Explorar el registro

Todas las entradas, por orden alfabético — 71.469 en total. Página 267 de 286.

• thatopen-syntax-propertiesUse when querying IFC properties, classifying model elements, or extracting data from loaded ThatOpen fragment
• thatopen-syntax-uiUse when building BIM user interfaces with ThatOpen UI components, creating panels, toolbars, or property disp
• thawatchai-petkaew-retroRun a story retrospective that distills lessons from closed work and feeds them back into the team's memory —
• thClaws/thClawsOpen-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider,
• the-archivistThis skill should be used when engineering decisions are being made during code implementation. The Archivist
• the-artificer-of-ciphers-llc-rubber-duckRubber duck debugging session. Use when the user is stuck on a bug and can't find the cause, says "I don't und
• the-artinet-project/agent-relayA Typescript library for discovering and sending messages between A2A enabled AI agents.
• the-artinet-project/artinet-sdkShip Agent2Agent in one line of code.
• the-artinet-project/cliAn interactive command-line interface that uses the Agent2Agent (A2A) & Model Context Protocols (MCP) to manag
• the-artinet-project/easy-a2aUse the Agent2Agent(A2A) protocol with any OpenAI API compatible endpoint.
• the-bisect-mindsetWhen a regression exists between a known-good and a known-broken state, you don't have to read the diff. Bisec
• the-contract-is-the-artifactWhen a system has both a data contract (file format, schema, protocol) and the tooling that renders/mutates it
• the-councilMulti-model advisory board using OpenAI Codex CLI and Google Antigravity CLI (agy) to provide second opinions
• the-fish-salmon-deep-researchCitation-disciplined literature pipeline backed by paper MCP servers (semantic-scholar, arxiv, paper-search).
• the-fish-salmon-handoffCapture a structured handoff snapshot so the next chat can resume. Writes handoff_latest.md to the Claude Code
• the-foolUse when challenging ideas, plans, decisions, or proposals. Invoke to play devil's advocate, run a pre-mortem,
• the-governorLegal, regulatory, privacy, IP, and compliance governance authority. Does not provide legal advice. Sits above
• the-homepageStructure a dev-tool homepage that converts developers into champions. Use when the landing page is written fo
• the-hugin-design-masterUnified design mega-skill for all artifact types: web pages, landing pages, dashboards, UI components, posters
• the-hugin-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• the-hugin-skill-creatorRecursively Self-Improving Module — persistent memory + structured improvement loop for Claude Code
• the-juryUse when a question, decision, plan, tradeoff, or claim needs a rigorous verdict and one perspective is not en
• the-oasis-project-reviewRun all five review agents on changes, synthesize findings, triage based on developer thinking, and fix approv
• the-open-agent/openagent⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-
• the-optimizerWorkflow automation and process improvement. Use when a recurring task reveals an opportunity to build a syste
• the-oracleThis skill should be used when the user asks to "use the oracle" or "ask the oracle" for deep research, analys
• the-pirate-baySearch The Pirate Bay for torrents and extract magnet links via the apibay.org JSON API. Use when asked to "fi
• the-rewriteModernizing legacy systems. Use when inheriting any codebase written by someone else, to chart the path from t
• the-selling-partner-api-for-ordersThe Selling Partner API for Orders API skill. Use when working with The Selling Partner API for Orders for ord
• the-stewardBusiness alignment and scope governance authority. See docs/governance/GOVERNANCE_LAYER.md for governance beha
• the-tunerCross-specialist coordination specialist for contract assembly, contradiction detection, semantic invalidation
• theabbieLive info about theabbie (Abhishek Chaudhary) from theabbie.github.io/about.json
• theagenticguy-researchMulti-agent research skill. Decomposes a question into 2–4 parallel Opus 4.7 research agents that write findin
• theatre历史剧场（Theatre）— 沉浸式历史角色扮演体验。用户扮演历史场景中的亲历者，通过对话与李白、杜甫、王维等真实历史人物互动，姿态决定相遇深度。只要用户说「/theatre」、「历史剧场」、「历史角色扮演」、「穿越历史
• thebrain-bird-addressUse BIRD Book Deconstructor 2.2 to apply the formal BIRD 2.1 Knowledge Address protocol to complex manuscript
