Create a pricing and packaging hypothesis, research plan, and low-risk validation path tied to customer value and unit economics.
Generate a consultant-grade strategic intelligence brief on a company. Long-running (35-120 min) and metered ($0.10-$5).
Search patent databases and academic literature for prior art relevant to an invention. Use when user says \"现有技术检索\", \"prior art search\", \"专利检索\", \"check patents\" — from…
Install or reconcile research-project safety rules and protected folder boundaries for data, code, outputs, and paper sources.
Run the proofreading protocol on documents. Checks grammar, typos, overflow, consistency, and academic writing quality for .tex, .qmd, .typ, and .md files.
Audits all SEO changes made to a domain within a given period (read-only). Reconstructs change history from cache, Shopware updatedAt fields and crawl diffs when logs are missing.
Use when initializing, adding, updating, deleting, or linting a package's state-backed Analysis view, or when distilling an evidence-backed insight into a package Rule.
Research and compare the Stateless Agent Methodology (SAM) against other methodologies using only verifiable reference material.
Full pipeline: decompose a broad goal into sub-plans, draft each with adversarial review, then execute all of them autonomously via /run-plan. One command, walk away.
Use when the user invokes /research-auto or asks to run an autonomous research campaign over one committed Direction toward a measurable gate.
Gather facts and context from codebase, docs, and web,... Use when exploring patterns, finding implementations, looking up documentation, or researching before decisions.
Research a chef from a taxonomy YAML using 4 sequential agent teams (2 researchers + 1 synthesizer each) to produce a completed research profile
Pesquisa etimologia de caracteres chineses consultando 7 fontes acadêmicas (MDBG, chardb/xiaoxue Academia Sinica, hanziyuan, shuowen.org, CantoDict).
Research a task, problem, bug, or feature by exploring the codebase. Use when starting new work, encountering bugs, or needing to understand how existing implementation r — from…
Research a task, problem, bug, or feature by exploring the codebase. Use when starting new work, encountering bugs, or needing to understand how existing implementation r — from…
Research a batch of companies in parallel using background subagents. Demonstrates the file-based result passing pattern to avoid context overflow.
Strategic research companion — brainstorm, evaluate, and decide on research directions. TRIGGER when the user wants to brainstorm research, evaluate research ideas, do project…
Comprehensive multi-source research with academic depth. Searches web, social platforms, news, academic databases, and GitHub.
Document Q&A with visual citations. Parses a folder of PDF/DOCX/PPTX/XLSX/images via LiteParse, answers a question, generates an HTML report with page screenshots and bounding-box…
Evaluate a research source from report_notes, understand its purpose, and create a Linear issue.
Validate and enforce standard YAML frontmatter on research documents with JD-aware path resolution. Use when creating, editing, or validating research files, when user mentions…
Technical research methodology using Context7, Exa, and Sequential Thinking for documentation, best practices, and complex investigations.
Builds ideal customer profiles and buyer personas from real voice-of-customer evidence — demographics, pain points, jobs-to-be-done, decision psychology, and online habitat for a…
Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset
Quick entry point for structured knowledge elicitation with epistemic tracking. PROACTIVELY activate for: (1) interviews and requirements gathering, (2) problem definition, (3)…
Map market landscape, competitive dynamics, TAM/SAM/SOM sizing, whitespace opportunities — every claim sourced, adjacent competitors checked, sizing shown with methodology.
Use when creating or materially restructuring a state-backed research package from a ratified Direction or explicit package input.
Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop) → Workflow 3 (paper writing, optional).
Turns the operator's own platform evidence — owned analytics, public metrics, manual exports, and prior eval outcomes — into a sourced per-platform evidence base across X,…
Coleta e organiza informacao tecnica multi-fonte antes de escrever docs, PRDs, ADRs ou artigos. Busca em: docs oficiais, GitHub (repos + issues), Stack Overflow, papers e blogs de…
Discovers what's working right now on short-form video platforms (TikTok, Instagram Reels, YouTube Shorts; X and LinkedIn video by opt-in) for a given topic and market — mines…
類似 DAW / CLAP ホスト / Rust オーディオプロジェクト（clap-host, clap-validator, clack, nih-plug, Meadowlark 等）のソースコードと CLAP / cpal / eframe の公式リファレンスを調査し、 実装方針レポートを出力する。…
Synthesize user research into themes, insights, and recommendations. Use when you have interview transcripts, survey results, usability test notes, support tickets, or NP — from…
Execute a research task using compositional workflow planning. Characterizes the task, selects an approach from a library of research strategies, executes it, and self-evaluates…
Multi-step research orchestration. Use when user asks "research X", "summarize current state of Y", "what's the latest on Z", or compares approaches.
Crawl and collect resources for a financial research topic using Exa with full HTML and chart extraction.
Conducts extensive web research on technical topics with validated references and citations. Use when you need external documentation, library comparisons, or best practices…
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle.
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle.
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never…
Deliver a mid-draft adversarial review of a paper — runs paper-critic + domain-reviewer + claim-verify + blindspot in parallel, optionally adds clarity-reviewer, then…
Comprehensive manuscript review covering argument structure, technical methodology, citation completeness, and potential referee objections
Systematic root-cause debugging for a failing test, production bug, flaky behavior, or unexplained error.
Run hypothesis-evolution round on a completed deep-research run. Mutator persona generates child hypotheses from top-Elo parents; children re-enter tournament.
Full research workflow orchestration from knowledge elicitation to consolidated findings. PROACTIVELY activate for: (1) end-to-end research projects, (2) comprehensive analysis,…
Set up runlab for this athlete — choose a data source, prove it can actually deliver, create the data root, and run the first import.
Comprehensive open data directory (100+ datasets across 14 categories) with auto-fetch capability, plus data collection instrument design, variable dictionaries, data management,…
Conduct exploratory data analysis (EDA) before hypothesis testing. Run when the user has a dataset and needs to load data, build the analytic sample, diagnose missing data,…
Draft, revise, or polish any section of a social science manuscript — Introduction, Theory, Methods, Results, Discussion, Abstract, or full paper.
Calibrate scientific claims and integrate citations properly. Use when adjusting claim strength, adding hedging language, integrating literature, or matching evidence to…
Extract full metadata from a ScienceDirect article page (abstract, authors, keywords, DOI, references, PDF link). Use when the user wants details about a specific paper.
Use when the user asks to "design an email A/B test", "set up a multivariate subject/CTA test", "run a send-time test", "build a hold-out group", or "is this email test…
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness,…
SB catalog-backed AF-DECIDE flow step (FS-SILVER_DEEP_RESEARCH) and `/silver:deep-research` workflow engine: rigorous multi-source research with phase-level evidence, nested…
Opt-in multi-model deep research. Composes canonical silver-deep-research engine, new /silver:multi-ai-task primitive, and Cursor/OCG backends. Dual serverless HTML reports.
Run 2–5 focused feasibility experiments before committing to an implementation approach. Each experiment has a hypothesis, executable code, and a VALIDATED / INVALIDATED / PARTIAL…
Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly…
Capture, persist, and query research findings across sessions through a 7-phase workflow with structural anti-skip enforcement.
Timeboxed feasibility experiment. Answers 'can this work?' questions. Creates .design/spikes// with hypothesis, timebox, scratch code, findings.
Download, split, and deeply read academic PDFs. Use when asked to read, review, or summarize an academic paper.