Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration…
Use when you have SWATH-MS raw data (mzML or vendor format) from an untargeted metabolomics experiment and need to identify metabolites.
Använd denna färdighet när användaren frågar om svensk statistik, svenska befolkningsdata, ekonomisk data för Sverige, svensk arbetsmarknad, svensk miljöstatistik,…
Använd denna färdighet när användaren frågar om Trafikanalys, transportstatistik, fordon i trafik, bilregistreringar, nyregistreringar, fordonskilometer, järnvägstransport,…
Pick the correct swipi game archetype (platformer, top_down, grid_logic, tower_defense, ui_heavy) from a user prompt using physics-first logic.
Design rules, template API, and implementation guide for ui_heavy-archetype games (UI-driven, no physics — card battles, visual novels, quiz games, trivia fighters like K.O.F…
Use when researching, specifying, designing, or QAing a Swiss FOI / Öffentlichkeitsgesetz / LTrans / transparency-law request builder, including “MuckRock for Switzerland” or…
Consolidate Agentic SWMM run artifacts into auditable provenance, comparison records, and local Obsidian audit notes.
GIS/DEM preprocessing for SWMM experiments using the user's own QGIS/GRASS layers. Use when the user asks to (1) delineate subcatchments through QGIS/GRASS (standard or…
Read historical Agentic SWMM experiment audit artifacts and summarize repeated assumptions, QA issues, failures, missing evidence, run-to-run differences, lessons learned, and…
Parameter and forcing uncertainty propagation and sensitivity analysis for EPA SWMM. Use when an agent needs to (1) propagate parameter uncertainty through SWMM (fuzzy alpha-cut…
科研模式触发：群论分析、不变量计算、Galois理论、Noether定理、轨道分类、商空间推理、对称性破缺分析。 English (Research mode): Trigger for group theory analysis, invariant computation, Galois theory, Noether's theorem, orbit…
Use when you need exact symbolic math in Python — algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX.
Scan the active project for @import directives pointing at agentic-research/concepts/ and append idempotent used_by: back-references to each target concept file.
Synchronize documents to Google NotebookLM for AI-powered research and content generation
Detect syntenic blocks and structural rearrangements between genomes using MCScanX (Wang 2012), JCVI/MCScan (Tang 2008 Python), GENESPACE (Lovell 2022) for orthology-anch — from…
Master research synthesis including qualitative analysis, affinity diagramming, theme identification, pattern recognition, and insight extraction.
Merge, deduplicate, rank, and format research findings from multiple channels into a coherent report. Use after research agents return their results.
Merges, dedupes, ranks, and formats research findings into a report. Use after research agents return results from multiple channels to produce a ranked report.
Produce a structured synthesis with summary, recommendation, confidence, and categorized open questions. Use as the final step after research, evaluate, and critique.
Synthesize information across multiple sources into a structured document. Processes sources in batches across sessions to handle more data than fits in context.
Use when generating a comprehensive markdown knowledge document on a specific topic, where verified reference links and multi-source research are required.
Synthesize all prior research into a unified GTM narrative. Run after `analyzing-contradictions` to prepare for slide deck generation (Phase 5).
Use AI personas for early-stage research signal — with hard guardrails on what synthetic methods can and cannot validate.
Use when you are preparing to run a complex multi-tool bioinformatics pipeline (such as HiC-Pro) on a new system or cluster, and need to confirm that all required binaries exist…
Probe system resources — CPU, RAM, disk, GPU/CUDA/MPS — and translate findings into experiment design recommendations. Run this at the start of any compute-intensive project.
Write system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured improvements) with project XML conventions.
Write system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured improvements) with project XML conventions.
Write system prompts, tool docs, and agent definitions. Combines research-backed prompt engineering (+15-30% measured improvements) with project XML conventions.
Domain patterns for ML/AI serving and training systems — model serving, feature stores, training pipelines, experiment tracking, A/B testing, GPU scheduling, and failure modes.
Systematic debugging techniques for unclear root causes. Use when a bug's origin is unknown, multiple hypotheses need testing, you need to narrow down a failing area, end-to-end…
当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。AI 自定检索词，多源检索→去重→AI 逐篇阅读并评分（1–10分语义相关性与子主题分组）→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作（固定摘要/引言/子主题/讨论/展望/结论），保留正文字数与参考文献数硬校验，强制导出 PDF 与…
Route questions about the rules and systems that make a world distinct — magic, metaphysics, naming, and the foundational axioms in the world-bible.
