Research & Data
HR0101/company-analysis
業界別・希望職種別・選考フェーズ(ES・1次面接・2次面接・最終面接・オファー比較)別・新卒/中途別のパターンから選択して、一次情報(有価証券報告書・決算説明資料・中期経営計画・統合報告書・採用ピッチ資料)と参考情報としての口コミに基づく徹底的な企業分析と、競合差別化・約1分の自己紹介・志望動機・仮説検証型逆質問・想定質問100問の作成を行うスキル。ユーザーが企業分析、企業研究、業界・競合比較、IR分析、または特定企業の選考・面接対策を求めたときに使用する。
$ npx skills add HR0101/company-analysis-claudeombharatiya/ai-evals
Build, review and fix evals for LLM apps, RAG pipelines and agents the way the aievals.co guide teaches. Error analysis on real traces before any metric, code checks before LLM judges, one binary PASS/FAIL judge per failure mode, judges calibrated against human labels (PASS and FAIL recall, not agreement), train/dev/test splits, regression sets, Wilson intervals, and paired release gates in CI. Use when asked to add evals or tests to an LLM feature, write or debug an LLM-as-judge prompt, label or review traces, pick metrics or sample sizes, compare two prompts or models, check whether an existing eval can be trusted, or wire evals into CI.
$ npx skills add ombharatiya/ai-evals-skillsvlaskos/architecture-documentation-skill
Produce and review software architecture documentation grounded in open standards — ISO/IEC/IEEE 42010, the arc42 template, the C4 model, the 4+1 view model, and Architecture Decision Records. Use when you need to document a system's architecture, decide which views to write for which stakeholders, structure an architecture description, capture decisions with their rationale, or review existing architecture docs for completeness and clarity.
$ npx skills add vlaskos/architecture-documentation-skillNicoSKOOL/keyword-fanout-map
Use for keyword research: turning a seed keyword, business type or topic into an intent-clustered keyword map with real search volumes, AI search volume and the fan-out questions a page must answer. Step 1 of the 5-skill SEO system. Also use when asked what to write about, which keyword to target, or to find keywords for a page.
$ npx skills add NicoSKOOL/keyword-fanout-mapvlaskos/brief-to-architecture
Turn a raw brief, RFP, discovery transcript, or feature spec into an architect-grade analysis — the architecturally significant requirements pulled out and split into functional / quality-attribute / constraint, each sharpened into something testable, prioritised by business value and architectural impact, checked for requirements that quietly contradict each other, and turned into measurable quality scenarios with the design strategies that would satisfy them. Use whenever a brief, pre-sales input, RFP, discovery-call notes, kickoff document, or set of requirements needs to be assessed before estimation or design — and whenever someone asks what is architecturally significant here, what...
$ npx skills add vlaskos/brief-to-architecturetoyin-software-factory/audit
Run /audit on a greenfield project, an existing codebase with missing docs, or one area (/audit src/auth) to bootstrap the project's AI context, the AGENTS.md files every later skill reads. Writes tool agnostic AGENTS.md plus thin CLAUDE.md pointers, adding only what is missing; never overwrites curated content.
$ npx skills add toyin-software-factory/factory-templateshannonmcgivney/consent-audit
Audits a website or vibe-coded app (Lovable, Bolt, v0, Replit, Next.js, React, plain HTML) for tracking that loads or sends data BEFORE the visitor agrees in the cookie banner - ad pixels (Meta, Google, TikTok, LinkedIn), Google Tag Manager, analytics, session replay, chat widgets, embeds, hosting-injected analytics, and customer emails or IDs sent to trackers. Read-only - a code scan plus a live fresh-visit network check - ending in an inventory and a minimal fix list. Use when someone asks "is
$ npx skills add shannonmcgivney/consent-before-trackingmenhguin/how-to-do-good-research
Use when planning, doing, or writing scientific research.
$ npx skills add menhguin/how-to-do-good-researchenestanerr/prove
Audit a document claim by claim: recompute every number, read charts back against the text, and check that cited sources exist. Use when the user asks to audit, verify, fact-check or sanity-check a report, PDF, deck, spreadsheet or draft; asks whether the numbers add up; or is about to send a document that contains figures, charts or citations. Verdicts are computed by a bundled script, not by the model.
$ npx skills add enestanerr/Proveychu824/statecraft-research
Organises a group of agents to run a research survey using statecraft from ancient Chinese classics (The Art of War, Han Feizi, Zuo Zhuan, Strategies of the Warring States, Records of the Grand Historian). It uses independent scouting from several entry points, separate verification, and a report graded by evidence level. Use this skill whenever the user asks to survey or 调研 a research area, find research ideas, map related work for a paper, shared task or challenge, scout a field they are new to, or wants to surface things they don't know exist ("unknown unknowns") while keeping out hallucinated or irrelevant results. Use it even when the user doesn't mention agents or the classics, and even for a one-line request like "survey direction X for me" or "帮我调研一下 X 方向".
