Research & Search

runchuan-bu Skill

Search PubMed for scientific literature. Use when the user asks to find papers, search literature, look up research, find publications, or asks about recent studies. Triggers on "pubmed", "papers", "literature", "publications", "research on", "studies about".

youliang-zhu Bundle

Calibrate a learner's existing knowledge before researching and explaining a technical question. Use when the user wants an adaptive learning or research workflow that distinguishes basic cognition from deep investigation, explains unfamiliar field jargon, prioritizes recent primary sources for current practice, uses high-quality Chinese explainers or technical blogs for intuition, and provides auditable quotations and source locations without over-researching settled basics.

hacker-valley-media Skill

Choose the right Interceptor surface. Use interceptor-browser for page DOM, network, browser tabs, rich editors, screenshots, and browser automation. Use interceptor-macos for native apps, browser chrome, URL bars, OS dialogs, cross-app routing, AX trees, native screenshots, Apple Events, trusted OS input, macOS Electron CDP/app web-content control, and in-process app runtime control. Use interceptor-ios for apps on an owned, unlocked, Developer-Mode iPhone. Use interceptor-research for deep multi-source web research. Background-first by default; focus changes require explicit opt-in.

hacker-valley-media Bundle

Deep web-research methodology for the interceptor browser surface — investigate a topic the way researchers, intelligence analysts, investigative journalists, private investigators, and OSINT operators do, not 'read 3 links and summarize.' Use when the task is research, deep research, investigate, go deeper, be thorough/exhaustive, OSINT, due diligence, competitive analysis, literature review, background check, dig in, or 'find everything about X.' Drives interceptor-browser verbs (websearch/open/read/find/inspect/net/eval/tab) with a planner loop, query-craft filters, a per-page escalation chain, pivot-chaining, an on-disk source ledger, and adversarial verification. Do every fetch and search through interceptor — never WebFetch/WebSearch. Pull the playbook any time with `interceptor research`.

tyrchen Bundle

Vendor reference repos as git submodules under ./vendors and produce deep research memos under ./docs/research covering architecture, design, key data structures, and load-bearing algorithms. Use whenever the user says "do research on X", "study how Y works", "submodule this repo and look into it", "understand the design of Z before we start", "spike on …", references prior-art crates / repos that should be evaluated, or asks to refer to ./vendors before designing or implementing. Trigger even when the user does not say the word "research" if they paste GitHub URLs and ask Codex to learn from them, compare alternatives, or extract patterns.

jtenniswood Bundle

Summarize user-facing changes made to this project over the last 7 days. Use when the user says "/updates", asks for recent updates, weekly updates, release-style highlights, or wants a concise feature summary ordered by importance.

parcadei Skill

Exploratory research via Ouros RLM — token-efficient reasoning with persistent REPL state

maskshell Bundle

cross-source-review — a same-family (同源, fresh-context) + different-family (异源) cross multi-round review engine that drives a doc-shaped artifact to SUBSTANTIVE convergence. Use it when a high-quality document needs adversarial cross-source review to convergence — "cross-review this requirements doc", "converge this design doc", "异源 review this spec/wiki page", "drive 同源+异源 review on this artifact". Produces a converged artifact + an honest convergence-record. NOT for code review (route to parallel-development), spec/arch-design authoring (blueprint-crafting), or research gathering (blueprint-crafting researcher). Does NOT judge whether the doc is "right" (outcome-axis — human). Phase A activation is EXPLICIT invocation (`/cross-source-review`); auto-routing is deferred.

dahls Bundle

Use when a structured search of research literature is called for — building a systematic-review search strategy, translating a research question into bibliographic database queries, picking specific target papers directly, chasing a paper's citations and authors, when a literature search returns far too much or mostly off-topic material and search terms must be kept, changed, or removed, or when an already-exported result set must be mechanically screened down to on-topic records.

reebeecka Skill

Summarize the current chat as a searchable SESSION_TREE (decisions, parked items, state, files) so later agents can grep the transcript; optionally write a gitignored handoff file for a brand-new chat. Use when the user asks for a session tree or handoff, after close-ticket, or when the conversation is getting long — offer before writing in the long-chat case.

s3644 Bundle

Academic deep research assistant. Use when the user needs: literature review, systematic review, research question formulation, fact-checking claims, Socratic guided research dialogue, evidence synthesis, methodology design, or APA 7.0 research reports. Triggers: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, methodology, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 系統性回顧, 引導我的研究, 幫我釐清.

s3644 Bundle

Academic paper writing assistant. Use when the user needs: write a paper, guided paper planning, paper outline, revision based on reviewer comments, abstract writing, literature review paper, citation format conversion, citation checking, AI disclosure statement. Supports 6 paper types (IMRaD, Lit Review, Theoretical, Case Study, Policy Brief, Conference), 5 citation formats (APA 7, Chicago, MLA, IEEE, Vancouver), bilingual abstracts (EN + 中文). Triggers: write paper, academic paper, guide my paper, draft, revise, abstract, convert citations, check citations, AI disclosure, 寫論文, 學術論文, 引導我寫論文.

