setup-extract
Skill234 starsChanged 8 months agoMITView on GitHub
Extract structured information from research papers, PDFs, or code into knowledge base extractions
In this repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- critiqueSkill
- edit-resumeSkill
- make-clSkill
- make-resumeSkill
- setup-build-kbSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
22 rules. About 0 are common, 15 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈15
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Read CLAUDE.md — check KB Corrections Log for known issues
- Very specific: line 20
Read config.md — load Personal Info (to identify user's author position), Provenance Flags
- Very specific: line 21
Read knowledge_base/extractions/_INVENTORY.md — see what's already extracted, avoid duplicates
- Distinctive: line 23
If the paper is already in the inventory:
- Distinctive: line 25
Ask: "This paper is already extracted.
- Distinctive: line 26
Wait for user response before proceeding
- Distinctive: line 32
Read the paper using the appropriate method:
- Distinctive: line 33
PDF files: Use the Read tool (supports PDF reading)
- Distinctive: line 34
.tex source: Read directly — often has more detail than the compiled PDF
- Distinctive: line 35
If both exist: Prefer .tex for content extraction, use PDF for figures/tables
- Distinctive: line 41
All computational methods, experimental techniques, software, and frameworks mentioned
- Distinctive: line 53
If the user's contribution is not obvious from the paper (common for multi-author work), ask:
- Very specific: line 70
Create the extraction file at knowledge_base/extractions/<AuthorYear_short_descriptor>.md
- Distinctive: line 74
If the user is first author: use their last name
- Very specific: line 136
Read and update knowledge_base/extractions/_INVENTORY.md.
- Distinctive: line 138
Add a row to the inventory table:
- Distinctive: line 150
After extraction is complete, present:
- Very specific: line 155
If more papers to extract: "Run /setup-extract [next paper path]"
- Very specific: line 156
If all papers done: "Run /setup-build-kb to synthesize extractions into experience files and bundles"
- Very specific: line 166
If $ARGUMENTS contains multiple file paths:
- Distinctive: line 168
Ask Phase 2 clarifying questions for ALL papers at once (grouped) before writing any extractions
- Distinctive: line 169
After all extractions: present combined inventory update and summary
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/setup-extract
User input: $ARGUMENTS
Parse $ARGUMENTS:
- File path to a paper (e.g.,
papers/Smith2024_catalyst.pdf,papers/project_report.tex) → read that file - Multiple paths separated by spaces → batch mode (process each sequentially)
- Empty → ask the user for the paper path or paste content
Startup
- Read
CLAUDE.md— check KB Corrections Log for known issues - Read
config.md— load Personal Info (to identify user's author position), Provenance Flags - Read
knowledge_base/extractions/_INVENTORY.md— see what's already extracted, avoid duplicates
If the paper is already in the inventory:
- Show the existing extraction path
- Ask: "This paper is already extracted. Re-extract (overwrite) or skip?"
- Wait for user response before proceeding
Phase 1: Read & Understand the Paper
Read the paper using the appropriate method:
- PDF files: Use the Read tool (supports PDF reading)
- .tex source: Read directly — often has more detail than the compiled PDF
- If both exist: Prefer .tex for content extraction, use PDF for figures/tables
While reading, collect:
- Full title, all authors, year, journal/venue, DOI (if available)
- The user's position in the author list (first, co-first, second, middle, last, corresponding)
- Publication status (check
config.mdProvenance Flags first, then infer: published / under review / draft / internal) - All computational methods, experimental techniques, software, and frameworks mentioned
- Quantitative results — speedups, accuracies, efficiencies, improvements over baselines
- Novelty claims — "first-ever", "new framework", "novel approach", etc.
- Collaboration indicators — other groups, institutions, shared resources
- Funding acknowledgments
Progress: "Reading paper... [title] by [first author] et al., [year]"
Phase 2: Clarify User's Role
If the user's contribution is not obvious from the paper (common for multi-author work), ask:
Questions to ask (skip any that are already clear from the paper):
- "What was your specific contribution? (e.g., all computational work, specific analysis, code development)"
- "Did you develop any tools, methods, or code used in this paper?"
- "Were there other groups or institutions involved? What was your group's role?"