• thebrain-mcp-serverMCP server for TheBrain 15: search by meaning, graph traversal and batch writes over the local API
• TheBushidoCollective/hanA curated marketplace of Claude Code plugins that embody the principles of ethical and professional software d
• thechandanbhagat-code-reviewPerform automated code reviews with best practices, security checks, and refactoring suggestions. Use when rev
• thechandanbhagat-debugDebug code, analyze errors, interpret stack traces, find root causes, and suggest fixes. Use when troubleshoot
• thechandanbhagat-docsGenerate documentation, API docs, README files, and code comments. Use for creating or improving project docum
• thechandanbhagat-docxWork with Word documents (DOCX/DOC) - read, extract content, create documents, convert formats, and process te
• thechandanbhagat-pdfWork with PDF files - read, extract text/images/tables, create PDFs, merge, split, and convert PDFs. Use when
• thechandanbhagat-pptxWork with PowerPoint presentations (PPTX/PPT) - read slides, extract content, create presentations, convert fo
• thechandanbhagat-refactorRefactor code to improve quality, apply SOLID principles, remove code smells, and suggest better patterns. Use
• thechandanbhagat-testGenerate unit tests, integration tests, and test data. Use when writing tests, improving test coverage, or cre
• thechandanbhagat-xlsxWork with Excel spreadsheets (XLSX/XLS/CSV) - read data, create spreadsheets, convert formats, analyze data, a
• thecrawlerUniversal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
• thedotmack-doExecute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — es
• thedotmack/claude-memPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, com
• theme-auditAudit theme coverage and consistency across a design system's semantic and component token tiers. Triggers: au
• theme-detectorDetect and analyze trending market themes across sectors. Use when user asks about current market themes, tren
• theme-factoryToolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing page
• theme-factory-addonExpansion pack of 100 curated color and font themes for the theme-factory skill, organized into 14 categories
• theme-stylingApply consistent theming with Tailwind CSS 4, including dark mode support and design tokens. Use when styling
• theme-updateSafely update a Weaverse Pilot theme to the latest version — detects current version, fetches release diffs, p
• themingScaffold a unified, cross-platform color theme system into an Expo Router app. Sets up semantic system colors
• theming-componentsProvides design token system and theming framework for consistent, customizable UI styling across all componen
• theming-systemDesign a theming architecture that supports brand variants, dark mode, and high-contrast modes with token mapp
• theneoai-architectLicensed Architect (AIA, LEED AP BD+C) with 15+ years designing commercial, institutional, and residential pro
• theneoai-prompt-engineerExpert-level Prompt Engineer skill. Transforms AI into a specialist who designs, evaluates, and optimizes prom
• theory-engineActivate when the user needs to select a theoretical lens, formulate a research gap, derive hypotheses or desi
• theory-of-changeConstrói teoria da mudança (insumos → atividades → resultados → impactos) e deriva indicadores de monitorament
• thermal-optical-mechanical-closurePerform or review screening-level STOP-style closure for telescope concepts by linking thermal cases, structur
• thermo-nuclear-code-quality-reviewRun an opt-in strict maintainability review for giant files, spaghetti growth, misplaced logic, weak boundarie
• theseus-protocolThoughtbox-first Theseus workflow for behavior-preserving refactors. Use this when structure changes but behav
• thesis-chapter-reconstructor围绕毕业论文主线重构章节：把原论文式叙事改成学位论文式叙事，重写章节目标、内容比重、前后承接与论证方式。 **Trigger**: 章节重构, chapter reconstructor, 毕业论文主线重构, paper
• thesis-citation-enhance-review为中文毕业论文补强并核验引用：找出必须有引文支撑的句子，扩展候选文献，检查引用与论断是否匹配，并回写参考文献与正文引用。 **Trigger**: 引用补强, citation enhance, 文献补充, 引用核验,
• thesis-compile-review对中文毕业论文进行编译、warning 分级、模板模式检查、数据与引用复查，并把问题回写成可继续迭代的 review checklist。 **Trigger**: 毕业论文编译检查, thesis compile re
• thesis-creator面向中国本科生的毕业论文全流程写作辅助系统。支持从选题到交稿的端到端工作流，包含降重优化、AIGC 降低和本地检测功能。用户说「帮我写论文」或「帮我降重」等时触发。
• thesis-defense-pptxCreate, polish, and quality-check editable undergraduate or graduate thesis defense PowerPoint decks from a lo
• thesis-driftAI Berkshire skill: 投资论文漂移检测：分清事实变化与措辞变化. Source: skills/thesis-drift.md.
