Use when creating reusable GitLab CI/CD configurations, building component catalog entries, or packaging pipeline templates for sharing - provides systematic guide following…
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, veri — from…
Support business understanding from small ventures to corporate strategy and academic research.
Sets product level buying role hypotheses for a B2B team before any deal: who likely champions, who signs, who evaluates, plus reviewers and daily users, each built from the…
Use when designing, updating, or exploring system architecture with C3 methodology - iterative scoping through hypothesis, exploration, and discovery across…
Homer L3 — Epic Research Muse. Deep synthesis from web + local research sources. Zeus dispatches Calliope as a parallel subagent when a plan includes a research subtask.
Shared author-guideline skill for Cambridge University Press nutrition journals: British Journal of Nutrition, Nutrition Research Reviews, Proceedings of the Nutrition Society,…
Cancer Research (AACR) figures: resolution (300-1200 DPI), formats (EPS/TIFF/AI), hierarchical panel labels (Ai, Aii, Bi), figure/table limits, legend requirements with replicate…
Append a single observation, question, hypothesis, or concern to TASK_STATE.md as task memory without disrupting in-progress work or requiring a full state sync.
Use when building the conceptual engine of a Contemporary Accounting Research (CAR) manuscript — the economic or behavioral mechanism, predictions/hypotheses, or the formal model…
Use when choosing or sharpening a research question for a Contemporary Accounting Research (CAR) manuscript — testing fit with CAR's deliberately method-agnostic, all-topic-areas…
North star principles from CATY equity research project - professional HTML standards, external source citations, audit-grade documentation, and target profile frameworks that…
因果推論架構師(頂刊識別策略,2026 前緣標準):現代差異中之差異 DiD——交錯採用(staggered adoption)下 TWFE 的偏誤、Goodman-Bacon 分解、Callaway & Sant'Anna / Sun & Abraham 等異質穩健估計量、事件研究圖與平行趨勢診斷(含 Rambachan & Roth…
Use when the user wants a terse, opinionated, research-backed answer to a "what tech/tools/stack do I need for X" question, or asks how to approach building something.
Use when assembling ethics approvals and availability statements for a Cancer Cell (Cell Press) manuscript — IACUC animal approval, human-sample IRB/consent, biosafety, and…
Use when responding to Cancer Cell (Cell Press) reviewer reports — planning new experiments, writing a point-by-point response, and calibrating claims for revision.
Use when AI/ML research engineering needs baseline reproduction, hypothesis-driven experiments, ablations, evaluation design, findings synthesis, research direction selection,…
Use when coordinating an end-to-end research competition or benchmark program across multiple lifecycle stages such as rules, data, baseline, experiments, claims, and submission;…
Use when an AI/ML research result, baseline promotion, ablation conclusion, benchmark claim, paper claim, surprising finding, or high-cost next experiment needs an…
Search Slack for interpreted organizational context -- decisions, constraints, and discussion arcs that shape the current task.
Use when positioning a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript's contribution against the literature — benchmarking the precise method/result delta versus specific…
Use when drafting or revising the literature-review section for a Journal-of-Finance-and-Economics manuscript, when the Chinese / English reference balance is off, or when…
Conference proposal & paper-submission orchestrator. Bootstraps a new submission project at ~/cfp// with full discipline (beads, CLAUDE.md, refs/, research/), runs the…
Academic paper writing skill for 3D vision, computer graphics, CAD, and 3D understanding. Covers NeRF, 3DGS, SLAM, point cloud processing, 3D shape understanding/generation, CAD…
Design and document chaos engineering experiments. Guide steady state baseline, hypothesis formation, failure injection plans, and results analysis.
Drafts filing-ready Annual Reports for State Charity Bureaus with certified financials, governance disclosures, and required attachments.
Researches state-specific charitable solicitation filing requirements keyed to gross revenue, producing a citation-backed state-by-state compliance matrix of audit thresholds,…
当用户明确要求"核查/优化综述 `{主题}_review.tex` 的正文引用"或"运行 check-review-alignment"时使用。通过宿主 AI 的语义理解逐条核查引用是否与文献内容吻合，只在发现致命性引用错误时对"包含引用的句子"做最小化改写，并复用 `systematic-literature-review` 的渲染脚本输出…
Use when designing or auditing the studies behind an ACM CHI paper — matching evidence shape to contribution type, powering quantitative experiments, making qualitative work…
Use when targeting 《体育科学》(China Sport Science) — the China Sport Science Society flagship and top CSSCI sport-science journal (体育学).
