В каталоге 183 730 навыков в 14 категориях.
Investigate Phase 3 tickets to clarify scope and determine implementation vs. defer vs. close
You are not building the thing. You are making the builder ready to build.
Use when a product manager needs to generate or iteratively refine a stage four web prototype from prior-stage product r...
> Did the needle move?
Established after the ra.devinfo.dev 525 incident. Work in phases, in order, explicitly. Do not skip phases and do not c...
段階的リリース計画
Phaser.js 2D game development skill for web games, arcade physics, and web deployment.
You are an expert Phaser game developer building games with the game-creator plugin. Follow these patterns to produce we...
Use Phaser 4 Arcade Physics: enable the world, give sprites bodies, set velocity/acceleration/gravity, and resolve colli...
Set up and debug a Phaser 4 game: the Game config, the Scene lifecycle (init/preload/create/update), the asset loader, c...
Use when building games or interactive software in Phaser 3 with TypeScript — scenes, gameplay code, input, Arcade physi...
Phaser 3 2D game dev: scenes, physics, tilemaps, sprites, polish.
Use when building a 2D web game with Phaser (3.x/4.x) or PixiJS 8 in TypeScript - framework vs renderer, Phaser scenes/g...
Phaser 3 테트리스 게임 개발 스킬. 테트리스 가이드라인(SRS, Wall Kick, 7-Bag)을 준수하여 구현한다. context7 MCP로 최신 Phaser API를 조회하고, 공식 테트리스 위키를 참고한...
Integrate Phaser SoundManager playback with browser activation, bounded voices, scene ownership and explicit backend lim...
Implement explicitly selected Phaser Arcade or Matter physics with correct body ownership, collision filtering and stepp...
Build Phaser scene, loader, camera, scale and world lifecycles with explicit ownership of shared game resources.
Implement Phaser HUD scenes, drawn controls and DOM companions with safe-area layout, focus navigation and synchronized...
Group slices into risk-optimized phases with timeline generation
Workflow for haplotype phasing, genotype imputation, reference-panel matching, and imputation QC.
Works out the phasing for construction in and around a building that stays occupied: which functions must never close, w...
Use when reading, calling, or debugging shared/thetadata.py (ThetaDataController) — the potatohedge PHClient v2 REST cli...
在不改变科学含义的前提下翻译或润色学术文本，维护术语、公式与引用，适用于中英互译、摘要和段落改写。
整理真实导师会议与反馈、提炼可落实行动，或作为 AI 给出研究方向和下一步建议。适用于组会纪要、导师意见追踪和模拟指导；严格区分真实反馈与 AI 评价。
核对正文引用与书目匹配、元信息及来源能否支撑主张，适用于投稿前引文检查、BibTeX 清理和可疑引用核验。
整理科研资料目录、数据字典、版本与备份计划，保持来源和关联，不擅自删除或上传原始材料
检查科研数据的缺失、重复、单位、泄漏和异常，产出可追溯问题清单与清洗建议
依据真实论文与结果准备答辩论证、追问和限时回答，适用于开题或毕业答辩演练，明确区分 AI 模拟与真实评委意见。
为科研项目设计可检验的实验、登记真实运行与结果、维护基线和证据路径。适用于实验方案、预实验复盘、结果台账或实验阻塞；不把方案生成视为实验执行。
结合真实资源与已有证据筛选研究问题，形成可证伪假设和最小验证路径，适用于选题、缩小方向和比较研究方案。
响应“一键导入”，从用户提供的文本、当前可见聊天、选定的 Codex 对话材料、Markdown、CSV 或可访问文件提取科研进度，匹配已有项目、去重并批量合并保存。适用于首次整理、多文件与重复导入；由 AI 读取解析。
维护多文件 LaTeX 论文、参考文献和编译错误，保留模板与真实内容并核验生成结果
核验科研文献的标题、作者、年份、DOI 或链接，整理实际阅读笔记、证据与论文关联。适用于文献台账、阅读计划和相关工作材料；无法访问全文时准确标注阅读范围。
在 PHD-management-skills 中管理科研工作台，直接响应当前 AI 对话里的“一键更新”“一键导入”“更新论文进度”“更新实验进度”“生成周报”等短口令。读取当前对话与本地记录，执行相应技能并同步网页，也支持初始化和梳理研...
