scientific-impact-assessment
Skill9 starsChanged 4 months agoMITView on GitHub
Assess research reach with OpenAlex citations, optional Altmetric data, and journal context. Use when comparing papers, journals, or literature shortlists by influence.
- Reads credentials
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- ai-scientist-evaluatorSkill
- arxiv-searchSkill
- beautiful-data-vizSkill
- bio-annotationSkill
- bio-assembly-qcSkill
- bio-binning-qcSkill
- bio-fasta-database-curatorSkill
- bio-foundation-housekeepingSkill
- bio-gene-callingSkill
- bioinformatics-projectSkill
- bio-interdomain-hgtSkill
- bio-logicSkill
- bio-phylogenomicsSkill
- bio-prefect-dask-nextflowSkill
- bio-protein-clustering-pangenomeSkill
- bio-reads-qc-mappingSkill
- biorxiv-searchSkill
- bio-stats-ml-reportingSkill
- bio-structure-annotationSkill
- bio-viromicsSkill
- bio-workflow-methods-docwriterSkill
- crossref-lookupSkill
- csag-extractionSkill
- exploratory-data-analysisSkill
- manuscript-review-councilSkill
- notebooksSkill
- pdf-to-mdSkill
- plotly-dashboard-skillSkill
- polars-dovmedSkill
- proposal-reviewSkill
- public-db-lookupSkill
- scientific-writingSkill
- tracking-taxonomy-updatesSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill to measure the reach of a paper with citation, attention, and journal-level context.
- Distinctive: line 12
Prefer a DOI or OpenAlex work ID as input.
- Very specific: line 13
If you only have a title, use /crossref-lookup first to resolve a DOI before running this skill.
- Distinctive: line 14
Use the bundled CLI:
- Distinctive: line 24
Keep paper-level and journal-level metrics separate in the final answer.
- Distinctive: line 25
Do not present journal impact factor as a proxy for article quality.
- Distinctive: line 26
Do not present Altmetric attention as equivalent to scholarly citation impact.
- Distinctive: line 27
If the journal is not in the curated table, return the OpenAlex result anyway and say the journal-level reference lookup was not available.
- Very specific: line 101
Solution: Check whether ALTMETRIC_API_KEY is set.
- Distinctive: line 106
Issue: Only a title is available.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Scientific Impact Assessment
Use this skill to measure the reach of a paper with citation, attention, and journal-level context.
Instructions
- Prefer a DOI or OpenAlex work ID as input.
- If you only have a title, use
/crossref-lookupfirst to resolve a DOI before running this skill.
- If you only have a title, use
- Use the bundled CLI:
- In this repository:
skills/scientific-impact-assessment/scripts/measure-impact - After installation:
~/.agents/skills/scientific-impact-assessment/scripts/measure-impact
- In this repository:
- OpenAlex is the default source for paper-level citation data.
- The CLI retrieves
cited_by_count, publication year, journal/source name, and citation history from OpenAlex.
- The CLI retrieves
- Altmetric is optional enrichment. The Details Page API requires an API key.
- Without
ALTMETRIC_API_KEY, the CLI reports Altmetric as unavailable (no_api_key) instead of failing. A keyless request toapi.altmetric.com/v1/doi/...returned HTTP 403 when checked on 2026-10-01.
- Without
- Journal-level impact factors come from the curated references table in
references/journal_metrics_2024.tsv.- These are curated public web values, mostly from official publisher pages.
- The
Sciencerow uses a labeled third-party fallback because no public official AAAS JIF page was located during skill creation on March 19, 2026.
- Keep paper-level and journal-level metrics separate in the final answer.
- Do not present journal impact factor as a proxy for article quality.
- Do not present Altmetric attention as equivalent to scholarly citation impact.
- If the journal is not in the curated table, return the OpenAlex result anyway and say the journal-level reference lookup was not available.
- Repeated OpenAlex lookups use a TTL-bound response cache and a cross-process pacing lock. Defaults are
--cache-ttl 86400and--min-interval 0.1; use--cache-dirorOPENALEX_CACHE_DIRfor a project/site cache. Live reports record this request policy.
Quick Reference
| Task | Action |
| Measure by DOI | skills/scientific-impact-assessment/scripts/measure-impact --doi 10.1038/nature12373 |
| Measure by OpenAlex ID | skills/scientific-impact-assessment/scripts/measure-impact --openalex-id W2741809807 |
| Add OpenAlex polite-pool email | --mailto you@example.org or OPENALEX_MAILTO |
| Enable Altmetric enrichment | Source ALTMETRIC_API_KEY from a private environment file before running |
| Text summary output | --format text |
| Save JSON report | --output impact-report.json |
| Journal metrics table | references/journal_metrics_2024.tsv (sources: references/README.md) |
| Regression test (repository root) | uv run --no-project --with pytest python -m pytest tests/test_scientific_impact_assessment.py -q |
Input Requirements
uv(the CLI runs the stdlib-only script throughuv run --script)- One of:
--doi <doi>--openalex-id <id>
- Optional:
--mailto <email>orOPENALEX_MAILTOfor OpenAlex polite-pool identification, only with an address the user gave for this purposeALTMETRIC_API_KEYloaded from a private environment file--output <path>--format json|text
Output
- OpenAlex-derived paper metadata including:
- title
- DOI
- OpenAlex ID
- publication year
- citation count
- citation history by year
- journal/source name
- Altmetric summary when an API key is available and the record exists
- curated journal-level impact-factor context when the journal matches the bundled references table
- explicit status values when Altmetric or journal-level lookup is unavailable
Quality Gates
- The input is resolved to a DOI or OpenAlex work ID before lookup
- OpenAlex citation data is reported separately from journal-level metrics
- Altmetric is marked optional and unavailable when no API key is configured
- Journal impact factors are read from the bundled references table, not improvised from memory
- Any third-party journal metric source is labeled as such in the output
- Repeated OpenAlex requests record cache TTL and minimum interval; expired responses are refreshed under the pacing lock.
Examples
Example 1: DOI-based report
skills/scientific-impact-assessment/scripts/measure-impact \
--doi 10.1038/nature12373 \
--format textExample 2: OpenAlex ID plus Altmetric
source ~/.secrets/altmetric.env
skills/scientific-impact-assessment/scripts/measure-impact \
--openalex-id W2741809807 \
--mailto you@example.org \
--output impact-report.jsonTroubleshooting
Issue: Altmetric is always unavailable.
Solution: Check whether ALTMETRIC_API_KEY is set. The Details Page API requires a key for every endpoint.
Issue: The journal-level lookup is empty.
Solution: The journal is probably not in references/journal_metrics_2024.tsv yet. Return the OpenAlex paper metrics and add the journal later if you can source a public metric page.
Issue: Only a title is available.
Solution: Resolve the title to a DOI first with /crossref-lookup, then rerun this skill using the DOI for a deterministic lookup.
Related Skills
/crossref-lookup: resolve DOIs before scoring impact/polars-dovmed: retrieve the full text that backs the impact claim
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.

