Skip to main content
Category ranking· 品类排行

The best AI skills for data & research做数据与研究最好用的

Skills that search, synthesize, analyze data, and turn research into decisions.检索、综合、分析数据,并把研究材料转成决策依据的 skill。

Editor's picks编辑精选榜单

2026-05-16 last re-ranked · 上次重排
#1Gold · 金

peer review

Editor's Choice· 编辑首选
by K-Dense-AI·updated 2w ago

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific…

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writin…

Claude CodeMedium risk · 中风险$
rating · 评分
21k
stars · 星标
View看详情 →
#2Silver · 银

depmap

Runner-up· 次选
by K-Dense-AI·updated 2w ago

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity…

Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets.

Claude CodeMedium risk · 中风险$
rating · 评分
21k
stars · 星标
View看详情 →
#3Bronze · 铜

ab-test-analysis

Pair with #1· 推荐配套
by phuryn·updated 3w ago

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/st

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

Claude CodeCodexMedium risk · 中风险$
rating · 评分
11k
stars · 星标
View看详情 →
#4

prompt guard

by Orchestra-Research·updated 2w ago

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ T…

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Claude CodeMedium risk · 中风险$
rating · 评分
8.2k
stars · 星标
View看详情 →
#5

variant analysis

by trailofbits·updated 2w ago

Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, bui…

Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.

Claude CodeMedium risk · 中风险$
rating · 评分
5.1k
stars · 星标
View看详情 →
#6

yara rule authoring

by trailofbits·updated 2w ago

Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or opt…

Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on…

Claude CodeMedium risk · 中风险$
rating · 评分
5.1k
stars · 星标
View看详情 →
#7

trailmark

by trailofbits·updated 2w ago

Builds and queries multi-language source code graphs for security analysis. Includes pre-analysis passes for blast radi…

Builds and queries multi-language source code graphs for security analysis. Includes pre-analysis passes for blast radius, taint propagation, privilege boundaries, and entry point enumeration. Use when analyzing call paths, mapping attack surface, finding complexity hotspots, en…

Claude CodeMedium risk · 中风险$
rating · 评分
5.1k
stars · 星标
View看详情 →
#8

semgrep rule creator

by trailofbits·updated 2w ago

Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing…

Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.

Claude CodeMedium risk · 中风险$
rating · 评分
5.1k
stars · 星标
View看详情 →
#9

mermaid to proverif

by trailofbits·updated 2w ago

Translates Mermaid sequenceDiagrams describing cryptographic protocols into ProVerif formal verification models (.pv fi…

Translates Mermaid sequenceDiagrams describing cryptographic protocols into ProVerif formal verification models (.pv files). Use when generating a ProVerif model, formally verifying a protocol, converting a Mermaid diagram to ProVerif, verifying protocol security properties (sec…

Claude CodeMedium risk · 中风险$
rating · 评分
5.1k
stars · 星标
View看详情 →
#10

sharp edges

by trailofbits·updated 2w ago

Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when revi…

Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by default' and 'pit of success' principl…

Claude CodeMedium risk · 中风险$
rating · 评分
5.1k
stars · 星标
View看详情 →

Why we didn't pick these为什么没选这些

Also common, but didn't make the picks同样常见,但未入精选
  • protocolsio integration

    Workflows that require stronger human review than this catalog entry documents.

    需要比当前目录条目更严格人工复核的工作流。

  • pptx posters

    Workflows that require stronger human review than this catalog entry documents.

    需要比当前目录条目更严格人工复核的工作流。

  • scientific writing

    Workflows that require stronger human review than this catalog entry documents.

    需要比当前目录条目更严格人工复核的工作流。

Didn't find what you need?没看到合适的 skill?

Tell us your pain points and we'll go look.把你的痛点告诉我们,我们会去找。

Skill Market
Find the best AI skills for the job·按品类找最好用的 AI 技能
v0.4 · 1252 skills indexed · last review 2026-05-16