Get detailed information about a specific research finding or observation. Use when injected research mentions "[/research-detail ID]" for more sources and context.
Score 70/100
Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages.
Score 70/100
Loop 1 of the Three-Loop Integrated Development System. Research-driven requirements analysis with iterative risk mitigation through 5x pre-mortem cycles using multi-agent…
Score 70/100
Autonomous research pipeline — topic to structured documents with HTML/PDF output. Proven at HEL (28 docs, 91K words) and OOPS (9 docs, 20K words) scale.
Score 70/100
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair.
Score 70/100
Prepare ethics applications, develop informed consent protocols, and navigate institutional review processes for human subjects research
Score 70/100
Assists authors in researching topics, verifying facts, and ensuring accuracy in their writing. Particularly useful for historical fiction, non-fiction, science fiction, and any…
Score 70/100
Research-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.
Score 70/100
Build knowledge bases that build software — research before code, teach before execute
Score 70/100
Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance…
Score 70/100
Analyzes research hotspots and recommends literature based on a disease or topic. Use when the user wants to identify current research trends, hot topics, or get literature…
Score 70/100
Search and analyze research papers, find related work, summarize key ideas. Use when user says \"find papers\", \"related work\", \"literature review\", \"what does this paper…
Score 70/100
Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), or Perplexity sonar-pro-search (academic paper…
Score 70/100
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims,…
Score 70/100
Processes research branches from Claude Code Web sessions - merges content, moves docs to docs/research/, and creates GitHub issues.
Score 70/100
Research methodology in psychology. Covers experimental design (independent/dependent variables, random assignment, control conditions, between/within-subjects designs), research…
Score 70/100
中文优先：用于研究运维相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Evidence-first current-state research workflow for ECC.
Score 70/100
Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.
Score 70/100
Download academic papers from open-access sources when the user provides a DOI/arXiv ID or requests a keyword-based paper search, and return the saved PDF path.
Score 70/100
End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM.
Score 70/100
Research ML techniques, architectures, or papers relevant to the current task and summarize actionable insights.
Score 70/100
Create refined user personas from research data — 3 personas with JTBD, pains, gains, and unexpected insights.
Score 70/100
Full research pipeline: Workflow 1 (idea discovery) \u2192 implementation \u2192 Workflow 2 (auto review loop).
Score 70/100
Discovery group skill. Designs the evidence-gathering plan based on what access is actually available.
Score 70/100
Generates a comprehensive research proposal design based on input literature, including hypothesis, mechanism verification, and budget.
Score 70/100
Find research directions, labs, and mentors worth chasing by getting specific about problem, proof of interest, and the first room to enter.
Score 70/100
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review.
Score 70/100
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal…
Score 70/100
Get a deep critical review of research from Claude via claude-review MCP. Use when user says \"review my research\", \"help me review\", \"get external review\", or wants critical…
Score 70/100
Поиск научных статей, экспериментов и неочевидных данных по теме проекта. 3 угла: фундаментальные (высокоцитируемые), свежие (< 2 лет), неочевидные (counterintuitive).
Score 70/100
Setup wizard for the research pipeline. Detects infrastructure, configures vault, installs optional tools. Run once per vault, re-run to update.
Score 70/100
Research file storage conventions and templates for dokhak agents. Use when: (1) saving research results from research-collector or researcher agents, (2) reading cached research…
Score 70/100
Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation.
Score 70/100
Synthesize research findings from memory into structured reports with evidence grading, contradiction resolution, and actionable recommendations
Score 70/100
Researches infrastructure best practices and generates deployment-ready configurations, Terraform modules, Dockerfiles, and CI/CD pipelines.
Score 70/100
Research writing conventions for academic and professional contexts. Covers the research process (question formation, literature review, methodology, evidence evaluation),…
Score 70/100
Automatically activated when user asks "what's the best way to...", "how should I...", "what are best practices for...", or requests recommendations, industry standards, or proven…
Score 70/100
Use when planning features and need current API docs, library patterns, or external knowledge; when testing hypotheses about technology choices or claims; when verifying…
Score 70/100
Research GitHub, GitLab, and Bitbucket repositories using DeepWiki MCP server. Use when exploring unfamiliar codebases, understanding project architecture, or asking questions…
Score 70/100
Track manuscript resubmission deadlines and automatically generate phase-appropriate task breakdowns for academic researchers based on remaining time.
Score 70/100
Assesses whether study results are trustworthy by auditing design integrity, sample structure, statistical handling, bias control, validation chain, and claim discipline.
Score 70/100
Use when experiments complete to judge what claims the results support, what they do not, and what evidence is still missing.
Score 70/100
Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state.
Score 70/100
When the user wants to research customer pain points, complaints, or sentiment using review platforms like Trustpilot, G2, Capterra, or app stores.
Score 70/100
Builds prioritized manuscript revision plans for major or minor revisions by separating comments that require experiments, analyses, clarification, restructuring, or wording…
Score 70/100
Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument…
Score 70/100
Phase 1 — Market research and idea discovery via store top charts and competitor analysis.
Score 70/100
Specialized research and analysis prompt methodology for Claude. Provides 11 tested approaches (3 identity, 4 reasoning, 4 output) for data analysis, policy research, systematic…
Score 70/100
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API.
Score 70/100
Sustained metric-improvement loop with atomic commits, auto-rollback, and experiment logging. Iterates with specialist agents, commits atomically, auto-rolls back on regression.
Score 70/100
Use claude-code-my-workflow when a research task needs a Claude Code workflow for papers, slides, data analysis, or replication packages with specialist-agent review and…
Score 70/100
Turn Claude Code into a command-driven workflow surface for research, planning, implementation, testing, and review instead of steering every step ad hoc.
Score 70/100
Use Open Deep Research when an agent should run a configurable research job that searches, compresses, synthesizes, and writes a cited report across multiple model and search…
Score 70/100
Deploy and run ML experiments on local or remote GPU servers. Use when user says \"run experiment\", \"deploy to server\", \"\u8dd1\u5b9e\u9a8c\", or needs to launch training jobs.
Score 70/100
Submit a training job to the Databricks GPU cluster, wait for results, and pull MLflow metrics back locally.
Score 70/100
Build repeatable evaluation experiments for agents and LLM apps with output checks, trajectory scoring, simulators, and trace-based review.
Score 70/100
Give an agent curated scientific workflows, databases, and domain-specific guidance when general prompting is not reliable enough for research-heavy work.
Score 70/100
Execute chaos engineering experiments to test system resilience. Use when performing specialized testing.
Score 70/100
Research market rates, build negotiation strategy, and create counter-offer scripts
Score 70/100
Schema.org research assistant for Logseq Template Graph. Investigates Schema.org classes and properties, suggests standard vocabulary, validates hierarchies, and provides…
Score 70/100