All categories
Research
Research, evidence gathering, literature, reports, investigation, and synthesis
- 21,343
- 890
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse research skills
Showing 73–96 of 21,343 skills
- Audit OutcomesTrace shipped product outcomes back to the original problem and metrics, PDLC's equivalent of backpropagation. Catches drift where the spec was built faithfully but stopped being the right thing.Votes: 0GitHub stars: 10
- Analyze CompetitionMap the competitive landscape and positioning gaps for a candidate problem space. Part of the PDLC Discover phase.Votes: 0GitHub stars: 10
- Create ArticleWrite, update, or revise a high-quality article given a target audience and relevant sources. Use when the user wants to write a new article, update or revise an existing article (to keep tone, structure, and style consistent with prior writing), or improve an article's research, clarity, or flow. Produces a structured, well-researched article tailored to the audience's knowledge level and interests, adding visualizations where they aid comprehension.Votes: 0GitHub stars: 10
- Arxiv CatchupFetches new arXiv cs.AI papers published since the last processed date, processes each paper's HTML version via the arxiv-article skill, and advances the date checkpoint. Use when the user says /arxiv-catchup, catch up on arXiv, or wants to read recent AI papers.Votes: 0GitHub stars: 10
- Arxiv ArticleDownloads an arXiv HTML article, converts it to markdown with pandoc, archives it, and returns a structured summary. Use when processing a single arXiv paper given its HTML URL (e.g., https://arxiv.org/html/2504.12345). Called by the arxiv-catchup skill but can also be invoked directly.Votes: 0GitHub stars: 10
- Representation Ethics> *"The question isn't whether we CAN simulate people. It's how we do it with dignity."* **Stack integration** (how this plugs into soul / mind / character / room / incarnation): [ETHICS.md](ETHICS.md) · Card: [CARD.yml](CARD.yml) ---Votes: 0GitHub stars: 56
- Play Learn LiftStart Playing. Keep Learning. Lift Others.Votes: 0GitHub stars: 56
- Place*Read [`GLANCE.yml`](GLANCE.yml) then [`CARD.yml`](CARD.yml) first. This is the protocol: how a place is keyed, how competing claims are held, and what may leave the repo.* `room` knows what is inside it and which way is out. `place` knows where it is. Almost everything on a map inherits both, and the combination is the normal case: ```yaml inherits: [coffeeshop, room, place] # a shop you can enter, at a tolerated address inherits: [room, place] # the same building after the s...Votes: 0GitHub stars: 56
- No Ai Slop> **"Don't be annoying. Don't make shit up. Ask when uncertain."** This skill covers EVERYTHING that makes AI annoying — not just writing style. ---Votes: 0GitHub stars: 56
- No Ai ParrotQuote clerk for the 'just a next token predictor' genre. Harvests, attributes and serves verbatim human text — both the clichés and the good human answers to them — for a human to select, copy and paste. Does not write the post.Votes: 0GitHub stars: 56
- Multi PresenceSame card active in multiple rooms simultaneouslyVotes: 0GitHub stars: 56
- ExperimentRun parameterized character simulations with structured output and evaluation.Votes: 0GitHub stars: 56
- DebuggingSystematic bug investigation with hypothesis trackingVotes: 0GitHub stars: 56
- Change NameChange a name, email address, phone number, handle, or any identifying string across the artifacts where it lives — starting with surgical, provenance-disciplined PDF editing: scan the file, describe what's found, discuss the changes, perform and verify them. Originals preserved, every change disclosed, institutional corrections pursued in parallel.Votes: 0GitHub stars: 56
- CauldronTwo-phase discipline for large cross-cutting technical plans. This file documents the full CAULDRON protocol: when to invoke, how each K-line works, how cauldron composes with the rest of MOOLLM, and a full worked walkthrough against the first real-world instance. **Classification: meta-orchestrator.** Cauldron is not a leaf skill — it sequences K-lines, iterates within them (SCRY loops, STIR turns, TASTE/STIR ping-pong), conditionally branches on state signals, composes sub-skill outputs int...Votes: 0GitHub stars: 56
- ResearchRun web and project research on a topic, producing a numbered report in cowork/research/ or a scoped research directory.Votes: 0GitHub stars: 2
- Paper Xray论文精读：把一篇论文讲透，不只是译出来。用户说“讲透这篇”“精读这篇”“这篇到底是怎么想出来的”“x-ray 一下”时使用——先通读全文含附录，还原作者真实的思考起点、押的那个赌注和证据落在哪，把每个符号和关键公式落到能自己动手算的小例子上，再怀疑式地过一遍超参、消融、基线和数字。产出写进 EasyRead 的页边讨论条目并锚到对应段落，也可以另存一份长文 Markdown。用于 精读论文、讲透一篇论文、还原作者思路、这篇论文哪里有问题、paper-xray、$paper-xray。不是摘要、不是逐段翻译、不是科普文。Votes: 0GitHub stars: 816
- Multi Source ResearchConduct deep, multi-source research by cross-referencing data from web search, news, social media, academic sources, and proprietary databases. Enforces APA 7th citations, evidence hierarchy, and 2-cycle verification per research theme. Built for competitive intelligence analyst workflows.Votes: 0GitHub stars: 2
- Knowledge Graph Curator> 版本：v1.0 | 分类：文化与组织运营 | 优先级：P1 > 作者：稷下 | 对标：Notion + Roam Research × Zettelkasten × 麦肯锡知识管理 > 触发场景：活动后24小时 / 项目复盘后 / 重要洞察产生时 / 定期知识梳理 ---Votes: 0GitHub stars: 2
- Global Talent RadarScan global talent markets via GitHub/Arxiv/LinkedIn APIs, build talent heatmaps with salary benchmarks, identify Tier S/A/B/C candidates. Use when: quarterly talent scanning, critical role hiring, competitive intelligence on talent pools. Includes real API integrations and data pipeline.Votes: 0GitHub stars: 2
- Res Survey DesignSurvey and questionnaire design — sampling plan, sample-size math, question wording, order and non-response bias checks, analysis-ready instrument. Use when user says "survey design", or needs quantitative validation of a hypothesis.Votes: 0GitHub stars: 3
- Res Research BriefResearch brief writing — turns a fuzzy topic into a scoped, decision-oriented brief with questions, success criteria, and an executable plan others can run. Use when user says "research brief", or needs to hand off a research task with clear scope.Votes: 0GitHub stars: 3
- Res Patent LandscapePatent landscape and freedom-to-operate analysis — IPC/CPC classification mapping, assignee and citation clustering, white-space and risk screening. Use when user says "patent landscape", "FTO", or before launching a product in a crowded tech field.Votes: 0GitHub stars: 3
- Res LitreviewStructured literature review — search strategy, inclusion/exclusion screening, quality appraisal, and synthesis map of a research field. Use when user says "literature review", "lit review", or needs to map what is already known about a topic.Votes: 0GitHub stars: 3