paper-to-theorem-distiller
Distill a dense theory paper into definitions, main claims, proof strategy, and reusable techniques. Use when reading theoretical ML or math papers efficiently.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
Writing & research
14,413 results
phd-application-package-auditor
Audit a full PhD or research-application package for coherence, missing evidence, narrative consistency, program fit, recommender risk, and deadline…
phd-program-fit-mapper
Map PhD applicant research interests to faculty, labs, departments, and program-fit evidence before writing school-specific application materials. Use this…
professor-cold-email-drafter
Draft, critique, and revise concise cold emails to professors for PhD applications, research internships, RA opportunities, lab rotations, or…
professor-research-direction-mapper
Define a professor's recent and trending research direction from publications, lab pages, grants, talks, students, and public materials before writing PhD…
proof-sketcher
Convert an informal mathematical idea into a precise theorem, lemma, or proof scaffold with explicit assumptions, dependency structure, and clearly marked gaps.
research-codebase-readme-writer
Write or audit a README.md for a research repository. Use this skill whenever the user wants to write, improve, fix, or review a README for a research codebase…
sop-writer
Write, review, score, improve, or iterate on Statements of Purpose and PhD application essays for research programs. Use this skill whenever the user is…
researcher
Delegate a deep research or survey task to Google's Antigravity CLI (agy staffer, fast Gemini). Use when the user says /agy:researcher, "ask agy to research",…
plan-newsletter
Plan a complete newsletter issue from a topic or idea, including research, draft, subject line, opening hook, and social promotion posts. Use when the user…
note-writer
Create Obsidian-compatible learning notes in Skill format. Use when requested to provide references, keywords, concept summaries, note creation, or knowledge organization. Supports various inputs such as text, URLs, images, and videos.
new-yorker-style
Write prose in The New Yorker's distinctive literary style. Applies the magazine's house conventions (diaeresis, British spellings, serial comma), elegant…
scientific-critical-thinking
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for…
scientific-writing
Write scientific manuscripts. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), abstracts, for…
brief
Interview for, draft from supplied material, or review a Writing Brief against the Library's writing-brief template of questions to answer before you write.…
autoresearch
Experiment loop discipline for autoresearch sessions — decision rules, git workflow, JSONL logging, benchmark metrics, anti-patterns
edgespeak-segment
Split a long run of text into natural sentences on-device via EdgeSpeak using a semantic sentence splitter that works on unpunctuated ASR output, or re-segment…
icc-jeanne-sulzer
Research, drafting, and analysis involving the International Criminal Court (Rome Statute system). Enforces a verification-first methodology — every case-law,…
writing-partner
Collaborative essay writing that preserves authenticity through structured interview, thread tracking, and voice calibration. Transforms AI from text generator…
zhihu-cli
Automate Zhihu (知乎) interactions including search, browsing hot topics, viewing questions/answers, posting pins/articles/questions, and user interactions. Use…
lov-anti-wechat-ai-check
Analyze articles for AI-generated content indicators and rewrite to pass WeChat's 3.27 non-human automated content creation detection. Checks for template…
lov-architecture-documentation
Generate architecture views, interface descriptions, and decision record drafts from the project's actual implementation. Supports explicit input and result read-back. Use to create architecture documentation from a codebase.
lov-article-creator
Uniformly create, rewrite, brand, or faithfully repost WeChat official account article packages: body writing invokes the single writing style and authorship capability, completing structure, branding, cover, 4:3 lead image, sources, and quality acceptance offline. Use when asked to write, brand, audit, or faithfully repost a WeChat article package.
lov-better-readme
Improve the README, installation instructions, usage examples, and real brand assets based on the project code. Support explicit input and reading back results. Use to create or improve a project README.