save-material
Skill1 starsChanged 3 months agoMITView on GitHub
Fetch a paper or web resource and save it as a structured markdown summary in the project resources. Use when the user shares a URL, DOI, paper title, or reference and wants it saved. Triggers on "save this paper", "add this source", "download and summarise", "store this reference", or when a link to a paper or technical resource is pasted.
In this repository13 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- factsSkill
- figureSkill
- full-reviewSkill
- ingestSkill
- onboardSkill
- plan-sectionSkill
- researchSkill
- reviewSkill
- statusSkill
- teachSkill
- verify-sourcesSkill
- writeSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Check for duplicates: Search resources/ for the same work before creating a file.
- Distinctive: line 58
Do not overstate a source.
≈ “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
/save-material — File a source properly
Steps
- Resolve the source. Fetch the URL, or look the paper up by DOI or title through OpenAlex, Semantic Scholar, or Crossref. If the publisher version is paywalled, try Unpaywall (
https://api.unpaywall.org/v2/{doi}?email={email}) for a legal open-access copy. If you cannot reach the full text, say so and summarise from the abstract and metadata, marking clearly which parts of your summary rest on the abstract alone. - Check for duplicates. Search
resources/for the same work before creating a file. If it exists, update it rather than adding a second copy. - Choose the destination.
- Academic work →
resources/theoretical/<firstauthor_year>.md - Domain, company, dataset, tool, or standards documentation →
resources/practical/<descriptive_name>.md
- Academic work →
- Write the summary.
# <Title>
## Metadata
- **Authors**:
- **Year**:
- **Venue**:
- **DOI / URL**:
- **Type**: journal article | conference paper | preprint | report | documentation | blog post
- **Peer-reviewed**: yes | no
- **Citation count** (as of <date>):
- **Access**: open | paywalled | read via institutional access
## What it argues
<The main contribution in a few sentences, in plain terms.>
## Method
<How the evidence was produced, and on what data or cases. Note the sample and the setting — this is what determines whether the finding transfers.>
## Findings relevant here
<Only what bears on this project, with page numbers where you would want to quote.>
## How this project uses it
- **Section(s)**:
- **Claim it supports**:
- **Limits**: <where it does not apply, or where its setting differs from this project's>
## Contradicts or complicates
<Sources in this project that it disagrees with, if any. This field is the reason the summary is worth writing.>
## Reference entry
<Formatted in the project's citation style, ready to paste.>- Report what was saved, which sections it serves, and whether it conflicts with anything already in
resources/.
Do not overstate a source. If the paper is tangential, say it is tangential.
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.

