Research Claude Skills
2 269 research skills from 396 authors. They find sources and get you up to speed on unfamiliar ground. Half of them fit into 2 278 tokens or less — that is what one costs your context window when the agent loads it. 663 ship runnable scripts rather than instructions alone. 4 of them cannot work without an MCP server, most often rube. We also found 264 copies of these same skills sitting in other people's repositories — counted once here, not 264 times.
2 269 unique 396 authors 1 169 updated this month 93 from vendors
| Apply a `citation-diversifier` budget report by injecting *in-scope* citations into an existing draft (NO NEW FACTS), so the run passes the global unique-citation gate without citation dumps.
|
| Generate and verify BibTeX entries from paper notes, writing `citations/ref.bib` and `citations/verified.jsonl`.
| Build a section-by-section claim–evidence matrix (`outline/claim_evidence_matrix.md`) from the outline and paper notes.
| Use when a broad paper candidate pool needs deterministic deduplication and a stable core set.
| Use when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.
| Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.
| Write the survey's front matter files (Abstract, Introduction, Related Work, Discussion, Conclusion) in paper voice, with high citation density and a single evidence-policy paragraph.
| Write one survey-quality paragraph from evidence packs (tension → contrast → evaluation anchor → limitation).
| Synthesize the shortlist into a discussion-ready research idea brainstorm memo, writing `output/REPORT.md`, `output/APPENDIX.md`, and `output/REPORT.json`.
| Generate a compact pool of discussion-worthy research directions from the signal table, writing `output/trace/IDEA_DIRECTION_POOL.md`.
| Map paper notes + taxonomy into a signal table of tensions, missing pieces, and promising academic axes for brainstorm discussion. Writes `output/trace/IDEA_SIGNAL_TABLE.md`.
| Rewrite limitation passages so the paper keeps limitations without falling into count-based slot phrases (e.g., \"Two limitations…\") across many H3s.
| Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report.
| Multi-route literature expansion + metadata normalization for evidence-first surveys.
| Use when `paper-review` needs a canonical manuscript text artifact before claim extraction.
| Use when `paper-review` needs overlap/delta positioning against provided related work.
| Write structured notes for each paper in the core set into `papers/paper_notes.jsonl` (summary/method/results/limitations).
| Deterministically compact final H3 bodies to the active delivery profile's paragraph budget without deleting prose or changing citation-block order.
| Write `output/DRAFT.md` (or `output/SNAPSHOT.md`) from an approved outline and evidence packs, using only verified citation keys from `citations/ref.bib`.
Run a research Workflow end to end when the user requests a survey, brief, review, tutorial, or idea exploration; route an unbound goal, execute one eligible Unit at a time, and stop at checkpoints or diagnosed failures.
| Remove repeated boilerplate across sections (methodology disclaimers, generic transitions, repeated summaries) while preserving citations and meaning.
| Use when `paper-review` has claims plus evidence gaps and needs the final referee-style report.
| Normalize cross-skill JSONL interfaces (ids + titles + citation key formats) so downstream skills do not rely on best-effort joins.
| Bind papers to chapter-level sections first, writing `outline/section_bindings.jsonl` and `outline/section_binding_report.md`.
| Map papers from the core set to each outline subsection and write `outline/mapping.tsv` with coverage tracking.
| Use when a `research-brief` workspace has a small paper set plus outline and needs a compact reader-facing briefing instead of a full survey.
| De-slot and harmonize paper voice across `sections/*.md` without changing meaning or citation keys.
| Polish a single H3 unit file under `sections/` into survey-grade prose (de-template + contrast/eval/limitation), without changing citation keys.
| Write survey prose into per-section files under `sections/` so each unit can be QA'd independently before merging.
| Identify survey/review papers in a retrieved set and extract taxonomy seeds into `outline/taxonomy.yml` (topics/subtopics/terminology).
| Build a 2+ level taxonomy (`outline/taxonomy.yml`) from a core paper set and scope constraints, with short descriptions per node.
| Draft non-prose visuals artifacts (timeline, figure specs) for a survey, grounded in evidence and using citation keys from `citations/ref.bib`.
| Fill `outline/tables_index.md` from `outline/table_schema.md` + evidence packs (NO PROSE in cells; citation-backed rows).
