literature-reading-and-synthesis
Skill2 starsChanged 31 days agoMITView on GitHub
Produce scientific claim/evidence notes, figure interpretations, cross-paper syntheses, or reading workflows. Exclude literature consultation that only supports a technical task.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jjfroehlich/agent-skills-for-academic-researchword for word, first seen Oct 17, 2026
Other versions1 project uses a version of this.
Word for word · 1
- jjfroehlich/agent-skills-for-academic-research★ 2100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- career-developmentSkill
- data-visualization-and-figuresSkill
- grant-writingSkill
- life-science-research-handbookSkill
- mentoring-management-and-lab-cultureSkill
- publishing-and-peer-reviewSkill
- research-strategy-and-project-designSkill
- scientific-communicationSkill
- scientific-feedbackSkill
- scientific-writingSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 65
Use checklists for quick execution once the relevant reference route is clear.
- Distinctive: line 66
Use examples when the user asks for a template, worked pattern, or concrete artifact.
- Distinctive: line 91
Keep claims, evidence and interpretation distinct at the requested scope.
≈ “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
Literature Reading And Synthesis
Purpose
Help users read scientific papers actively, extract claims and evidence without flattening them, maintain a sustainable literature-tracking routine, and turn notes into synthesis artifacts.
Use this skill when
- First classify the requested work: continue only when the user needs renewed reading, evidence extraction, comparison, or synthesis of literature sources.
- The user needs a reading plan for one or more papers.
- The user asks how to unpack figures, tables, methods, claims, or limitations.
- The user wants a synthesis matrix, comparison table, or reusable note template.
- The user is setting up or debugging a literature-alert or reading queue.
- The user needs presentation, journal-club, or project-decision readiness from papers.
Do not use this skill when
- A completed literature review is only an input to downstream plan, code, pipeline, manuscript, or documentation updates.
- Relevant papers are only supporting evidence for a computational-analysis, pipeline, model-architecture, fine-tuning, or implementation strategy.
- The task is to trace dataset URLs, downloads, schemas, or pipeline provenance without interpreting the scientific literature.
- The user only asks for a factual summary of one paper and does not need a method.
- The task is mainly manuscript drafting, grant writing, or peer review rather than reading/synthesis.
- The request is citation formatting or citation-manager mechanics.
Core workflow
- Reassess the current user request independently on every turn. Continue only when renewed literature reading or a literature-native synthesis artifact is the primary deliverable; prior paper use or source consultation supporting a technical decision does not retain this workflow.
- Infer the goal from supplied context: orient, skim, present, compare, decide, track, or synthesize. Ask only when missing information could change the answer.
- Route to the right playbook: paper reading, claim extraction, literature tracking, or synthesis matrices.
- Pick the appropriate depth: quick triage, targeted section read, figure/evidence read, or high-stakes deep read.
- Record the material actually inspected: abstract only, selected sections or figures, full article, and any supplement checked. Separate reported observations, author interpretations and your appraisal; do not upgrade a screening note to verified evidence.
- For figures and tables, decode the evidence before writing the take-home.
- Return the requested literature artifact at the necessary depth. A focused evidence question may need one supported paragraph; use a table or full extraction only when it helps the comparison or the user requests it.
- State caveats when advice is about habit design, dated source lists, or unsupported citation-manager mechanics.
Output formats
Select only the format that fits the requested deliverable; these are patterns, not mandatory response sections.
- Reading-depth plan.
- Six-question paper note.
- Figure/table unpacking note.
- Claim and evidence extraction table.
- Literature alert portfolio.
- Weekly literature triage queue.
- Synthesis matrix.
- Build-on-it note with next research action.
Reference routing
- Open
references/paper-reading-workflow.mdfor reading goals, article-type routing, section intent, deep-read passes, and presentation readiness. - Open
references/claim-extraction.mdfor six-question extraction, figure/table unpacking, claim appraisal, and critique discipline. - Open
references/literature-tracking.mdfor alert streams, source portfolios, query tuning, weekly triage, and backlog pruning. - Open
references/synthesis-matrices.mdfor matrix fields, field-source maps, build-on-it notes, and comparison outputs. - Open
references/handbook-access.mdwhen a fuller explanation or worked example would help with the current task. - Use checklists for quick execution once the relevant reference route is clear.
- Use examples when the user asks for a template, worked pattern, or concrete artifact.
Quick checklist
Apply only the checks relevant to the requested scope and artifact. Inspect supplied context first; treat identify or clarify as analysis when the answer is already available, and ask only for missing information that could change the result.
- What is the user's reading goal and deadline?
- Is this quick triage, targeted reading, or high-stakes deep reading?
- What article type is it?
- Which claims, figures, methods, limitations, and next steps must be separated?
- Does the output need a paper note, figure note, tracking queue, or synthesis matrix?
- Are citation-manager mechanics being requested without source-backed guidance?
Common pitfalls
- Reading every paper at the same depth.
- Copying the abstract instead of extracting claims and evidence.
- Accepting figure take-homes before decoding the display.
- Treating publication as proof.
- Building an alert stream too large to process.
- Turning a synthesis matrix into a miscellaneous notes field.
Quality bar
- Choose depth that fits the reading/tracking goal; state the goal when doing so helps the user understand the scope.
- Keep claims, evidence and interpretation distinct at the requested scope. Include limitations that could change the answer; add next actions when they serve the user's task.
- Figure and table advice must include concrete evidence-decoding steps.
- Literature tracking advice must be sustainable and volume-aware.
- Outputs must be reusable by the user after the conversation.
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.

