Search
Testing & QA · For researchers
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Review and validate claims using counter-hypothesis testing. | bradygaster/ | 3.3k | — | ~503 | Automated safety check: Pass | MIT | yesterday |
| 2 | A skill your agent uses whenever the user asks to generate, collect, inspect, or prepare early-experience training data (Implicit World Modeling or Self-Reflection, in the sense of arXiv:2510.08558)… | OSU-NLP-Group/ | 103 | — | ~4.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 3 | End-to-end AI-assisted meta-analysis pipeline orchestration from TOPIC.txt to final manuscript and reviewer responses. | htlin222/ | 139 | — | ~2.3k | Automated safety check: Pass | Unknown | 18 days ago |
| 4 | A skill your agent uses when changing Deep Researcher Agent continuous integration, pre-commit, or contributor governance — editing .github/workflows/ (ci, ui, skills-eval, request-nvskills-ci)… | NVIDIA-AI-Blueprints/ | 886 | — | ~1.5k | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 5 | Activate when working on the Agentic SDLC Handbook. An agent skill from danielmeppiel/agentic-sdlc-handbook. | danielmeppiel/ | 158 | — | ~1.2k | Automated safety check: Pass | Unknown | 3 mo ago |
| 6 | Use only SciAtlas search-papers to take a novice user from zero setup to a final small evidence-backed paper search result, including setup, registration guidance, configuration, retrieval, artifact… | zjunlp/ | 160 | — | ~1.3k | Automated safety check: Pass | MIT | 11 days ago |
| 7 | Route HugeGraph MCP regression testing tasks to the current public tool surface, including inspection, read-only queries, Gremlin generation, extraction, controlled import, schema validate/dry-run… | apache/ | 144 | — | ~493 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 8 | Polish academic prose, de-AI-ify text, control claim strength, or rewrite method sections for CS/AI/ML papers. | joshua-zyy/ | 115 | — | ~780 | Automated safety check: Pass | MIT | 6 days ago |
| 9 | This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure", "self-review before submission", "audit claims", "check overclaiming"… | Galaxy-Dawn/ | 5.7k | — | ~1.5k | Automated safety check: Pass | MIT | 18 days ago |
| 10 | Builds the code for a frozen research experiment test-first, with leakage controls, seed handling and saved evidence so results can be rerun and audited. | Light0305/ | 640 | — | ~2.3k | Automated safety check: Pass | MIT | 3 mo ago |
| 11 | Detects host inventory and effective CPU, memory, disk, scheduler, container, and accelerator limits when a user asks for resource-aware planning or before a clearly resource-sensitive local workload. | K-Dense-AI/ | 48k | 1 repo | ~2.9k | Automated safety check: Pass | MIT | 6 days ago |
| 12 | Supports structured what-if scenario analysis for research planning, experimental contingencies, and scientific project decisions. | K-Dense-AI/ | 48k | 1 repo | ~2.9k | Automated safety check: Pass | CC-BY-NC-4.0 | 6 days ago |
| 13 | Run structured What-If scenario analysis with multi-branch possibility exploration. | LeonChaoX/ | 944 | 1 repo | ~2.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 14 | Generates synthetic but realistic patient records (FHIR R4 bundles, C-CDA documents, CSV) with MITRE Synthea for development, CI fixtures, demos, and leakage-gate test sets — zero real PHI. | maziyarpanahi/ | 5.5k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | today |
| 15 | 15.Paper Review Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. | EvoScientist/ | 478 | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | 11 days ago |
| 16 | Slate v2 quality-gap Autoresearch shortcut. An agent skill from udecode/plate. | udecode/ | 17k | — | ~474 | Automated safety check: Pass | Unknown | yesterday |
| 17 | 17.Challenge Stress-test a finding against the choices you did not make. An agent skill from pedrohcgs/claude-code-my-workflow. | pedrohcgs/ | 1.7k | — | ~1.9k | Automated safety check: Notes | MIT | 14 days ago |