$ npx skills add ychu824/ancient-chinese-agent-skillsma455173220/materials-project-workflow
Plan and run project-specific ML, VASP and HPC materials calculations from a research goal, including selection, recovery, monitoring and usable results. Use for computational-materials project planning or active calculations; AiiDA is optional.
$ npx skills add ma455173220/materials-project-workflow-skillbuiltnotboosted/research
Finds and checks topics, stories, facts and figures for content, then hands over a sourced research brief that the writing and video-scripting skills build from. Use when someone asks what to post about, wants ideas or angles, asks to research a topic, check a fact or statistic, find out what their audience is searching for or asking, react to news or a data release in their industry, plan around a calendar of announcements, or build or tidy their list of trusted sources. Trigger phrases include "research this", "what should I post this week", "find me a story", "is this stat right", "what are people searching for", "react to today's news", "content ideas for", "fact-check this post" and "update my sources". Every claim it returns carries a named source and a date, and it never invents a figure, quote, review or story.
$ npx skills add builtnotboosted/built-not-boosted-skillsbbulman/create-survey
Write a survey whose every question feeds a decision, with the sample size and analysis worked out first.
$ npx skills add bbulman/research-skillsejklock/research-artifacts
Organize, format, and index research as OKF-conformant knowledge bundles — dated, sourced, append-only snapshots of the external evidence behind a decision (technology evaluations, library comparisons, industry-practice surveys). Use when recording research output, structuring a docs/research/ session, enforcing source discipline (primary sources, vendor-COI flags, inference-vs-fact labels, confidence levels), or wiring the research → decision → issue traceable chain. Pairs with deep-research (which gathers/verifies the evidence) and living-docs (which owns the ADR/issue artifacts research feeds into).
$ npx skills add ejklock/living-docs-skillbbulman/create-interview-script
Draft a short interview guide that gets real stories and tests what you actually need to know.
$ npx skills add bbulman/research-skillsbbulman/create-journey-map
Map what happens today, or what should happen in future, step by step, from your beliefs or from real research.
$ npx skills add bbulman/research-skillsZrobDev/sql-tuning
Use when a SQL query is slow, a plan shows Seq Scan or bad row estimates, EXPLAIN ANALYZE output needs reading, an index choice is unclear, OFFSET pagination degrades, an ORM issues N+1 queries, pg_stat_statements needs triage, or a BigQuery/Snowflake query scans too much. Postgres first.
$ npx skills add ZrobDev/data-engineering-skillsbbulman/create-diary-study
Plan a diary study people will actually finish, for behaviour that plays out across days or weeks.
$ npx skills add bbulman/research-skillsbbulman/affinity-diagram
Sort real research notes into the themes people actually share. Needs data to work from.
$ npx skills add bbulman/research-skillsZrobDev/etl-pipelines
Use when designing, reviewing or debugging batch ETL/ELT in Python - duplicate or missing rows after a rerun, double-counted backfills, watermark gaps, late-arriving data, retry storms, schema drift breaking a load, scrape-to-warehouse pipelines, a job that silently loads zero rows, or choosing between cron, n8n, Airflow and dlt.
$ npx skills add ZrobDev/data-engineering-skillsSaeedSheikhAmiri/ai-audio-models
Guidance for choosing, pricing, licensing, and comparing AI audio models across TTS, ASR, voice conversion, music generation, sound effects, singing synthesis, audio LLMs, and audio restoration. Use when a user asks which audio model or API to use, what it costs at their volume, whether a license allows commercial use, or how to assemble a speech/audio pipeline.
$ npx skills add SaeedSheikhAmiri/ai-audio-models-skillpwquint24/org-babel-r
Complete guide for data science, statistical computing, graphics devices, ESS integration, and reproducible research using R with Org Babel.
$ npx skills add pwquint24/org-babel-agent-skillsnova9/natural-academic-writing
Draft, revise, or critique academic prose while preserving meaning, evidence, and the author's voice. Use for research papers, theses, reports, literature reviews, abstracts, and academic paragraphs, including requests to make writing less formulaic, generic, inflated, or AI-like.
$ npx skills add nova9/natural-academic-writing-skillsvinesc1234/prompt-check
Use for almost any request for facts, research, analysis, comparisons, recommendations, advice, summaries or drafts, including short or casual-sounding ones like \"tell me about X\", \"why did X happen\", \"what's the best X\" or \"find stats on X\". Checks the request for gaps or wrong premises and asks before answering, then holds the answer to cited, verified, complete standards.
$ npx skills add vinesc1234/prompt-check-skill