Research & Search

matthull Skill

Transcribe a YouTube video and do something with the transcript. Wraps youtube-to-signal. Use when a YouTube URL appears and the user wants to work with its content — summarize, analyze, extract quotes, review, or anything else.

matthull Skill

Divergence before convergence — generate maximally independent candidates to escape mode collapse. Use when choosing among approaches and premature convergence would be costly (UX design, architecture, research angles, communication strategies).

microclaw Skill

Research a topic and produce a ready-to-listen podcast episode (a single audio file). Use when the user asks to make a podcast, generate an audio episode, a daily news digest in audio, a two-host show, or 'read this to me as a podcast'. Writes a spoken script then calls the generate_podcast tool to synthesize and stitch one mp3. Triggers on mentions of podcast, audio episode, news digest, narrate, two hosts, radio show, 播客, 做一期播客, 生成播客, 音频节目, 每日新闻播报, 双主播.

microclaw Skill

Investigate a question across multiple web sources, cross-check claims, and synthesize a cited answer. Use when users ask you to research a topic, compare options, find out 'what's the latest on X', verify a claim, or gather evidence before deciding. Uses the web_search and web_fetch tools (no API key). Triggers on mentions of research, look into, find out, compare, latest on, evidence, sources, fact-check, 调研, 研究一下, 查一下, 对比, 求证, 最新进展.

microclaw Skill

Condense long text, articles, threads, documents, or transcripts into a faithful short summary at the requested length and focus. Use when users paste a wall of text or a link's content and want the gist, key points, TL;DR, or a one-line takeaway. Triggers on mentions of summarize, summary, TL;DR, key points, gist, takeaways, condense, in short, 总结, 概括, 摘要, 要点, 提炼, 长话短说.

microclaw Skill

Run contract-governed deep research with parallel investigators, an adversarial verifier, and a cited synthesis. Use for high-stakes or broad research requests that need source independence, conflict detection, and explicit evidence quality. Triggers on deep research, comprehensive research, investigate thoroughly, 深度调研, 深入研究, 全面调查.

ocean326 Bundle

搜索 arXiv 论文并输出标题、作者、摘要和链接，适合研究主题跟踪和论文初筛。

hsigstad Skill

Create a new research idea with YAML frontmatter and add it to ideas/index.md. Use when the user wants to record a new research idea.

hsigstad Skill

Regenerate each project's docs/refs/manifest.toml from the workspace citation registry. Walks docs/ and paper/ for [ns:key] tokens with external namespaces, looks each up in research/refs/registry.toml, and writes the public-facing subset (title + description, no internal paths) to the project manifest. Use when the user invokes /cite-sync, /cite-sync <slug>, or asks to 'sync the manifest', 'rebuild the refs manifest', 'regenerate citations manifest'.

hsigstad Skill

Discover academic literature for a project: search APIs, curate relevant papers, write literature.md + bib entries, download PDFs. Use when user wants to find, update, or expand a project's literature review.

hsigstad Skill

Scaffold a new research project from materials the user has placed in a folder under projects/. Reads existing files to extract context instead of asking questions. Use when the user wants to create a new research project.

hsigstad Skill

Read raw entries in research/rules/writing_feedback_log.md, cluster them by tag, propose concrete edits to writing_style.md (general baseline + workspace overlay + per-section files), and let the user approve a batch. Flips status of consumed entries to distilled or rejected. Use when the log has accumulated enough raw entries to be worth turning into rules.

imbue-ai Bundle

Compare and rank multiple proposals (experiments, literature searches, and solution candidates), separating solution candidates from other proposals.

imbue-ai Bundle

Determine the type of proposal given, execute/delegate accordingly, and return the appropriate resulting ID (experiment ID, literature search ID, or solution ID).

imbue-ai Bundle

Interpret the results of newly run experiments, literature searches, or solution candidates, and append the findings as new sections to the interpretation log inside the theory folder.