Use when the user describes a note by vibe, concept, or paraphrase rather than literal terms — "find notes about the feeling of X", "that idea I had about Y and Z", "something…
Use when the user wants to explore, trace, map, or synthesize their thinking across multiple notes on a topic — "how have I thought about X?", "trace Y through my notes", "map…
TA（主题分析）研究全流程AFP工作流协调器。采用心跳信号、HUD仪表盘、 原子级单步输出、硬停止确认、多方案选择等AFP设计理念，共12个检查点。 关键决策节点（理论定位、叙事结构、标题/摘要/关键词）提供多方案+理由供选择。 每步暂停等待用户确认，所有写作工作由专项skill完成。 当用户明确提到主题分析（TA）相关的全流程时触发，例如：…
Use when the user asks to find, search, or look up a note in their Zettelkasten with specific named terms — "find my note about X", "search for Y in my notes", "list everything…
Use when the user wants to add, populate, enrich, fill, estimate, compute, classify, segment, or evaluate data on an existing Grasp table: financials, employees/headcount, current…
Guides data analysts through a multi-step Tableau dashboard creation workflow - brand setup, data exploration, dashboard planning, interactive HTML mock creation, Tableau…
Create multiplayer spatial board games using TabletopKit on visionOS. Use when building tabletop game experiences with boards, pieces, cards, and dice, managing player seats and…
Use TabTab to run AI-powered tasks in a sandboxed multi-agent environment. Supported capabilities: - General agent: open-ended tasks, writing, research, summarisation - Data…
Use when you have raw tabular experimental data (CSV or Excel) with column headers annotated using MESSES tag syntax (#
.id for record identifiers, #.
Use when wiring LLM APIs to bioinformatics analysis result tables in this repository, especially when users ask to interpret DEG, enrichment, ssGSEA, pathway-map, or…
Use when packaging a TACAS (ETAPS) artifact for the ETAPS Artifact Badges (Available, Functional, Reusable), covering the two-round model (mandatory, PC-parallel evaluation for…
Use when preparing an accepted TACAS (ETAPS) paper for its Springer LNCS camera-ready, covering de-anonymization of a double-blind research paper, the llncs.cls format and LNCS…
Use when designing or auditing a TACAS (ETAPS) evaluation, covering shared verification benchmarks (SV-COMP-style task sets), fair baseline configuration and equal time budgets,…
Use when positioning a TACAS (ETAPS) submission against the verification literature across TACAS, CAV, VMCAI, FMCAD, SPIN, and journals (STTT, FMSD), writing delta-first contrast…
Use when strengthening TACAS (ETAPS) reproducibility, covering the clean evaluation-VM packaging that the artifact process assumes, pinned dependencies and offline execution, a…
Use when reasoning about how a TACAS (ETAPS) submission is evaluated, covering the per-category blind model (double-blind research vs single-blind tool/case-study), the single…
Use when auditing a TACAS (ETAPS) submission for EasyChair readiness, covering the choice among the four paper categories (research, case-study, regular tool, tool-demonstration),…
Use when deciding whether a formal-methods / verification project belongs at TACAS (ETAPS) or a sibling like CAV, VMCAI, FMCAD, SPIN, or a journal, AND — distinctively — which of…
Use when revising a TACAS (ETAPS) paper for a clear construction-or-analysis contribution on the first page, a stated soundness/completeness claim, honest benchmark evidence,…
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages.
Practical guide for adults 60+ starting tai chi sword (tai chi jian / 太极剑). Covers safety screening, fall-prevention benefits backed by research, senior-friendly sword weight and…
Trae una historia/tarea/issue de Taiga con el subagent `taiga`, releva el contexto real del codebase con el subagent `researcher`, guarda ambos resultados como una tarea…
UI Take Root: uGUI + TextMeshPro, паттерн MVP (пассивный View + plain-C# Presenter, создаваемый в CoreEntryPoint.InitPresenters), реактивщина на UniRx, биндинг через…
Use when the user asks about Katie Roberts''s talk \"Stop Maintaining, Start Evolving: Applying AI-Native Practices to Brownfield Codebases\" — including questions about using AI…
Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required.
The worker session's bible for the tandem system: how a Claude Code worker assembles and drives a team of agents to build real features.
Use when you have an unknown MS/MS spectrum (tandem mass spectrum) with a measured precursor m/z and fragment peaks, and you need to assign the most likely molecular formula and…