• thesis-figure-skill生成学术论文配图：LaTeX/TikZ 代码（结构化图表，直接嵌入论文）或 draw.io XML （技术路线图、汇报配图）。自动按论文领域风格设计，编译验证后交付。 Use when the user asks for
• thesis-frontmatter-sync同步中文毕业论文的非正文部分：摘要、附录、封面、成果、致谢、名单等，确保这些部分与正文口径一致，而不是最后临时补写。 **Trigger**: 摘要同步, frontmatter sync, 附录同步, 封面检查, 非正
• thesis-markdown-aligner在 Markdown 中间层统一毕业论文的主线、术语、符号、指标、图表口径与章节边界，让整篇论文先在中间层收敛成“一篇论文”。 **Trigger**: markdown 对齐, thesis markdown alig
• thesis-outline-ththesis outline ครบ chapter | สำหรับ นักศึกษา. Triggers when user says (Thai/EN): 'thesis', 'วิทยานิพนธ์', 'โคร
• thesis-question-list维护中文毕业论文的 `codex_md/question_list.md`：把本轮问题、边界、优先级、协作方案和验收口径结构化，作为整条 thesis pipeline 的控制面。 **Trigger**: 毕业论文问题
• thesis-reviewerUse when the user wants to review, evaluate, or provide feedback on a master's or doctoral thesis (硕士/博士学位论文).
• thesis-source-role-mapper将中文毕业论文已有材料映射到“毕业论文角色”：把论文、模板、Overleaf 源稿、PDF、图表和实验材料按章节角色、研究问题和证据用途重新归位。 **Trigger**: 毕业论文材料映射, source role m
• thesis-style-polisher对中文毕业论文做最终润色与去 AI 味：重点处理章首导言、章末小结、贡献描述、总结与展望中的模板腔、宣传腔与 AI 口癖。 **Trigger**: 论文润色, thesis style polish, 去 AI 味,
• thesis-tex-writeback把已经在 Markdown 中间层收敛的中文毕业论文内容回写到 `chapters/*.tex` 与相关交付层文件，保持结构、图表、公式、交叉引用与章节承接一致。 **Trigger**: tex 回写, thesis
• thesis-tracker166 production-ready Claude AI skills organized by corporate role — executive leadership, finance, HR, marketi
• thesis-visual-layout-planner规划中文毕业论文的图表、流程图和版面节奏：先决定哪些图表支撑主线，再做草图、拼版预演与图文映射。 **Trigger**: 图表规划, figure layout, thesis visual plan, 版面预演, 图
• thesis-workspace-init初始化中文毕业论文工作区：检查学校模板与已有材料的放置位置，明确提示当前还缺什么，建立 `codex_md/` / `claude_md/` / `tmp_layout*/` 等中间层目录，并生成材料盘点与初始工作文件。
• thesis-writerWrite publication-quality MSc/PhD thesis chapters that pass examiner scrutiny and AI detection tools. Use when
• thesvgFetch brand SVG logos and cloud architecture icons (AWS, Azure, GCP) from theSVG. Use when the user asks for a
• thewatcher01-sarif-parsingParses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers
• thewoolleyman-critiqueCritique an existing livespec specification or a pending proposed change, surfacing ambiguities, contradiction
• thienphuprogrammer-patch-notesGenerate player-facing patch notes from git history, sprint data, and internal changelogs. Translates develope
• thiientv-code-simplificationSimplifies recently changed or explicitly scoped code while preserving observable behavior, error semantics, s
• thiientv-frontend-designDesigns, builds, or refactors user-facing web or application interfaces with deliberate visual direction, typo
• thiientv-using-git-worktreesCreates and manages isolated Git worktrees for parallel agents, risky experiments, or long-running feature wor
• thingctxDrive devices and APIs from their W3C Thing Description. You gate every operation.