Festlandchina Wirtschaftsverkehr: Board Paper China Risk. Geführter Spezialskill mit Quellenlogik, Prüfroutine, Red-Team-Fragen und verwertbarem Output.
Route language-model training, data, evaluation, checkpoint, representation, steering, ablation, jailbreak, tool-calling, Apple-runtime, and benchmark requests.
Applies the Chuqlab brand CSS design system to any Tailwind CSS v4 project. Includes brand color palette, Geist font configuration, and utility classes.
GitLab CI/CD for Rails 8 — .gitlab-ci.yml structure, RSpec + lint + security parallel stages, cache strategy (bundler, yarn, assets), services keyword for Postgres + Redis, Auto…
Use when the literature section of a 《中国工业经济》 (China Industrial Economics) manuscript is a citation pile instead of a critical review that locates the gap.
Rebuild bidirectional citation edges across the research corpus. Scans outgoing citation tables, computes the inverse map, and rewrites all incoming tables to match.
Use when identifying seminal papers in a research field, mapping research lineage and intellectual heritage, discovering related work through reference tracking, or finding…
Format citations and bibliographies in multiple academic styles (APA, IEEE, Chicago, Harvard, MLA, Nature, Science).
Verify citations against the research corpus to prevent hallucinated references and enforce GRADE compliance
Extracts every citation in a document — statute, case, rule, regulation, quotation, or cross-reference — and states exactly what needs verifying about it and how, attempting live…
Source tier definitions, citation formatting, verification patterns, and hallucination prevention. Load when writing content that requires external evidence, statistics, or expert…
研究 repo の引用 3 層 (docs 実引用 → .zenodo.json references → graph.jsonld ExternalReference) を監査し、下層から順に同期する orchestrator。旧層 4 (Wikidata P2860) は 2026-07 の governance revocation により恒久…
4-layer response shape for MCP tools that emit claims linked to sources — source-exists, claim-derivable, no-over-extension, no-hallucinated-cite.
Use when building the literature review and contribution positioning for a 《中国管理科学》 (Chinese Journal of Management Science) manuscript — running the Chinese and international…
Produces a structured research plan for tracing a widely circulated claim back to its original source — mapping the citation chain, identifying where distortion may have occurred,…
Use when planning and synthesizing product/user research as a method-and-repository discipline — selecting the right method for the goal (generative interviews vs usability test…
AI Agent Collaboration Platform - Register, discover ideas, vote, claim tasks, earn trust scores
Publish research papers to clawRxiv. Use when you want to share research findings, analyses, or technical write-ups to a public academic archive for AI agents.
Multi-agent swarm coordination via the ClawTeam CLI. Use when the user wants to create agent teams, spawn multiple agents to work in parallel, coordinate tasks with dependencies,…
Safely remove intermediate files from completed research sessions while preserving important data
Use when writing or reviewing ad-hoc research SQL in a dbt-ClickHouse project, or running federated queries via `postgresql()` from ClickHouse for data-quality investigations —…
Generates a structured prompt framework for clinical study protocols. Supports Diagnostic, Efficacy, Etiology, and Prognosis studies.
The single home for delegating a bug hunt to clink agents — read it before sending any failure to clink-subagents or clink-brainstorm, not only a bug that already survived a pass.
Use when asked 兴趣班怎么选, 孩子报几个兴趣班合适, 课外班规划, 双减后还能报什么班, 寒暑假怎么安排, 预付费培训退费, or plan a child's out-of-school activities in mainland China.
Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.
Use when a solution needs a coherent structure before implementation or production for Software implementation and code architecture: Swift and iOS apps for API evolution — from…
Protocol-level two-agent paper writing workflow. Use when the user wants Codex to plan and review from global context while DeepSeek writes or revises the manuscript through the…
Delegiert Code-Review, Research-Synthesis, Adversarial-Cross-Check an Codex CLI (`codex exec`, `codex review`).
Diagnose and fix broken LLM model configurations in CogniForge microservices. Use when: AI responses are empty, garbage, or missing LaTeX; reasoning-agent returns empty answers or…
Use when meeting Cognitive Psychology (Elsevier) open-science expectations — sharing data, model code, analysis scripts, and materials so the modeling is reproducible, depositing…