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 CYC2002tommy/Deep-Research-Agent --skill deep-science-writergit clone --depth 1 https://github.com/CYC2002tommy/Deep-Research-AgentWrote 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/cyc2002tommy/deep-research-agent/deep-science-writer)<a href="https://agentmods.dev/skills/cyc2002tommy/deep-research-agent/deep-science-writer"><img src="https://agentmods.dev/badge/skills/cyc2002tommy/deep-research-agent/deep-science-writer/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/cyc2002tommy/deep-research-agent/deep-science-writer"><img src="https://agentmods.dev/badge/skills/cyc2002tommy/deep-research-agent/deep-science-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 Data Exfiltration · line 154 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 164 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 189 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 218 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 | $0.00113 | $0.14355 |
| Opus 5.5 | $0.00045 | $0.05742 |
| Sonnet 5.5 | $0.00023 | $0.02871 |
| Haiku 4.5 | $0.00011 | $0.01435 |
Grade A, and why
deep-science-writer scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **DOI/URL Liveness Test**: Use the `Bash` tool (via `curl -I`), Exa Search MCP, or a Python script (e.g., `requests.get` / `urllib`) to ping every DOI or URL in the reference list. For bulk or programmatic URL resolut How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Science Writer (End-to-End Pipeline)
This skill orchestrates a multi-stage pipeline for scientific research, combining neural search, browser automation, academic synthesis, and humanized writing. It merges the capabilities of Exa Search, Playwright, Google Science Skills, Deep Research, and Text Humanization into one cohesive workflow.
🎯 Trigger Conditions
- User asks to write a scientific article, literature review, or deep-dive research report.
- User asks to "find literature for X", map a field, locate a research gap, back an Introduction or proposal with references, or turn a syllabus into a reading list (see the strategies in Phase 0 step 4).
- User requests comprehensive research using web searching and scraping (Exa + Playwright).
- The output requires rigorous academic citations (APA 7th) but a highly natural, human-like reading flow.
🤝 Local helpers: agy, the local model and the RAG (this machine only)
Use them when they exist: C:\Users\User\AppData\Local\agy-helpers\ask-agy.cmd (agy custom agents on Gemini), ask-local.cmd (the local Ollama model, gemma4:12b), and the obsidian-rag MCP server registered in ~/.claude.json. Where a tool is missing, skip its steps, do that work yourself, and say so in the delivery note.
| Helper | Phase | Job |
|---|---|---|
| challenger | 0 step 4 | reviews the blueprint before the user sees it (at most 2 rounds) |
| lit-reader | 0.5 step 1 | screens abstracts; 40 per call at most, passed as a JSONL file path |
| local model | 0.5 step 1 | the screener when agy errors or its quota is spent (ask-local --job screen --input <jsonl>) |
| lit-reader | 0.5 steps 2-3, 2 | reads downloaded full texts in batches of at most 8: values with unit and basis, page, verbatim quote, internal inconsistencies |
| rag-admin | 0.5 step 2 | page-image QA of PDF-derived texts before they count (--schema ingestqa); diagnoses notes that fail the RAG health gate |
| manuscript-auditor | end of 4.5 | independent second review of the grounded draft at the section and manuscript gates |
| local model | after each ingest | writes the retrieval-check questions (scripts/rag_check.py, via rag_ingest.py) |
What ships with it
16 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/academic-api-patterns.md 4.0 KB
- references/python-docx-manipulation.md 1.7 KB
- references/remi.md 24 KB
- references/research-workflows.md 11 KB
- scripts/export_reference_table.py 8.2 KB runs code
- scripts/fetch_oa_fulltexts.py 4.3 KB runs code
- scripts/fulltext_search.py 13 KB runs code
- scripts/mermaid_to_png.py 2.2 KB runs code
- scripts/node/extract_pdf_text.js 2.1 KB runs code
- scripts/node/fetch_unpaywall_oa.js 2.2 KB runs code
- scripts/node/generate_docx.js 14 KB runs code
- scripts/node/scrape_html_fulltext.js 2.0 KB runs code
- scripts/rag_check.py 6.9 KB runs code
- scripts/rag_ingest.py 11 KB runs code
- scripts/verify_urls.py 4.3 KB runs code
- templates/fetch_openalex_background.js 8.3 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.
- 5d ago Changed · +137 lines · +78 tokens per session 895e3d07035b
- 1mo ago First seen · 245 lines · 35 tokens per session scan A 17c077e5aca5
deep-science-writer is a skill published in the GitHub repository CYC2002tommy/Deep-Research-Agent (365 stars, last pushed 5d ago), licensed MIT. It adds 113 tokens to every session and 14,355 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
latex-posters
Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.
data-viz-plots
Create publication-quality plots and visualizations using matplotlib and seaborn. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).
gnomad-database
Query gnomAD (Genome Aggregation Database) for population allele frequencies, variant constraint scores (pLI, LOEUF), and loss-of-function intolerance. Essential for variant pathogenicity interpretation, rare disease genetics, and identifying loss-of-function intolerant genes.
arxiv-database
Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories.
meta-analysis
Perform quantitative meta-analysis with effect size calculation, forest plots, funnel plots, and heterogeneity assessment. Use when: user asks to combine results from multiple studies, calculate pooled effect sizes, assess publication bias, or create forest/funnel plots. NOT for: systematic review protocol (use…
post-processing
Extract, analyze, and visualize simulation output data. Use for field extraction, time series analysis, line profiles, statistical summaries, derived quantity computation, result comparison to references, and automated report generation from simulation results.