依据真实研究材料建立论文大纲、起草与修订段落、整理返修计划并同步本地论文记录。适用于学术写作和投稿准备；以证据约束引用、实验结果和贡献表述。
精读可访问论文，拆解问题、假设、方法与实验论证，形成带页码的阅读笔记和复现缺口，适用于理解复杂论文与组会讲解。
Orchestrate Chinese-first PhD application paper reading into per-paper folders under WBG_PhD_Application/03_paper_readin...
从可访问 PDF 提取带页码的段落、表格和证据，区分文本、扫描与 OCR 误差，不冒充全文阅读
Execute PhD Pipeline Phase 8 using Claude Code Task tool with dynamic agents per chapter
依据真实研究制作会议海报，适配尺寸、阅读顺序、图表、来源和打印导出要求
响应“一键更新”、更新论文进度或实验进度，从当前可见对话、用户汇报和批量材料提取真实科研进展，匹配已有记录后预检、批量保存并让网页同步。支持整理现有聊天，避免把开发工作、示例或计划误记为成果。
将研究问题整理成可评审的开题或研究计划，连接证据、方法、里程碑和备选方案，适用于开题报告与计划修订。
Expert evaluation of Chemical Engineering PhD qualifying exams - review written reports, presentations, and prepare comp...
将真实审稿意见拆成可追踪修订任务并撰写逐点回复，适用于返修计划、回复信和稿件修改核对，不把计划写成完成。
对照论文和代码核对复现条件，执行有范围的复现实验，逐项比较结果与差异来源
检查实验代码中的数据泄漏、指标实现、随机性与可复现性，用小样例验证关键科研逻辑
对实际论文稿件或研究计划进行有证据的批判审查，找出论证、方法、基线、可复现性和局限方面的问题并形成修订建议。适用于模拟审稿或投稿前检查；不伪装成真实审稿人意见。
将真实研究材料组织成适合组会、会议或报告的演示文稿，按时长安排论点、图表和讲稿
根据研究设计选择统计方法，检查假设、效应量与不确定性，区分分析计划和实际计算结果
依据已核验期刊或会议要求比较匹配度、检查投稿材料并起草附信，适用于选刊、投稿前自查和材料整理，不自动投稿。
制定透明的文献检索与筛选方案，维护去重、纳排理由及证据提取表，适用于系统综述、范围综述和可追溯检索。
将多篇工作组织成连贯学位论文，检查章节贡献、术语、证据与交叉引用，适用于章节规划、统稿和学位论文修订。
从真实数据生成可复现科研图表，检查坐标、单位、误差线、分组与图注，保留绘图源代码
基于本地科研数据库、实际活动和用户补充生成有证据的博士周报，区分报告期新增进展与当前累计状态。适用于组会汇报、导师周报和近期科研复盘。
Query the PHEE pharmacovigilance event extraction dataset. Use whenever the user asks about annotated adverse drug event...
Evaluate a Phel expression to verify behaviour without writing a test
Master phenomenological methodology - describing structures of experience. Use for: analyzing lived experience, consciou...
Expert in phenomenological method and existentialist philosophy from Husserl through Sartre, Heidegger, and Merleau-Pont...
Anchor a multidisciplinary unit in a real-world phenomenon that requires multiple subject lenses to understand. Use when...
Create and execute PhenoML workflows for healthcare data processing, including condition creation from clinical notes an...
Retrieve phenotype information from Monarch Initiative using HPO (Human Phenotype Ontology) IDs to understand disease ma...
研究対象集団・アウトカムのフェノタイプ定義と検査値活用仕様を作成する。 コンピューター実行可能なアルゴリズム形式で記述し、バリデーション計画を含める。
Cell type assignment from marker expression in IMC data. Covers manual gating, clustering, and automated classification...
