formulation
- Extract the exact LaTeX formula
- Note assumptions and constraints
- Record reference papers
B. Code Survey (Implementation)
- Search codebases for implementations
- Extract the corresponding code
- Note implementation details and variations
- Record reference repositories
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/lingzhi227/agent-research-skills
- Categories
- AI & Agent Building, Data Science & ML
- First seen
- Jun 3, 2026
More from lingzhi227/agent-research-skills
All 31- Paper To Code1.6K
- Experiment Code1.6K
- Paper Assembly1.6K
- Symbolic Equation1.6K
- Excalidraw Skill1.6K
- Literature Review4.1K
- Literature Search2.7K
- Figure Generation2.3K
- Latex Formatting2.3K
- Backward Traceability2.3K
- Math Reasoning2.2K
- Citation Management2.2K
- Data Analysis2K
- Deep Research2K
- Idea Generation1.9K
- Novelty Assessment1.9K
- Paper Writing Section1.8K
- Paper Revision1.8K
- Experiment Design1.8K
- Github Research1.8K
- Research Planning1.8K
- Survey Generation1.8K
- Algorithm Design1.7K
- Rebuttal Writing1.7K
Recommended
More AI & Agent Building
bidsK-Dense-AI/scientific-agent-skillsUse this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy1.6Kskills.sh installs
paper-to-codelingzhi227/agent-research-skillsConvert an ML research paper into a complete, runnable code repository. 3-stage pipeline from Paper2Code — Planning (UML + dependency graph) → Analysis (per-fil1.6Kskills.sh installs
r3f-best-practicesemalorenzo/three-agent-skillsReact Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/f1.6Kskills.sh installsexperiment-codelingzhi227/agent-research-skillsWrite ML experiment code with iterative improvement. Generate training/evaluation pipelines, debug errors, and optimize results through code reflection. Use whe1.6Kskills.sh installs
auth0-nextjsauth0/agent-skillsUse when adding Auth0 login, logout, protected pages, or middleware to a Next.js application. Supports App Router and Pages Router with @auth0/nextjs-auth0 — us1.6Kskills.sh installs
dotnet-timezonegithub/awesome-copilot.NET timezone handling guidance for C# applications. Use when working with TimeZoneInfo, DateTimeOffset, NodaTime, UTC conversion, daylight saving time, schedul1.6Kskills.sh installs