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 shikaijieskj/science-skills --skill science-readergit clone --depth 1 https://github.com/shikaijieskj/science-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/shikaijieskj/science-skills/science-reader)<a href="https://agentmods.dev/skills/shikaijieskj/science-skills/science-reader"><img src="https://agentmods.dev/badge/skills/shikaijieskj/science-skills/science-reader/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/shikaijieskj/science-skills/science-reader"><img src="https://agentmods.dev/badge/skills/shikaijieskj/science-skills/science-reader.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 | $0.00084 | $0.00506 |
| Opus 5 | $0.00042 | $0.00253 |
| Sonnet 5 | $0.00017 | $0.00101 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
science-reader 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 12d 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.
What it actually says
Science Reader
Use this skill to help users understand a paper without collapsing it into a generic summary. Preserve source grounding and figure logic.
Chinese trigger examples include 中英文对照, 原文对照, and 全文翻译解读.
Defaults
- Do not invent text not present in the source.
- Do not provide full copyrighted article text unless the user supplied it and the use is allowed.
- For paywalled or inaccessible papers, work from accessible metadata, abstract, figures supplied by the user, or open versions, and state the limitation.
- Keep figure/table placement near the relevant prose when possible.
- For Chinese users, explain scientific logic in Chinese while preserving technical terms.
Open extra files
| File | Open when |
|---|---|
| references/output-spec.md | Need the Markdown reader structure |
| references/grounding-rules.md | Need source anchors, copyright limits, or figure/table handling |
Workflow
- Identify source type: PDF, DOI, publisher HTML, preprint, abstract, or pasted text.
- Extract metadata: title, authors, journal, year, DOI, article type.
- Build a paper map:
question -> gap -> approach -> main results -> figures -> limitations -> reuse. - Place each figure/table near the section it supports.
- Produce bilingual blocks only when source text is provided or lawful to use; otherwise produce Chinese explanation and concise paraphrase.
- Finish with a claim-evidence table and discussion questions.
Output contract
Use Markdown:
# [Title]
## Metadata
## One-sentence takeaway
## Paper map
## Section-by-section reader
## Figure and table guide
## Claim-evidence map
## Limitations and open questions
## Journal-club discussion prompts
If the user explicitly asks for full bilingual translation and provides the source PDF/text, preserve source anchors for every block.
What ships with it
3 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.
- 12d ago First seen · 66 lines · 84 tokens per session scan A acce1c38cadf
science-reader is a skill published in the GitHub repository shikaijieskj/science-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 506 once invoked, about $0.0004 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
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
proof-writer
A tool for writing or checking rigorous mathematical proofs for claims such as theorems, lemmas, propositions, and corollaries.
tooluniverse-organic-chemistry
Organic chemistry reasoning guide for reaction product prediction, mechanism analysis (electrophilic/nucleophilic substitution, addition, elimination, pericyclic, radical), and spectroscopy interpretation (1H/13C NMR, IR, MS). Reasons from first principles (electron flow, kinetic vs thermodynamic) rather than…
build-interactive-explainers
A guide for building interactive explainers, calculators, and simulations driven by an executable model. Users change inputs, steps, states, or events to understand a rule or see how a process develops over time.
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…
edu-chem-reaction
A guide for turning a chemical reaction into a self-contained interactive 3D web demonstration. It shows molecules changing while also displaying the balanced equation, explanations, atom counts, and optionally an energy curve.