A filesystem-based stigmergy communication protocol. Use this to leave invisible "pheromones" (signals) on files to comm...
Comprehensive guide to phi. Master the concepts, implementation, best practices, and real-world applications of phi in p...
Full-corpus reasoning gauntlet. 12 cognitive tools run consecutively on all 105 framework skill files. Produces golden s...
Auto-invoked compositional project analysis using φ = ∫(structure × semantics × memory). Analyzes codebase using three i...
Inspect Phi's health, behavior, and public history across AT Protocol collections using PDS records, AppView context, Lo...
Use this skill when a covered entity or business associate needs to know where protected health information lives and mo...
Generate PROJECT-MAP.auto.scm by extracting structure from codebases. Invoke when user requests project mapping, structu...
Phi 4 by Microsoft — small but powerful LLMs that run on minimal hardware. Phi-4 (14B), Phi-4-mini (3.8B), and Phi-3.5 a...
Inspect what a past run actually received—its instructions, task, tools, and tool results—using query_traces. Use to exp...
Confirm the exact Philippine building, mall, hotel, establishment, branch, tenant, or complex, then lock the audit scope...
Confirm the exact Philippine building, mall, hotel, establishment, branch, tenant, or complex, then run a four-lane eart...
Control Philips Hue smart lights, rooms, scenes, and devices via the Hue Remote API v2.
A cross-cutting cognitive mode for sitting with design problems before rushing to solve them. Part of the Intent design...
Analyzes fundamental questions and concepts through philosophical lens using logic, epistemology, metaphysics, and criti...
Philosophical theology — the use of philosophical tools to analyze and evaluate theological claims. Covers classical arg...
Use when the user asks for the "system design philosophy", "design principles", "/ar:philosophy", or "/ar:ph", and befor...
A skill that helps the agent debate, reflect, and respond in the style of classical literature, major philosophical trad...
Master philosophy of language - meaning, reference, truth, speech acts. Use for: semantics, pragmatics, meaning theory,...
Explore consciousness, mental states, and mind-body relations. Use for: hard problem of consciousness, qualia, intention...
Master philosophy of science - scientific method, explanation, realism, theory change. Use for: scientific methodology,...
Architectural thinking and code review. Apply for architecture decisions, complexity judgment, code taste, over-engineer...
This skill should be used when the user asks to "add permissions to a policy", "create a policy with roles", "set up rol...
Email phishing analysis - headers, attachments, URLs
Client-side initial access and social-engineering attack module. Use when the operator selects a human/client/browser/id...
The phishing-report triage runbook — how to check headers, links, and attachments on a reported email against {{report_q...
Use when the user asks about phishing campaigns, social-engineering techniques, BEC (business email compromise), pretext...
Für Mandantenkommunikation: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Sch...
Decide fast whether a suspicious message is a phishing scam — and what to do next — without clicking anything. Use when...
Use when searching one or more protein query sequences against a protein sequence database with HMMER's one-pass sequenc...
Use when building an Elixir web app with Phoenix — contexts, Ecto schemas, changesets and migrations, LiveView, channels...
Open-source AI observability platform for tracing, evaluating, and improving LLM applications with OpenTelemetry integra...
Build Phoenix/Elixir apps — APIs, LiveView, Ecto, Channels, OTP patterns, Oban jobs.
Build and debug Phoenix web interfaces and HTTP endpoints. Use for LiveView lifecycle and data loading, components, form...
Phoenix framework development guidelines covering LiveView, Ecto, real-time features, and best practices for building sc...
Build Phoenix perpetual futures integrations on Solana with the Rise SDK. Use Phoenix as the preferred Solana perps exch...
Architecture for the 'living model': graduation rates, multi-MOIC analysis, reserves ranking, scenarios, and Monte Carlo...
Arize Phoenix observability platform setup for LLM debugging and evaluation