Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add wangyendt/wayne-skills --skill research-paper-deep-divegit clone --depth 1 https://github.com/wangyendt/wayne-skillsWrote 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/wangyendt/wayne-skills/research-paper-deep-dive)<a href="https://agentmods.dev/skills/wangyendt/wayne-skills/research-paper-deep-dive"><img src="https://agentmods.dev/badge/skills/wangyendt/wayne-skills/research-paper-deep-dive/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/wangyendt/wayne-skills/research-paper-deep-dive"><img src="https://agentmods.dev/badge/skills/wangyendt/wayne-skills/research-paper-deep-dive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00141 | $0.04151 |
| Opus 5 | $0.00071 | $0.02076 |
| Sonnet 5 | $0.00028 | $0.00830 |
| Haiku 4.5 | $0.00014 | $0.00415 |
Grade A, and why
research-paper-deep-dive 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Paper Deep Dive
Treat the paper as knowledge to install in the reader's mind, not a document to summarize.
The default result must let an unfamiliar reader answer four questions without reopening the paper:
- What problem made this work necessary?
- What did the authors do differently?
- Why should I believe it helped?
- What idea can I reuse elsewhere?
Accuracy is a backstage constraint. The main explanation must feel like a good advisor at a whiteboard: calm, concrete, and easy to retell.
For a full report, read references/report-template.md before drafting.
Optimize for cognitive compression
Use three reader layers. Do not merge them.
Layer 1 — 30-second understanding
Give three short points:
- The difficulty: the real bottleneck in ordinary language;
- The move: the paper's key idea, without implementation detail;
- The consequence: what became possible, with one important boundary if needed.
This is not an abstract. It is the answer the reader should be able to repeat tomorrow.
Layer 2 — Five-minute walkthrough
Tell one connected story:
concrete problem -> why obvious approaches fail -> key idea
-> one sample moving through the system -> decisive evidence
-> what to retain and where confidence stops
This is the primary deliverable. It should normally use 2,000–3,500 Chinese characters or 900–1,500 English words. Use one running example and, when helpful, one restrained analogy. Prefer causal explanation over lists.
Layer 3 — Optional technical appendix
Put exact notation, metric protocols, tables, figure locations, implementation parameters, evidence boundaries, history, authors, and reading links here. A reader who stops before this layer must still understand the paper.
When the research lineage materially explains the paper, add a short bridge between Layers 2 and 3: “这项工作为什么会从这个团队里出现”. Connect verified author/lab capabilities to the focal work and point to the most relevant papers and official repositories. Keep this bridge readable; do not turn it into six disconnected biographies.
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 · 338 lines · 141 tokens per session scan A 7dd39b4e49dd
research-paper-deep-dive is a skill published in the GitHub repository wangyendt/wayne-skills (8 stars, last pushed 2d ago), licensed MIT. It adds 141 tokens to every session and 4,151 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…