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 zjunlp/SciAtlas --skill sciatlas-idea-groundinggit clone --depth 1 https://github.com/zjunlp/SciAtlasWrote 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/zjunlp/sciatlas/sciatlas-idea-grounding)<a href="https://agentmods.dev/skills/zjunlp/sciatlas/sciatlas-idea-grounding"><img src="https://agentmods.dev/badge/skills/zjunlp/sciatlas/sciatlas-idea-grounding/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/zjunlp/sciatlas/sciatlas-idea-grounding"><img src="https://agentmods.dev/badge/skills/zjunlp/sciatlas/sciatlas-idea-grounding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 15 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00077 | $0.01078 |
| Opus 5 | $0.00039 | $0.00539 |
| Sonnet 5 | $0.00015 | $0.00216 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
sciatlas-idea-grounding 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 10d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SciAtlas Idea Grounding
Use this skill to position a research idea against prior work using only sciatlas search-papers.
Operating Contract
- Do not call any SciAtlas downstream command. The only SciAtlas retrieval command allowed is
search-papers. - Own the end-to-end novice flow: install or locate the CLI, guide registration, configure environment variables, run retrieval, inspect artifacts, and produce a grounded positioning memo.
- Ask the user only for human-only setup values: email, verification code, token, or one concise clarification about the idea.
- Do not ask the user to run shell commands when tool access is available.
- Do not reveal the full API token in final output.
Zero-Start Bootstrap
- Check whether the
sciatlasexecutable exists without invoking a SciAtlas command: useGet-Command sciatlas -ErrorAction SilentlyContinueon Windows PowerShell orcommand -v sciatlason macOS/Linux. If missing, install withpython -m pip install -e ./sciatlasin this repo orpython -m pip install "git+https://github.com/zjunlp/SciAtlas.git#subdirectory=sciatlas". - If
SCIATLAS_API_KEYis absent, guide the user tohttp://sciatlas.openkg.cn/register. - Ask for the email verification code only when needed. Ask for the returned
sciatlas_xxxtoken after registration. - Configure:
$env:SCIATLAS_API_BASE_URL = "http://sciatlas.openkg.cn"
$env:SCIATLAS_API_KEY = "<token>"
setx SCIATLAS_API_BASE_URL "http://sciatlas.openkg.cn"
setx SCIATLAS_API_KEY "<token>"
export SCIATLAS_API_BASE_URL="http://sciatlas.openkg.cn"
export SCIATLAS_API_KEY="<token>"
- If token validity is uncertain, test with a one-result
search-papersquery, nothealthorconfig.
Idea Parsing
Before searching, decompose the idea into:
- Problem: what pain or research question it attacks.
- Proposed mechanism: the technical novelty the user claims.
- Target domain: where it applies.
- Evaluation target: what would prove it works.
- Neighboring literatures: 2-4 adjacent concepts.
What ships with it
1 file 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.
- 10d ago First seen · 95 lines · 77 tokens per session scan A dec52ebd1a01
sciatlas-idea-grounding is a skill published in the GitHub repository zjunlp/SciAtlas (146 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,078 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 2026-08-30.
Other skills, from other repositories
paper2video
Turn a research paper, a paper2assets package, or an existing PPT deck into a narrated MP4 video by fully delegating slide authoring to the installed ppt-master skill and fully delegating rendering, subtitles, timeline assembly, and strict media QA to the installed pptx2video skill and its public CLI. Resolves one…
idea-quality
Score the QUALITY of a research idea at the idea stage — given a Markdown file with Title / Motivation / Method sections (no experiments needed), produce a per-axis quality assessment with cited evidence and an overall 0–100 score plus a verdict; or, given two such idea files, a blind head-to-head comparison. TRIGGER…
scienceworld-measurement-taker
Use when the agent needs to measure a quantitative property (temperature, weight, pH) of a target object or substance using a measurement tool. This skill covers acquiring the tool, preparing both tool and target with focus actions, executing the measurement via "use [TOOL] on [TARGET]", and interpreting the resulting…
scienceworld-object-selector
Use when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical component, container), properties, or category. This skill surveys visible objects with "look around", evaluates each against the task requirements…
scienceworld-threshold-evaluator
Use when the agent has just obtained a numerical measurement (temperature, weight, pH) and must compare it against a predefined threshold to determine a binary outcome. This skill extracts the measured value, evaluates it against the threshold condition (above/below), and executes the corresponding branch action such…
scienceworld-animal-identifier
Use when the agent needs to locate, identify, and focus on a specific animal or biological entity in the ScienceWorld environment. This skill handles tasks involving animal comparison, examination, or interaction (such as determining lifespan extremes) by navigating to the correct location with "teleport to"…