• things-macManage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from
• things-ui-skillsThings's UI design system. Use when building interfaces inspired by Things's aesthetic - light mode, Inter fon
• things3Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from
• things3-managerManage tasks, projects, areas, headings, and tags in the Things 3 macOS app via a local CLI (list Inbox/Today/
• thinkTurns rough ideas into approved plans with validated structure before writing code. Covers new features, archi
• think-abstraction-ladderingBuilds an abstraction ladder that moves a problem up ("why / to what end?") and down ("how / what specifically
• think-achAnalysis of Competing Hypotheses. Operationalizes Richards Heuer's CIA-tradition technique for systematically
• think-affinity-mappingProduces a clustered theme map that groups many raw notes, observations, quotes, or data points bottom-up into
• think-after-action-reviewProduces a structured after-action review by comparing what was expected against what actually happened, diagn
• think-analysis-of-competing-hypothesesHandles a by-name request for ACH (Analysis of Competing Hypotheses), the evidence-by-hypothesis disconfirmati
• think-argument-mappingProduces an argument map by laying out a claim's supporting reasons, the co-premises each silently depends on,
• think-assumption-reversalGenerates non-obvious ideas by surfacing the foundational assumptions a problem or solution rests on, negating
• think-authentic-dissentChecks whether a decision has genuine minority dissent or only smooth surface consensus, identifies who actual
• think-backcastingProduces a backcast path by fixing a vivid desired future state and reasoning backward through the milestones
• think-before-codingUse before writing or changing code on any non-trivial task, to surface hidden assumptions, keep the change mi
• think-belief-update-routineProduces a belief-update ledger that re-scores a standing inventory of open beliefs against newly arrived evid
• think-boundary-critiqueAudits the boundary judgments that silently define a problem frame. For each of four sources, who benefits, wh
• think-brainstormGood-faith divergent brainstorming for achieving a goal. Validates assumptions, then spawns brainstormers runn
• think-brainwritingGenerates ideas the way silent parallel brainwriting does, producing several independent idea streams that bui
• think-causal-layered-analysisProduces a four-layer matrix (litany, system, worldview, myth) of the current 'used future' beside a reconstru
• think-causal-loop-diagramsBuilds a signed causal loop diagram by closing the feedback loops in a situation, labeling each loop reinforci
• think-complexity-domain-sortRuns a Complexity Domain Sort, sorting a situation into Clear, Complicated, Complex, Chaotic, or Confusion and
• think-concept-mappingBuilds a concept map - a non-hierarchical network of concept nodes joined by directed, labeled linking phrases
• think-consider-the-unknownsProduces a known-unknowns ledger by enumerating the relevant evidence not in hand, the variables that bear on
• think-contradiction-resolutionConverts a stuck trade-off into a contradiction to dissolve rather than a compromise to settle for. Names the
• think-contradiction-tension-mappingProduces a both/and polarity map - two interdependent poles, the upside and downside quadrant of each, a great
• think-decision-journalProduces a decision journal entry that records a consequential decision at the moment it is made - the decisio
• think-decision-option-reviewProduces a criteria-weighted option matrix by comparing a set of options against weighted criteria, scoring ea
• think-deliberateAdversarial deliberation process for making decisions. Spawns advocate agents for each option who argue their
• think-diagnoseAbductive reasoning about causes. Takes a phenomenon, separates observations from interpretations, then spawns
• think-dialectical-bootstrappingProduces a dialectical estimate that improves a single committed number by polling the inner crowd, make a fir
• think-eisenhower-moscow-paretoRuns one of the three lightweight prioritization presets (Eisenhower urgent-important 2x2, MoSCoW Must/Should/
• think-ethical-matrixProduces an ethical matrix, a grid that cross-references affected parties (rows, deliberately including voicel
• think-evidence-vs-inference-sortProduces an evidence/inference ledger by sorting the claims in a prompt, document, or proposed conclusion into
• think-expected-value-decision-treeEvaluates competing actions under uncertainty by building a decision tree of choice and chance nodes, placing
• think-far-analogy-ideationGenerates novel solution candidates by stating a problem's deep relational structure, mapping it to distant so
• think-fermi-estimationProduces a Fermi decomposition worksheet that estimates an unknown numeric quantity by factoring it into a cha
• think-firstCognitive engagement coach based on "Think First, AI Second" principles. This skill should be used when the us
• think-five-whysRuns a Five Whys root-cause trace caveat-first. It leads with the weak evidence (Card 2017 found the single-ch
• think-frame-creationGenerates a new problem frame from theme analysis of the broader context, an abductive standpoint stated as ap
• think-framework-advisorProduces a prioritized, evidence-graded Thinking Plan that diagnoses which thinking frameworks a situation act
• think-frameworks사용자가 고민·결정·문제를 적으면 16개 사고/의사결정 프레임워크 중 적절한 것을 진단·추천하고 그 절차를 실제로 적용해 구조화된 분석을 출력한다. 중요한 결정이면 2~3개로 교차검증(삼각측량) 후
