One repeatable pass that turns "look at " into scoped, witnessed, license-clean, FILED backlog.
Use this skill when the user wants to evaluate academic writing style (without source comparison) — KI-frei.
Use when the user asks to "generate subject line variants", "pre-score my subject lines", or "will this subject get truncated / trigger spam filters"; produces a labeled subject +…
Generate the submission-time disclosure block for a manuscript — the AI-use disclosure statement matched to the target journal's policy, CRediT author-contribution roles,…
Quick-summarize a single paper from a local PDF. For full discovery+screening+acquisition pipeline, use /research instead.
Plan and autonomously build a software task end-to-end. Triggered by `/supergoal`, "plan and ship X", "supercharged plan", "autonomous build", "plan it out and don't stop until…
Free, KEYLESS web search — no API key, no setup, no config. Encyclopedic full-text via Wikipedia + instant answers via DuckDuckGo.
Free, KEYLESS web search — no API key, no setup, no config. Encyclopedic full-text via Wikipedia + instant answers via DuckDuckGo.
Generates a research-grounded execution plan for a coding task. MUST BE USED whenever the user asks for a plan, design, architecture, or spec — including in plan/approval mode,…
Deep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking claims, evaluating architectures, or any tas — from…
Deep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking claims, evaluating architectures, or any tas — from…
Synthesize user research from interviews, surveys, and feedback into structured insights. Use when you have a pile of interview notes, survey responses, or support ticket — from…
Schedules a non-coding work item — research inquiry, audit, survey, experiment, or written report — as a backlog entry.
Turn a research paper into teaching materials — a lecture outline, the 3-5 results worth presenting (with intuition), a slide skeleton ready for `/create-lecture`, discussion…
Compressed bug-fix pipeline — reproduce, write failing test, minimal fix, verify. Skips Question/Research/Design/Structure/Plan phases. Trigger on "/team-fix ".
팀 에이전트 병렬 리서치 오케스트레이터. 프로젝트 시작 전 기술 스택, 아키텍처, 경쟁 제품을 리서처 서브에이전트로 병렬 조사하고 결과를 취합한다. '/team-research', '팀 리서치', '리서치해줘', '사전 조사' 등 언급 시 호출
Autonome technische haalbaarheidstoets per kandidaat-oplossing (HMW-statement). Identificeert benodigde technologieën, beoordeelt maturity (proven/emerging/experimental), schat…
SDD Phases 1-2 for provider development. Clarify requirements, research, produce provider-design-{resource}.md, and await human approval before any code is written.
자율 웹 리서치 → 실행 가능 계획 도출. 주제를 받아 웹 검색 → 정보 수집 → 분석 → 구조화된 리서치 보고서 생성. '알아봐', '조사해', '리서치해줘', '검색하고 정리해', 'research and plan' 같은 요청에 반드시 사용. 웹 검색 후 실행 가능한 계획까지 도출이 필요할 때 적극 활용.
기술 비교, 아키텍처 조사, 경쟁사 분석 등 깊이 있는 리서치가 필요할 때 사용한다. '심층 조사', '자세히 알아봐', 'deep research', '전면 리서치', '비교 분석 보고서', '종합 리서치' 같은 요청에 반드시 사용. 단순 검색이 아닌 멀티소스 교차검증이 필요한 리서치에 적극 활용.
웹 검색/리서치가 필요할 때 사용한다. '검색해줘', '찾아봐', '최신 정보', '이거 뭐야', '심층 조사', '자세히 알아봐', 'deep research', '전면 리서치', '자율 리서치', '조사해', 'research and plan' 같은 요청에 반드시 사용.
Systematically assess whether a paper's theoretical results can be strengthened: relax assumptions, sharpen rates, align theory with model and experiments, and benchmark against…
Research State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture.
Reconstruct WHY something was built the way it was from evidence outside the code, and report what could not be found.
Execute a training experiment from a recipe. Use when user says "开始训练", "run experiment", "train model", or wants to execute a recipe.
Track and analyze trends, breaking news, and market shifts. Measures velocity across web, social, news, GitHub, and academic signals.