| 18 | This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure", "self-review before submission", or mentions systematic paper quality… | brycewang-stanford/ | 4.6k | 1 repo | ~1.2k | Automated safety check: Pass | Unknown | 6 days ago |
| 19 | Run Azure SDK QA bot evaluations on curated datasets locally, including a single test case. | Azure/ | 134 | — | ~1.1k | Automated safety check: Notes | MIT | yesterday |
| 20 | A skill your agent uses when downloading repositories, preparing datasets, checking licenses, creating environments, running smoke tests, or preparing reproducible research code. | BingHanOfUESTC/ | 106 | — | ~458 | Automated safety check: Pass | MIT | 3 mo ago |
| 21 | 21.Add Journal A skill your agent uses when a target journal has no profile yet. | Aperivue/ | 333 | — | ~2.6k | Automated safety check: Pass | MIT | 6 days ago |
| 22 | Detects differential alternative splicing between conditions using rMATS-turbo (binomial LRT on junction counts), leafcutter (Dirichlet-multinomial GLM on intron clusters), MAJIQ V3 deltapsi/HET… | GPTomics/ | 1.2k | 2 repos | ~6.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 23 | Orchestrates an end-to-end long-read structural-variant pipeline - basecalling to minimap2 alignment (platform-matched preset) to Sniffles2/cuteSV/pbsv calling to optional assembly-based calling… | GPTomics/ | 1.2k | 1 repo | ~5.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 24 | 24.Aer Workflow A skill your agent uses when deciding which AER-skills sub-skill to use next, before choosing a specialized skill or after a user asks how to sequence manuscript work from topic selection through… | brycewang-stanford/ | 4.6k | — | ~2.6k | Automated safety check: Pass | Unknown | 6 days ago |
| 25 | Design a diary study — prompts, cadence, duration, participant criteria, and analysis frame. | Owl-Listener/ | 2.9k | 1 repo | ~313 | Automated safety check: Pass | MIT | 1 mo ago |
| 26 | A skill your agent uses for all requirements-related work in a MATLAB MBSE project using the Requirements Toolbox (slreq). | matlab/ | 184 | — | ~6.3k | Automated safety check: Pass | Unknown | 2 days ago |
| 27 | Creates, optimizes, validates, and packages AI Agent Skills (SKILL.md format). | LeoYeAI/ | 2.2k | — | ~4.3k | Automated safety check: Notes | Apache-2.0 | 2 mo ago |
| 28 | Generate structurally realistic synthetic datasets for pipeline prototyping, test coverage, or prospective power analysis. | flonat/ | 146 | — | ~2.5k | Automated safety check: Pass | MIT | 12 days ago |
| 29 | Review commitments and stalled work from Prismer tasks and memory, then produce an evidence-based weekly plan with explicit coverage gaps. | Prismer-AI/ | 1.6k | — | ~679 | Automated safety check: Pass | MIT | 11 days ago |
| 30 | Orchestrator for the full academic research pipeline: research - write - integrity check - review - revise - re-review - re-revise - final integrity check - finalize. | brycewang-stanford/ | 4.6k | — | ~11k | Automated safety check: Pass | Unknown | 6 days ago |
| 31 | 31.Data Finder Find and assess datasets for a research question. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills. | brycewang-stanford/ | 4.6k | — | ~1.7k | Automated safety check: Pass | Unknown | 6 days ago |
| 32 | 32.F5 Humanization Quality Verifier - Ensures transformation integrity and quality Validates that humanization preserves meaning, citations, and academic standards Use when: after G6 transformation… | brycewang-stanford/ | 4.6k | — | ~2.2k | Automated safety check: Pass | Unknown | 6 days ago |
| 33 | Validate the staged or published DocMason knowledge base and repair blocking issues until the quality gate passes. | JetXu-LLM/ | 147 | — | ~762 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 34 | Multi-agent paper review loop simulating top-venue peer review. | appleweiping/ | 119 | — | ~843 | Automated safety check: Pass | MIT | 1 mo ago |
