research-alerts

Monitor research topics and alert the user when new papers are published. Use when user says "/watch", "监控", "关注这个课题", "有新文献告诉我", "monitor this topic", "alert me on new papers", "track new publications". Stores watch configurations and checks for new results at session start.

42 stars

Best use case

research-alerts is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Monitor research topics and alert the user when new papers are published. Use when user says "/watch", "监控", "关注这个课题", "有新文献告诉我", "monitor this topic", "alert me on new papers", "track new publications". Stores watch configurations and checks for new results at session start.

Teams using research-alerts should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/research-alerts/SKILL.md --create-dirs "https://raw.githubusercontent.com/Zaoqu-Liu/ScienceClaw/main/skills/research-alerts/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/research-alerts/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How research-alerts Compares

Feature / Agentresearch-alertsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Monitor research topics and alert the user when new papers are published. Use when user says "/watch", "监控", "关注这个课题", "有新文献告诉我", "monitor this topic", "alert me on new papers", "track new publications". Stores watch configurations and checks for new results at session start.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Research Alerts

Monitor research topics and notify the user when new relevant papers appear on PubMed or bioRxiv.

## When to Use

- User says "/watch TOPIC" or "监控 X 的最新文献"
- User says "有新文献告诉我" or "关注这个课题"
- User says "/watches" to list active watches
- User says "/unwatch TOPIC" to stop monitoring

## How It Works

### Watch Storage

Watches are stored as individual JSON files in `~/.scienceclaw/watches/`:

```json
{
  "topic": "THBS2 immunotherapy",
  "query": "THBS2 AND (immunotherapy OR immune checkpoint)",
  "created": "2026-03-10",
  "last_check": "2026-03-10",
  "interval_days": 7,
  "last_count": 47,
  "channel": "telegram"
}
```

File naming: `~/.scienceclaw/watches/<slug>.json` (e.g., `thbs2-immunotherapy.json`)

### Creating a Watch

When the user says `/watch TOPIC`:

1. Parse the topic into a PubMed search query (add appropriate MeSH terms or Boolean operators)
2. Run an initial search to get the baseline count
3. Save the watch configuration
4. Confirm: "已设置监控「TOPIC」,每周检查 PubMed 新文献。当前共 N 篇。"

```bash
mkdir -p ~/.scienceclaw/watches
cat > ~/.scienceclaw/watches/SLUG.json << 'EOF'
{"topic":"TOPIC","query":"PUBMED_QUERY","created":"DATE","last_check":"DATE","interval_days":7,"last_count":N,"channel":"current"}
EOF
```

### Checking Watches at Session Start

At the start of each session (as part of Session Greeting):

1. List files in `~/.scienceclaw/watches/`
2. For each watch, check if `today - last_check >= interval_days`
3. For due watches, run a PubMed search with `mindate=last_check`:

```bash
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&retmode=json&retmax=5&sort=pub_date&term=QUERY&mindate=LAST_CHECK&maxdate=TODAY&datetype=pdat"
```

4. If new results found, fetch brief summaries and report:

```
📩 文献监控更新 — TOPIC
  发现 N 篇新文献(自 LAST_CHECK 以来):
  1. "Title..." (Authors, Journal, Year) PMID: xxx
  2. "Title..." (Authors, Journal, Year) PMID: xxx
  
  要详细了解哪篇?或回复 /unwatch TOPIC 停止监控。
```

5. Update `last_check` and `last_count` in the watch file

### Listing Watches

When the user says `/watches`:

```bash
for f in ~/.scienceclaw/watches/*.json; do
  python3 -c "import json; d=json.load(open('$f')); print(f\"  📡 {d['topic']}  (每{d['interval_days']}天, 上次检查: {d['last_check']}, 累计: {d['last_count']}篇)\")"
done
```

### Removing a Watch

When the user says `/unwatch TOPIC`:

1. Find the matching watch file by topic
2. Delete it
3. Confirm: "已停止监控「TOPIC」。"

## Custom Intervals

Users can specify interval: `/watch TOPIC --daily`, `/watch TOPIC --monthly`

| Flag | interval_days |
|------|--------------|
| `--daily` | 1 |
| `--weekly` (default) | 7 |
| `--biweekly` | 14 |
| `--monthly` | 30 |

## Integration with Telegram/Discord

When the watch `channel` is set to "telegram" or "discord", the alert is sent proactively at session start via the configured channel. For terminal sessions, the alert appears as part of the greeting.

Related Skills

tooluniverse-target-research

42
from Zaoqu-Liu/ScienceClaw

Gather comprehensive biological target intelligence from 9 parallel research paths covering protein info, structure, interactions, pathways, expression, variants, drug interactions, and literature. Features collision-aware searches, evidence grading (T1-T4), explicit Open Targets coverage, and mandatory completeness auditing. Use when users ask about drug targets, proteins, genes, or need target validation, druggability assessment, or comprehensive target profiling.

tooluniverse-literature-deep-research

42
from Zaoqu-Liu/ScienceClaw

Conduct comprehensive literature research with target disambiguation, evidence grading, and structured theme extraction. Creates a detailed report with mandatory completeness checklist, biological model synthesis, and testable hypotheses. For biological targets, resolves official IDs (Ensembl/UniProt), synonyms, naming collisions, and gathers expression/pathway context before literature search. Default deliverable is a report file; for single factoid questions, uses a fast verification mode and may include an inline answer. Use when users need thorough literature reviews, target profiles, or to verify specific claims from the literature.

tooluniverse-drug-research

42
from Zaoqu-Liu/ScienceClaw

Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections. Covers identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties. Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.

tooluniverse-disease-research

42
from Zaoqu-Liu/ScienceClaw

Generate comprehensive disease research reports using 100+ ToolUniverse tools. Creates a detailed markdown report file and progressively updates it with findings from 10 research dimensions. All information includes source references. Use when users ask about diseases, syndromes, or need systematic disease analysis.

Science Communication — Making Research Accessible

42
from Zaoqu-Liu/ScienceClaw

## Overview

research-recipes

42
from Zaoqu-Liu/ScienceClaw

Pre-built research workflow templates that execute complete multi-step analyses from a single user prompt. Triggers on gene analysis, target validation, literature review, differential expression, clinical queries, researcher profiling, drug repurposing, or molecular dynamics simulation. Use when the user's query matches a Recipe pattern defined in SCIENCE.md.

research-lookup

42
from Zaoqu-Liu/ScienceClaw

Look up current research information using Perplexity Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations.

research-grants

42
from Zaoqu-Liu/ScienceClaw

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.

Patent Drafting — Intellectual Property Protection for Research

42
from Zaoqu-Liu/ScienceClaw

## Overview

Local Research Dashboard Skill

42
from Zaoqu-Liu/ScienceClaw

## 概述

market-research

42
from Zaoqu-Liu/ScienceClaw

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.

market-research-reports

42
from Zaoqu-Liu/ScienceClaw

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.