Borrowing it
Nothing to install: this file belongs to BIH-CEI/zotero-comfort. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BIH-CEI/zotero-comfort/main/.claude/skills/ceir-publication-sync/SKILL.mdgit clone --depth 1 https://github.com/BIH-CEI/zotero-comfortWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bih-cei/zotero-comfort/ceir-publication-sync)<a href="https://agentmods.dev/skills/bih-cei/zotero-comfort/ceir-publication-sync"><img src="https://agentmods.dev/badge/skills/bih-cei/zotero-comfort/ceir-publication-sync/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bih-cei/zotero-comfort/ceir-publication-sync"><img src="https://agentmods.dev/badge/skills/bih-cei/zotero-comfort/ceir-publication-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00134 | $0.00772 |
| Opus 5 | $0.00067 | $0.00386 |
| Sonnet 5 | $0.00027 | $0.00154 |
| Haiku 4.5 | $0.00013 | $0.00077 |
Grade A, and why
ceir-publication-sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CEIR Publication Sync
Sync Workflow
- Fetch publications from Charité API for all team members with tokens
- Enrich with PubMed metadata where DOI/abstract missing
- Deduplicate by DOI (primary) then normalized title (fallback)
- Filter out pre-affiliation papers (see filtering rules in references)
- Compare against existing Zotero items (match DOI or title)
- Create missing items in Zotero, assign to year collections
Charité Forschungsdatenbank API
Primary source. No browser needed — call REST endpoints directly.
BASE = https://forschungsdatenbank.charite.de/experts/expert
GET /publications/pub_per_exp/{token}/FPS → publications
GET /exp/co_per_exp/{token}/FPS → co-authors
GET /exp/info_per_exp/{token} → profile info
Use 0.3s delay between requests. Returns: title, authors, year, DOI, journal, volume/issue/pages, abstract, PubMed/PMC links, open access status, internal co-authors with tokens.
Implementation: src/zotero_comfort/external/charite.py — ChariteClient class, CEIR_TEAM roster.
Other Sources
- PubMed (
src/zotero_comfort/external/pubmed.py): Enrich metadata, verify DOIs, get PMIDs - ORCID (not yet implemented): 5 members have ORCID only — see references/roster.md
- arXiv (
src/zotero_comfort/external/arxiv.py): Low priority, most team output is journals/conferences - BIH website: Just links to Forschungsdatenbank profiles, no publications inline. Skip.
Deduplication
Publications appear under multiple members. Deduplicate with:
- DOI (case-insensitive, stripped) — strongest
- Normalized title (lowercase, non-alnum removed, first 50 chars) — fallback
First occurrence wins. See ChariteClient._deduplicate().
Zotero Sync Target
- Library: CEI_Publications (ID 5767153), key at
~/.secret/ceir-os-zotero-token(format:library_id:api_key) - Collections: Year-based (2018–2026)
- Item mapping: See
workflows_external.py→_paper_to_zotero_item() - Blocker (2026-02-04): API key is read-only. Need write access.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 59 lines · 134 tokens per session scan A 98d14736cbfb
ceir-publication-sync is a skill published in the GitHub repository BIH-CEI/zotero-comfort (1 stars, last pushed 4mo ago), licensed MIT. It adds 134 tokens to every session and 772 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…