- "Any quantitative results you can personally claim? (e.g., 'I ran all the simulations')"
- "Is there anything in this paper that should NOT appear on your resume? (e.g., collaborator's experimental data)"
>>>>>> MANDATORY STOP — DO NOT PROCEED <<<<<<
Present your understanding of the paper and ask the clarifying questions above. You MUST wait for the user's explicit text response before continuing.
Phase 3: Write Extraction
Create the extraction file at knowledge_base/extractions/<AuthorYear_short_descriptor>.md
Naming convention: <FirstAuthorLastName><Year><2-3_word_descriptor>.md
- Examples:
Smith2024_protein_stability.md,Chen2023_binding_affinity.md - If the user is first author: use their last name
- Normalize to lowercase with underscores
Extraction format:
# [Full Paper Title]
## Metadata
- **Authors:** [author list — highlight user's name with bold]
- **Year:** [year]
- **Journal:** [journal/venue or "unpublished"/"internal"/"under review at X"]
- **DOI:** [DOI or "N/A"]
- **User's role:** [first author / co-first / contributing / corresponding]
- **Status:** [published | under review | draft | internal]
## Methods & Tools
- **Computational methods:** [e.g., MD, ML, FEA, CFD, etc. — be specific about methods, force fields, etc.]
- **Software/frameworks:** [e.g., GROMACS, PyTorch, ABAQUS, custom code, etc.]
- **Hardware/HPC:** [if mentioned — clusters, GPU resources, etc.]
- **Key techniques:** [specific methodological details that map to resume skills]
## Key Results
[Number each result. Include quantitative metrics wherever possible.]
1. [Result with numbers — e.g., "Achieved 5,000x speedup over brute-force screening"]
2. [Result — e.g., "Screened 8,500 variants, identified 7 top candidates"]
3. [...]
## Novelty Claims
[What's genuinely new — be precise, avoid overclaiming]
- [e.g., "First application of framework X to system Y"]
- [e.g., "New method combining A and B — no prior work exists"]
## Collaboration & Scope
- **Other groups:** [institutions, PIs involved]
- **User's specific contribution:** [from Phase 2 clarification]
- **Shared vs. sole work:** [what the user did alone vs. with others]
## Provenance Notes
- **Publication status:** [matches config.md if listed there]
- **Safe to claim:** [what the user can put on a resume without hedging]
- **Needs hedging:** [claims that require "contributed to" or "supported" framing]
- **Do NOT claim:** [results from collaborators, claims that would be overclaiming]
## Resume Bullet Seeds
[3-5 draft bullets in STAR format. These are seeds, not final text.]
[Use full-ownership verbs only for sole-contributor work. Hedge for shared work.]
1. [Action verb] + [what was done] + [quantitative result/impact]
2. [Action verb] + [method/tool developed] + [what it enabled]
3. [Action verb] + [scope — e.g., "across N systems"] + [outcome]
4. [Optional: collaboration-framed bullet]
5. [Optional: tool/infrastructure bullet]Save the file. Show the user the complete extraction.
Progress: "Writing extraction for [short title]... [N] results identified, [M] bullet seeds drafted"
Phase 4: Update Inventory
Read and update knowledge_base/extractions/_INVENTORY.md.
Add a row to the inventory table:
| [filename] | [short title] | [user's role] | [status] | [primary methods] | [date extracted] |Present the updated inventory entry to the user.
Phase 5: Next Steps
After extraction is complete, present:
- Extraction summary: [N] methods, [M] quantitative results, [K] bullet seeds
- Provenance flags: Any items that need special handling
- Suggested next action:
- If more papers to extract: "Run
/setup-extract [next paper path]" - If all papers done: "Run
/setup-build-kbto synthesize extractions into experience files and bundles"
- If more papers to extract: "Run
>>>>>> MANDATORY STOP <<<<<<
Present extraction summary. Wait for user feedback or next paper. You MUST wait for the user's explicit text response before continuing.
Batch Mode
If $ARGUMENTS contains multiple file paths:
- Process each paper through Phases 1-4 sequentially
- Ask Phase 2 clarifying questions for ALL papers at once (grouped) before writing any extractions
- After all extractions: present combined inventory update and summary
- Single STOP at the end (not per paper)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

