Research & Search

nvidia Bundle

Queue deep, multi-step research and analysis tasks to the DeepAgents worker. Supports execution depth presets, request-specific rubrics, SubAgent delegation, and RubricMiddleware cross-validation.

nvidia Bundle

Read and summarize Slack channel history from inside the NemoClaw sandbox.

magnus919 Bundle

Use when exploring adjacent ideas, overlooked angles, or lateral research paths without prematurely collapsing into a single answer.

sidsaladi9 Skill

Create evidence-based user personas — or honest proto-personas when data is thin. Use when someone says "create a persona", "build user personas", "proto-persona for X", "who are our users", or "turn this research into personas". Focuses on goals, jobs-to-be-done, pains, and real behavior, then shows how to use personas to make product decisions.

sidsaladi9 Skill

Build a customer journey map across stages — actions, thoughts, emotions, touchpoints, pain points, and the single biggest opportunity per stage — grounded in evidence with assumptions flagged. Use when someone says "map the customer journey", "build a journey map", "where do users drop off", "what's the experience from awareness to renewal", or "turn this research into a journey".

sidsaladi9 Skill

Turns a list of shipped changes into audience-tiered release notes — a benefit-led user-facing changelog, a what/why/impact internal log, and a short social announcement cut. Use when you say "write release notes," "draft the changelog," "we just shipped X, announce it," "turn these tickets into release notes," or "summarize this release for customers and the team."

viasrijan Skill

---

viasrijan Skill

---

onedro1d Bundle

Parse a video (mp4/mov/webm) into a transcript + timestamped frames so Claude can consume it, then extract context — specifically Dark Factory requirements — from it. Use when given a recording, demo, app walkthrough, screen recording, or "video" to summarize or turn into requirements/specs; when asked to "watch", "process", "consume", or "transcribe" a video; or to extract requirements/context from a demo for a dark factory build (PO vision, data contracts, validation rules, test scenarios).

traygerbig Bundle

7-mode intelligent summarizer with Chain-of-Density, 8 languages, and smart caching

jperrello Bundle

Animate the title as a COLD OPEN in the TOP banner over the live opening footage — no blocking center card — held until TITLE_SWAP (default 2.0s) so brand-overlays can hand off to the source citation in the same slot. Frame 1 stays content (a face mid-sentence) to protect the swipe-rate / "Stayed to Watch" signal. ONE animation for every short — the glitch style (RGB-split banner + scanline tear, style-matched zap/crackle SFX) — a PIL frame sequence anchored at TITLE_ANCHOR_FRAC (default 0.135).

lazygophers Bundle

SKEIN planning 独立入口: 建 task→填 TaskSpec→research 分流→subtask DAG 拆分→grill 硬门→confirm 人审。工件写法见 references/plan.md, 调度模型见 references/dag.md。skein-flow 在 $1=plan 或含 --plan 时路由到本 skill。

lazygophers Bundle

This skill should be used when the user asks to "research X", "deep dive into X", "compare A vs B", "evaluate this project", or requests evidence-backed technical research, architecture review, or technology selection.

lazygophers Bundle

This skill should be used when the user needs to plan a research investigation or clarify research scope and questions. Typical triggers include creating a research plan, defining research questions, or structuring a study. Use when planning or scoping research tasks.

lazygophers Bundle

This skill should be used when the user needs to synthesize research evidence into conclusions and recommendations. Typical triggers include summarizing evidence, reconciling conflicting sources, or deriving recommendations.

mannnrachman Skill

Deprecated — forwards to bmad-deep-recon (domain type)

mannnrachman Skill

Deprecated — forwards to bmad-deep-recon (market type)

mannnrachman Bundle

Check that planning is complete enough to implement, then generate the sprint status file from the epics. Can also summarize sprint progress and validate or repair the tracking file. Use when the user says "run sprint planning", "generate sprint plan", "check implementation readiness", "show sprint status", "validate sprint status", or "fix sprint status"

mannnrachman Skill

Deprecated — forwards to bmad-deep-recon (technical type)

panjose Skill

Generate a `ResearchPlan` from `input.md` or equivalent raw research input.

panjose Skill

Run the canonical literature search bridge for one evidence query and persist traceable evidence artifacts.

panjose Skill

Interpret the user's high-level research intent into `RUN_POLICY.yaml` and `state/POLICY_DECISION.json`.

panjose Skill

Run the full literature-grounded review for a hypothesis.

panjose Skill

Summarize the completed reviews for a hypothesis.

panjose Skill

Generate exactly one grounded child hypothesis by strengthening evidence, specificity, and literature support.

panjose Skill

Generate exactly one literature-grounded hypothesis candidate for the active round.

panjose Skill

Start one Co-Scientist run from Codex using a research goal or imported brief.

neuroaihub Bundle

Core scientific methodology principles: research planning, method justification, assumption checking, and human-in-the-loop decision making for cognitive science and neuroscience

neuroaihub Bundle

Domain-specific statistical power analysis guidance for cognitive and neuroscience research, encoding effect size priors and sample size recommendations by modality

neuroaihub Bundle

Expert guidance for selecting and parameterizing cognitive psychology experimental paradigms based on research questions

neuroaihub Bundle

Advises on when to use DDM vs. LBA vs. race models for choice-RT data based on experimental design and research goals

neuroaihub Bundle

Domain-validated guidance for SEM-based mediation analysis of creative self-efficacy and moderation by baseline creativity in AI-augmented creativity research

qihangzhang-272 Bundle

Use when the user asks to 搜一下、调研、找资料、沉淀素材、补截图、做产品事实收集、投资/OSS research、公众号选题搜索、写作前第 0 步，或需要在写作/产品分析前建立可复查的 evidence folder.

qihangzhang-272 Bundle

Use when the user asks to 批量抓取或导出微信公众号历史文章、建立对标账号语料库、按日期或原创标记筛选公众号内容、批量处理 mp.weixin.qq.com URL，或把账号级素材交给公众号选题研究。该技能只采集并规范化获准访问的公开文章语料，不写文章、不推断私有指标、不发布内容。

rocm Skill

Use when user wants to list, analyze, review, or summarize GitHub PR comments on a pull request number or URL

davila7 Skill

Summarizes uncommitted git changes in a concise machine-readable format. Use in CI pipelines, scripts, or headless invocations where the output will be piped or captured.