| 35 | Identify recurring weak arguments, unsupported assumptions, and vulnerable inference patterns across a literature corpus. | flonat/ | 146 | — | ~1.5k | Automated safety check: Pass | MIT | 12 days ago |
| 36 | A skill your agent uses when the research design is the bottleneck for a 《中国行政管理》 manuscript — choosing and stress-testing a quantitative, qualitative, or normative design and matching it to the… | franklee16/ | 223 | 1 repo | ~614 | Automated safety check: Pass | No licence | 23 days ago |
| 37 | A skill your agent uses when the bottleneck is identification and inference for an Econometrica manuscript — identification conditions and asymptotic distribution theory for an estimator, or axioms… | franklee16/ | 223 | 1 repo | ~1.9k | Automated safety check: Pass | No licence | 23 days ago |
| 38 | A skill your agent uses when an Econometrica manuscript needs finite-sample evidence and edge-case scrutiny — Monte Carlo design, finite-sample performance, regularity-condition stress tests, and… | franklee16/ | 223 | 1 repo | ~1.4k | Automated safety check: Pass | No licence | 23 days ago |
| 39 | A skill your agent uses when shaping or stress-testing a research question for the Journal of Business Venturing (JBV) — confirming the entrepreneurial phenomenon is central, picking a… | franklee16/ | 223 | 1 repo | ~1k | Automated safety check: Pass | No licence | 23 days ago |
| 40 | A skill your agent uses when shaping or stress-testing a research question for the Journal of Consumer Research (JCR) — confirming it is a genuine consumer-behavior question with a conceptual… | franklee16/ | 223 | 1 repo | ~1k | Automated safety check: Pass | No licence | 23 days ago |
| 41 | A skill your agent uses when shaping or stress-testing a research question for Management Science (INFORMS) — confirming the decision-relevance bar, choosing the right Department lane (analytical vs… | franklee16/ | 223 | 1 repo | ~998 | Automated safety check: Pass | No licence | 23 days ago |
| 42 | A skill your agent uses when shaping or stress-testing a research question for MIS Quarterly — confirming it is a genuine information-systems question, naming which of the four IS traditions… | franklee16/ | 223 | 1 repo | ~1k | Automated safety check: Pass | No licence | 23 days ago |
| 43 | A skill your agent uses when shaping or stress-testing a research question for Manufacturing & Service Operations Management (M&SOM) — confirming an operations decision is central, choosing the… | franklee16/ | 223 | 1 repo | ~845 | Automated safety check: Pass | No licence | 23 days ago |
| 44 | A skill your agent uses when selecting, implementing, or stress-testing the causal identification strategy for an empirical The Review of Economic Studies (REStud) manuscript — DID (incl. | franklee16/ | 223 | 1 repo | ~1.6k | Automated safety check: Pass | No licence | 23 days ago |
| 45 | A skill your agent uses when the causal-inference or asset-pricing identification strategy is the bottleneck for a The Review of Financial Studies (RFS) manuscript — quasi-experiments (DID, IV, RDD… | franklee16/ | 223 | 1 repo | ~1.4k | Automated safety check: Pass | No licence | 23 days ago |
| 46 | This skill should be used when the user asks for "TAM", "addressable population", "peak sales", "epi model", "how many patients", "bottoms-up market size", "penetration assumption", or wants to… | hh-health-AI/ | 101 | — | ~822 | Automated safety check: Pass | MIT | 3 days ago |
| 47 | Disciplined idea refinement for research projects. An agent skill from appleweiping/WEIPING_WIKI. | appleweiping/ | 119 | — | ~887 | Automated safety check: Pass | MIT | 1 mo ago |
| 48 | A skill your agent uses when deciding what characterization and experimental detail an Advanced Materials manuscript must show to prove its structure–property claim, and what belongs in the… | brycewang-stanford/ | 1.2k | — | ~1.5k | Automated safety check: Pass | MIT | 14 days ago |
