Scientific Agent Skills is a collection of reusable procedures that give AI agents capabilities for scientific research across areas such as biology, chemistry, medicine, and drug discovery. It is used by researchers and by people building AI scientist workflows with compatible coding agents. The catalogue contains many of the project's skills and supporting instructions.
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 K-Dense-AI/scientific-agent-skills --skill fictivgit clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-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/k-dense-ai/scientific-agent-skills/fictiv)<a href="https://agentmods.dev/skills/k-dense-ai/scientific-agent-skills/fictiv"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agent-skills/fictiv/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/k-dense-ai/scientific-agent-skills/fictiv"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agent-skills/fictiv.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 | $0.00209 | $0.03237 |
| Opus 5.5 | $0.00084 | $0.01295 |
| Sonnet 5.5 | $0.00042 | $0.00647 |
| Haiku 4.5 | $0.00021 | $0.00324 |
Grade A, and why
fictiv 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 16d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fictiv: quote, order and troubleshoot custom parts
This skill operates Fictiv through its logged-in web app. The official sources reviewed on 2026-09-30 document browser workflows and a managed cXML Punchout integration, but no public customer API, SDK, authentication, endpoint, or pagination contract. Do not reverse-engineer private app calls. Use the logged-in web app at https://app.fictiv.com with browser tools. Prefer the user's own browser (e.g. Claude in Chrome), because that's where their Fictiv session lives. This skill tells you where everything is, what each state means, and where the money and legal decisions are, which need clear user authorization. Public-documentation review does not revalidate the September 2026 authenticated UI snapshot; verify current labels and selections before acting.
Files in this skill
| File | Read it when |
|---|---|
references/ui-map.md |
Before the first browser action. Covers URLs, page anatomy, exact labels, and automation tricks and pitfalls. |
references/quoting.md |
Uploading, configuring, DFM, lead times, manual quotes, sharing (the core flow) |
references/checkout-and-payment.md |
Anything involving address, shipping, tax, card, PO or placing the order |
references/orders-library-teams.md |
Tracking, documents, cancel or change, returns, reorders, Library, Teams, account |
references/capabilities.md |
Choosing process, material or finish; tolerances, file formats, size limits, design rules, compliance |
references/troubleshooting.md |
Anything that isn't working: upload, DFM, pricing, checkout, automation |
scripts/check_cad_file.py |
Before every upload. It checks documented formats and heuristic STEP/STL geometry, units and size; ITAR text scanning is limited to STEP. |
scripts/quote_state.js |
Whenever you need the state of a quote or checkout page as a compact digest. Paste it into the browser's JS tool. |
scripts/list_dropdown_options.js |
To list every option in an open (virtualized) dropdown, such as materials, finish colors or threads |
What ships with it
9 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.
- references/capabilities.md 19 KB
- references/checkout-and-payment.md 10 KB
- references/orders-library-teams.md 11 KB
- references/quoting.md 17 KB
- references/troubleshooting.md 13 KB
- references/ui-map.md 19 KB
- scripts/check_cad_file.py 13 KB runs code
- scripts/list_dropdown_options.js 2.0 KB runs code
- scripts/quote_state.js 8.6 KB runs code
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.
- 16d ago Changed · +3 lines · +1 tokens per session c4f9b182d2f4
- 17d ago Changed · +5 lines 02144d17d428
- 18d ago First seen · 151 lines · 208 tokens per session scan A 81b5e64ee505
fictiv is a skill published in the GitHub repository K-Dense-AI/scientific-agent-skills (52,240 stars, last pushed 2d ago), licensed MIT. It adds 209 tokens to every session and 3,237 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
beat-sync-reel
Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.
product-reel-generator
Generates Instagram-ready product reels from any e-commerce product page URL. Scrapes product images, classifies by type, generates AI-animated clips via Higgsfield API, creates text overlays with style presets, and composes a 15-20 second reel with music. Supports model-based and product-only reels.
amazon-search
Search Amazon products - find items, compare prices, read reviews.
ebay-search
Search eBay listings - find items, auctions, deals, and compare prices.
18-ot-ics-security
Operational Technology and industrial control system security — Purdue model segmentation, industrial protocol analysis (Modbus, DNP3, S7, EtherNet/IP), PLC/HMI exposure, IEC 62443 alignment, and MITRE ATT&CK for ICS, for authorized and safety-conscious assessments.
product-photoshoot
Create faithful studio, lifestyle, and on-model product photography through the GooseWorks Product Photos workflow, then approve selected results for reuse in future creative work.