• think-futures-wheelProduces a consequence map by tracing the first, second, and third order effects of a change or decision radia
• think-iceberg-modelProduces an iceberg that moves a problem down four levels of causation - from the visible event, to the patter
• think-in-codeUse when analyzing multiple files, auditing a codebase, scanning dependencies, or counting lines -- one Bash p
• think-interest-based-negotiationProduces a negotiation preparation map that separates both sides' positions from their underlying interests, a
• think-interval-calibration-checkAudits whether a stated confidence interval means what it claims by running an equivalent-bet indifference tes
• think-issue-treeProduces an issue tree that decomposes one big, ambiguous question top-down into a mutually-exclusive, collect
• think-ladder-of-inference-checkProduces an annotated reasoning trace that reconstructs how a conclusion was reached, from the observable data
• think-lightCut reasoning-token weight. Use when thinking or reasoning tokens dominate the bill, when asked to cap a think
• think-like-mePersonal engineering rules and reasoning patterns the user has curated over time. Consult BEFORE writing, modi
• think-linear-model-aggregationBuilds a simple mechanical scoring model - a few weighted predictive cues combined by a fixed formula and appl
• think-minimax-regretProduces a regret (opportunity-loss) matrix with the minimax pick and the binding worst-case state, choosing a
• think-morphological-analysisProduces a morphological field (a Zwicky box of independent parameters by their possible values) plus a cross-
• think-natural-frequency-bayesianConverts a conditional-probability or base-rate question into natural frequencies over a concrete population (
• think-one-way-vs-two-way-doorProduces a reversibility classification that triages a decision before any analysis - labeling it a reversible
• think-pairwise-comparisonProduces a binary-vote comparison matrix (every pair judged A-beats-B), a derived ranking, and a consistency c
• think-parallel-perspectives-reviewEvaluates a decision or idea through several deliberately separated lenses in turn (facts, upside, risks, intu
• think-premortemGenerates a ranked risk register that stress-tests a planned decision by imagining it has already failed, surf
• think-problem-restatementGenerates several genuinely different framings of an ambiguous problem by varying altitude, stakeholder, and g
• think-process-tracingEvaluates rival causal explanations of a single case by typing each piece of within-case evidence by its diagn
• think-pyramid-principleProduces a pyramid that structures a recommendation answer-first - a single governing thought on top, a small
• think-qualitative-comparative-analysisHandles a by-name request for QCA (Qualitative Comparative Analysis), the truth-table-and-Boolean-minimization
• think-question-burstGenerates a rapid burst of questions about a problem (questions only, no answers), then ranks them for which w
• think-random-frameworksGenerates three off-pattern framework analyses of a topic by drawing frameworks at random, applying each regar
• think-red-team-lightProduces an adversarial critique by constructing the strongest case against a proposal or thesis (the best obj
• think-reference-class-forecastingProduces a reference-class estimate by defining a class of similar past cases, taking their base-rate distribu
• think-reflectRetrospective learning from a completed experience. Takes a project, incident, decision that played out, or ti
• think-reflective-equilibriumRuns reflective equilibrium (mutual adjustment between considered case judgments, general principles, and back
• think-reframeProblem redefinition before problem solving. Takes a stated problem, extracts its premises, then spawns refram
• think-replace-methodREPLACE with one sentence. Lead with an action verb (Generates / Produces / Evaluates / Audits / Checks), name
• think-research-frameworkResearches a thinking framework end to end and produces a schema-valid proposed registry entry plus a learning
• think-role-stormingProduces a persona-tagged divergent idea list, ideas generated while inhabiting a chosen non-self identity to
• think-scamperGenerates a structured set of variations on an existing idea, product, or process by running it through seven
• think-scenario-planningProduces a scenario set, 2-4 contrasting and internally consistent short narratives of alternative external fu
• think-scrutinizeGood-faith adversarial scrutiny of an idea or plan. Spawns critical skeptics across relevant lenses, pairs the
• think-speculative-harms-anti-goalsProduces an anti-goals register by assuming a design succeeds at scale, narrating the near-future in which tha
• think-stocks-and-flows-reasoningProduces a stock-flow map by separating a quantity that accumulates from the inflows and outflows that change
• think-swotRuns a SWOT analysis (strengths, weaknesses, opportunities, threats) caveat-first. It leads with the weak evid
• think-theory-of-constraintsProduces a constraint-intervention plan that names the single binding constraint capping a system's throughput
• think-three-horizonsProduces a three-curve transition map (a declining present H1, a contested middle H2 read in two directions, a
• think-toolUse when facing a complex decision, multiple possible approaches, or before making irreversible changes. Use w
• think-top3Produces a worked three-framework analysis of a topic. Ranks the library's thinking frameworks for relevance,
• think-twiceForces Claude to pause before picking an implementation approach and ask: "Is there a cleverer, cheaper way?"