imbue-ai Bundle

Search arXiv for relevant papers, download papers, and produce a structured literature review

imbue-ai Bundle

Run a targeted literature search on specific findings or questions that emerged during theory development

imbue-ai Bundle

Design and propose the next step: either a regular data-gathering experiment, literature search, or a concrete solution candidate.

imbue-ai Bundle

Summarize the current research status

imbue-ai Bundle

Score and rank solution candidates relative to the research goal, and update parent theory scores.

imbue-ai Bundle

Summarize the current goal progress

jimweller Bundle

Web research via OpenAI GPT-5. Use for current info, technical docs, and any research needing live web data.

xingfanxia Bundle

Use this skill to analyze a secular technology/industry trend, supply chain, company, or public investment thesis using a Serenity-style bottleneck research process. The skill converts a broad narrative into concrete constraints, evidence gates, disconfirmation tests, and next primary-source checks. It must not be used to copy trades, produce buy/sell signals, or treat social-media posts as proof.

karlorz Skill

Source-triaged research across local files, docs, repos, and current facts. Use for deep research, comparisons, or latest versions.

karlorz Skill

Dev-channel source-triaged research across files, docs, repos, and current facts. Use for deep research or latest-version questions.

mattforni Bundle

Group trip and getaway planning. Scope the trip, pull live lodging availability, present options with per head cost, verify before booking, research the constraint that actually drives the trip (weather windows, permit and reservation release dates, access rules), hand off the booking, then capture a trip doc and schedule the time sensitive follow ups. Use this skill whenever Forni mentions planning a trip, a getaway, a group house, a cabin or Airbnb or VRBO for a crew, a basecamp for a race or hike or backpacking objective, finding lodging for friends, splitting a house, acclimation lodging, or asks "where should we stay", "find us a place", or "book the house" for an upcoming adventure. Also trigger for "/assist:plan-trip", "plan the Aspen trip", "find a house for the boys", or "we need a place for the loop weekend". Trip records live under `~/Eudaimonia/Craft/Adventure/`; this skill is the workflow counterpart to the Adventure planning conventions documented there.

mattforni Bundle

Drain the work search queue. Consume Queued roles from the FY27 work search log and produce a complete application package per role, one at a time, in this order - fit sanity check, cover letter, application question responses, hiring manager research, follow-up email draft - then move the row to Applied once Forni confirms submission. Use whenever Forni says "apply to the queue", "run the applications", "apply to <company>", or Queued rows exist after a recruiter sweep. Replaces the retired job-apply skill.

paulkinlan Skill

Review existing documents, reports, and references on a topic to synthesize findings and identify gaps

paulkinlan Skill

Conduct structured research producing organized notes with sources

oimiragieo Skill

tensor-grep research frontier

oimiragieo Skill

Use when you have a hunch, a candidate optimization, a novel technique, or an "I think X is faster/better/possible" idea for tensor-grep and must turn it into an ACCEPTED result or a DOCUMENTED RETIREMENT — the research discipline. Covers the evidence bar (one mechanism must explain every observation INCLUDING the negatives, and survive an assigned adversarial refutation whose every claim cites file:line), predicting the number + noise band BEFORE you run, the idea lifecycle (experimental default-OFF -> dogfood/benchmark -> council-verify -> conscious flag-flip to adopted OR retirement recorded in docs/PAPER.md so it is never retried), verifying an AI-drafted plan against real code, and where good ideas actually come from. The scientific-method META sibling to change-control (gates) and research-frontier (targets).

siddsachar Skill

Strategic patterns for effective browser automation — research, forms, and data extraction.

siddsachar Skill

Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.

parcadei Bundle

Document codebase as-is with thoughts directory for historical context

faaz17 Skill

Draft cold emails to several companies in one session for one person, each individually researched and never templated. Use when a batch of outreach is planned. Respects the five-per-day cap and stops early if research quality drops.

faaz17 Skill

Research a target company and write a dossier into shared/companies/ — what they actually build, which team an intern would join, recent specific news, and the overlap with the candidate. Use before writing any first-contact email, when deciding whether a company is worth targeting, or when preparing for an interview.