s3644 Bundle

Systematic literature review specialist. Use when the user asks for: literature review, survey of papers, related work analysis, research gap identification, annotated bibliography, paper collection, literature synthesis, or scoping review. Triggers: literature review, survey papers, related work, research gap, systematic review, annotated bibliography, literature synthesis, collect papers, find papers on, what is known about.

yaacovcorcos Bundle

Search and synthesize biomedical literature for medical, clinical, epidemiologic, public-health, and translational research questions. Use when the user asks what the literature says, asks for evidence on a medical claim, wants PubMed or biomedical database searching, asks for a literature review, or needs studies found, screened, compared, or summarized. Do not use for patient-specific diagnosis or treatment advice.

sipengxie2024 Bundle

Use when starting complex multi-step tasks, research projects, or anything needing >5 tool calls. Provides the persistent .planning/ directory used as on-disk working memory across sessions.

skygazer42 Bundle

Research a question on the live web and write a concise answer grounded in traceable sources.

lucadominguez Skill

arXiv Research

lucadominguez Skill

Polymarket — Prediction Market Data

lucadominguez Skill

Blogwatcher

014-code Bundle

Use this skill when asked to review a small service and summarize its important modules.

archit-13028 Skill

Write a conventional commit message from a git diff. Use when the user asks to commit, write a commit message, or summarize staged changes.

aojili Bundle

Analyze any user decision, choice, tradeoff, option selection, or whether-to-do-something question. Use when the user asks for decision help, wants a recommendation, or invokes decision-advisor. The workflow clarifies the decision, candidate options, background, purpose, core question, jurisdiction, constraints, and decision weights; runs research-backed analysis through economics, strategy, psychology, risk management, legal/regulatory, and technical feasibility lenses; applies critique-revision loops; and returns a clear recommendation, alternatives, action plan, and review signals.

akijain2000 Skill

Draft, review, evaluate, and improve SKILL.md files using a compiled knowledge base of best practices and anti-patterns. Use when writing a new skill, reviewing an existing one, measuring skill behavior, or debugging why a skill does not trigger.

srid Skill

Enter talk mode — conversation and research, no repo changes

fuzhiyu Bundle

Guide for rigorous economic data analysis. Use PROACTIVELY whenever performing data analysis on economic or financial datasets — importing, cleaning, merging, constructing variables, or producing summary statistics. Three core principles: (1) describe before and after every transformation, (2) document in jupytext percent format with interleaved code/narrative/outputs, (3) validate against economic intuition, literature, and cross-variable relationships. Includes pitfall checklists for merges, aggregations, filtering, and variable construction. Language-agnostic (Python, Julia). Trigger: any data analysis task involving economic, financial, or panel data.

jwilger Skill

Use this skill for ADRs, architecture choices, technology selection, boundaries, and updates to `docs/ARCHITECTURE.md`. It keeps research ahead of prose and requires explicit approval before a decision is treated as merged.

pskoett Skill

Ensures alignment between user and Claude during feature/spec planning through a structured interview process. Use this skill when the user invokes /plan-interview before implementing a new feature, refactoring, or any non-trivial implementation task. The skill runs an upfront interview to gather requirements across technical constraints, scope boundaries, risk tolerance, and success criteria before any codebase exploration. Do NOT use this skill for: pure research/exploration tasks, simple bug fixes, or when the user just wants standard planning without the interview process.

nealcaren Bundle

R statistical analysis for publication-ready sociology research. Guides you through phased workflows for DiD, IV, matching, panel methods, and more. Use when doing quantitative analysis in R for academic papers.

nealcaren Bundle

Find scholarship on a topic via OpenAlex and Crossref and add the chosen works straight into the user's local Zotero library (by writing zotero.sqlite directly). Use when the user wants to search the literature and capture references (NOT to screen, annotate, or synthesize them). Adding items requires Zotero to be closed.

nealcaren Bundle

Computational text analysis for sociology research using R or Python. Guides you through topic models, sentiment analysis, classification, and embeddings with systematic validation. Supports both traditional (LDA, STM) and neural (BERT, BERTopic) methods.

nealcaren Bundle

Stata statistical analysis for publication-ready sociology research. Guides you through phased workflows for DiD, IV, matching, panel methods, and more. Use when doing quantitative analysis in Stata for academic papers.

t3chnaztea Skill

Use when [the specific situations, symptoms, and phrases that should trigger this skill]. Pack the words someone would actually type when they want this. Describe ONLY when to use it, never summarize the workflow inside. Keep the whole frontmatter under 1024 characters. End by naming what this skill is NOT for, pointing at the sibling skill that covers it.

learnprompt Bundle

Turn multiple GitHub release notes or version-update notes into a Chinese weekly release digest or changelog roundup. Use when the user wants a multi-version weekly release summary. Do not use for single-note copyediting, wording review, or generic team or meeting weekly reports.

jennie-shawn Bundle

Create, inspect, and maintain a local StarWork project knowledge base with `starwork knowledge`, focused on long-term stable project knowledge.

jwynia Skill

Diagnose research quality and guide systematic query expansion. Use when starting research on any topic, when stuck in research, or when unsure if research is complete.

jwynia Skill

Verify claims in generated output against sources. Use as a separate pass AFTER content generation to catch hallucinations. Critical constraint - cannot be reliably combined with generation in a single pass.