Research a subject along two axes — how it got here and how it compares today — and cross them into a traceable report on where it goes next.
Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition — from…
Research latest Claude Code / ECC changes, deep-analyze impact, implement, commit on feature branch, create PR, merge, install to ~/, and cut a GitHub release
Thorough on-demand refresh of one skill in this repo. Researches kb/upstream/docs in parallel, gates twice for approval, bumps version, updates CHANGELOG, runs just check, commits…
Evaluates platform upgrade readiness across Claude model versions, CC releases, and OrchestKit updates with 6-dimensional assessment.
Orchestrate a full website design upgrade — snapshot the current site, research references via design-dna, synthesize a direction, score the gaps, write a prioritized plan,…
Autonomous iterative optimization loop for measurable metrics like coverage, performance, or bundle size. Use when repeated experiments can be judged by a mechanical score.
Fast codebase scouting using shell search and optional parallel research agents. Use for file discovery, task context gathering, and quick scoped searches across director — from…
Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition — from…
VC signal-to-thesis skill for Marathon-style deal discovery. Weekly all-sector radar, OSS radar, agent-native research workbench, theme drill-downs, company backtrace, and GitHub…
Orchestrate Agent Teams for parallel multi-session collaboration. Use for research, implementation, review, and debug workflows requiring independent teammates.
End-to-end applied AI/ML research pipeline. Takes a research question and dataset, runs literature review, multi-method classification/regression analysis with parallel model…
End-to-end AI/ML methodology research pipeline. From research direction to publication-ready manuscript with novel architectures, training strategies, or evaluation methods.
End-to-end applied statistical research pipeline. Takes a research question and dataset, runs literature review, statistical analysis with parallel method tracks, and produces a…
End-to-end statistics methodology research pipeline. From research direction to publication-ready manuscript with novel estimators, theoretical proofs, simulation studies, and…
EXPERIMENTAL v2: Enhanced parallel veracity audit with 12 gap fixes. Launches 20 agents per run in 5 waves (decomposition + quality gate + 3 verification waves).
Power search via Exa MCP. Modes: quick, deep research, code, docs, debug, news, compare. Use when searching the web, finding docs, debugging errors, or researching any topic.
Audit the Research Vault concept wiki read-only for fragmentation, missing tags, write-only concepts, and draft or anatomy conformance, producing a Markdown report.
Fill in the per-paper TODO sections (Problem/Method/Key Results/Limitations/Reusable Ingredients/...) of research-wiki/papers/.md pages that /research-lit, /arxiv,…
Extract Crunchbase company profiles, funding rounds, and investor data into raw/. Use for startup, investor, or market research.
Extract product listings, pricing, and auction data from Amazon, eBay, Etsy, Shopify into raw/. Use for product research or price tracking.
Extract patent text, claims, and citations from Google Patents, Espacenet, USPTO into raw/. Use for IP and prior art research.
Orchestrate fetching a URL or research query into the vault using the best available adapter.
End-to-end vault workflow — status, research/fetch, raw prepare, wiki ingest, lint, build-site, validate — with optional user gates between stages.
Get word count, character count, reading time, and text statistics. Quick analysis without questions.
Use when working, planning, grooming, or closing a backlog item. Bridges backlog items to SAM planning with GitHub Issue, Project, and Milestone tracking.
Podejmij prosty ticket (max 3 SP) z biezacego projektu Monolynx. Uproszczony flow: 1 dev + krytyk jako zwykle subagenty (bez Agent Teams).
Document a recently solved research problem to compound methodological knowledge
Divergent research ideation — generate many candidate directions, then adversarially filter to the strongest
Transform research descriptions into well-structured implementation plans following project conventions
Run multi-agent econometric review on estimation code, identification arguments, and research artifacts
Execute research implementation plans efficiently while maintaining estimation quality and finishing features
Manage git worktrees for isolated parallel development sessions. Create, list, switch between, and remove worktrees with safety checks for uncommitted changes and unpushed…
Zarządzanie zdalnymi sesjami Claude Code (tmux + Remote Control) na VPS z poziomu lokalnego komputera — bez ręcznego wchodzenia na serwer.