| Normalize terminology across a draft (canonical terms + synonym policy) without changing citations or meaning.
| 为中文毕业论文补强并核验引用：找出必须有引文支撑的句子，扩展候选文献，检查引用与论断是否匹配，并回写参考文献与正文引用。
| 将中文毕业论文已有材料映射到“毕业论文角色”：把论文、模板、Overleaf 源稿、PDF、图表和实验材料按章节角色、研究问题和证据用途重新归位。
Execute exactly one eligible Unit in an existing research Workspace; use for stepwise or manual semantic execution when status, Attempt, Artifact, Manifest, checkpoint, and acceptance evidence must remain synchronized.
Initialize a missing research Workspace from the repository template without overwriting existing Run state; use before Pipeline binding when the target under `workspaces/` has no valid core artifacts.
| 社会情感学习（SEL）专家系统——基于CASEL框架的完整知识体系与实践指南。 涵盖五大核心能力（自我意识/自我管理/社会意识/人际关系/负责任决策）、 课程设计、教学策略、评估工具及全球本土化实践。 触发词：「SEL」「社会情感学习」「情绪教育」「CASEL」「社交技能训练」 适用场景：教育工作者、家长、学校管理者、教育研究者
| 量子位（QbitAI，国内AI行业Top 1科技媒体）的AI科技自媒体创作思维——团队出品·数据驱动·速报+深析+智库三位一体。 触发词：「量子位视角」「像量子位那样写」「AI行业新闻快讯」「AI十大趋势」「AIGC全景图谱」「MEET智能未来」。 擅长：AI行业新闻快讯、深度特稿报道、产业研究报告（AI十大趋势/AIGC全景图谱）、年度大会内容框架、 行业人物深度专访、数据驱动新闻、短快讯50+条密集型更新。
Orchestrates a comprehensive research effort across multiple design systems/component libraries
| Audits how often deprecated CDS exports are actively used in customer codebases using Sourcegraph MCP search tools. Use this skill whenever asked to assess removal readiness for deprecated CDS APIs, investigate the blast radius of removing a deprecated component or hook, check Sourcegraph for customer usage of deprecated exports, or help the team decide which deprecated APIs are safe to remove in the next major version. Always invoke when asked to "audit deprecated APIs", "check Sourcegraph for deprecated usage", "find usages of deprecated exports", "analyze deprecation impact", or any similar request involving CDS deprecations and customer adoption.
Amazon keyword research and market opportunity analysis for sellers. Retrieve autocomplete suggestions (long-tail keywords), analyze competitor landscape, and assess market opportunity for any keyword on 12 Amazon marketplaces (US/UK/DE/FR/IT/ES/JP/CA/AU/IN/MX/BR). No API key required. Make sure to use this skill whenever the user mentions Amazon product research, finding products to sell on Amazon, Amazon keyword ideas, niche analysis, competition analysis for Amazon, market opportunity on Amazon, comparing Amazon keywords, evaluating whether a product is worth selling, Amazon autocomplete data, seasonal demand for Amazon products, or anything related to researching what to sell on Amazon — even if they don't explicitly say 'keyword research'. Also trigger when the user asks vague questions like 'is this a good product to sell?', 'what's the competition like for X on Amazon?', 'should I sell X or Y?', or 'what are people searching for on Amazon?'.
Profitable niche discovery for Amazon sellers. Identifies underserved markets with high demand but low competition. Analyzes market gaps, emerging segments, and untapped opportunities across categories. Use when the user asks about finding niches, profitable markets, underserved segments, market gaps, blue ocean opportunities, niche research, or what markets to enter on Amazon.
Use when the spoken content of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to summarize, quote, transcribe, translate, fact-check, or extract anything from a video. Also use for research or learning when a video is the source. Not for uploads or account management.
Use when a YouTube playlist is involved: pasted playlist links or IDs, requests to list playlist videos, browse playlist contents, or work through a playlist for transcripts or research. Also use when the user wants all videos from a series, course, or collection. Not for creating playlists or account management.
Use when the spoken content of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to summarize, quote, transcribe, translate, fact-check, or extract anything from a video. Also use for research or learning when a video is the source. Not for uploads or account management.