• think-veil-of-ignorance-reasoningProduces a veiled-decision comparison that decides a values trade-off as if the decider had an equal chance of
• think-walton-argumentation-schemesEvaluates one short defeasible argument by classifying it as a stereotyped reasoning scheme (appeal to expert
• think-what-would-have-to-be-trueConverts a strategy, option, or contested claim into the specific conditions that would have to be true for it
• think-woopProduces a WOOP commitment card by working through Wish, Outcome, Obstacle, and Plan - contrasting the desired
• think4mingMing's automatic thinking-partner mode for ambiguous framing, open exploration, trade-off analysis, or decisio
• thinkbackWhen the user wants to review past decisions, understand why something was built a certain way, audit decision
• thinkinaixyz-algorithmic-artCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this wh
• thinkinaixyz-code-reviewComprehensive code review assistant that analyzes code quality, security, and best practices
• thinkinaixyz-doc-coauthoringGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documen
• thinkinaixyz-docxComprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting
• thinkinaixyz-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• thinkinaixyz-git-commitGenerate well-formatted git commit messages following conventional commit standards
• thinkinaixyz-mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with externa
• thinkinaixyz-pdfComprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting do
• thinkinaixyz-pptxPresentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for:
• thinkinaixyz-skill-creatorGuide for creating effective skills. This skill should be used when users want to create a new skill (or updat
• thinkinaixyz-web-artifacts-builderSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web tech
• thinkinaixyz-xlsxComprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis
• ThinkInAIXYZ/deepchat🐬DeepChat - A smart assistant that connects powerful AI to your personal world
• thinkingMulti-mode analytical and creative thinking — first principles decomposition, iterative depth analysis, creati
• thinking-bounded-rationalityUse when search or investigation could run forever. Set an explicit good-enough threshold first, then stop at
• thinking-circle-of-competenceUse when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch
• thinking-cynefinWhen the right response mode is unclear, classify the cause-effect domain first; decompose disorder.
• thinking-effectuationUnder genuine uncertainty with no reliable forecast, inventory means, cap downside at affordable loss, act for
• thinking-fast-slowWhen the user is facing a decision where their intuition is firing strongly OR they suspect bias is shaping th
• thinking-first-principlesWhen a constraint is treated as fixed, separate physics from convention, keep only independently supported pri
• thinking-five-whys-plusWhen a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked
• thinking-in-betsWhen the user is judging a past decision by its outcome ("I made the wrong call because it didn't work out") o
• thinking-jobs-to-be-doneDeciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumsta
• thinking-kepner-tregoeUse when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/wa
• thinking-lindy-effectUse when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then
• thinking-map-territoryWhen a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map
• thinking-margin-of-safetyWhen provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual err
• thinking-model-combinationWhen one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence compleme
• thinking-model-routerWhen unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by d
• thinking-oodaUse under time pressure when the situation is still changing and you must act before certainty — cycle Observe
• thinking-opportunity-costBefore committing scarce time, people, or money, name the best forgone use of those resources and the value de
• thinking-partnerA deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, s
• thinking-partner-workflowUse Claude as an iterative thinking partner by combining memory, voice, and artifact creation to move from ide
• thinking-pre-mortemBefore committing to a plan or launch, assume it already failed and reason backward through concrete causes —
• thinking-probabilisticUse when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→
• thinking-red-teamFor authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface,
• thinking-reversibilityBefore heavy deliberation, classify the decision as cheap or costly to undo; decide two-way doors fast and sta
• thinking-scientific-methodWhen a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating o
• thinking-second-orderWhen a change has effects past the immediate fix—incentives, scale, feedback—trace consequence chains with tim
• thinking-socraticWhen a request is vague, assumption-laden, or "obvious," ask the few load-bearing questions that expose hidden
• thinking-steel-manningBefore rejecting a proposal or reflexively agreeing, build the strongest faithful opposing case, state agreeme
• thinking-systemsWhen behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/
• thinking-theory-of-constraintsWhen throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinat
• thinking-thought-experimentWhen a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, f
• thinking-toolkitSelect and apply a complete toolkit of decision-making, problem-solving, systems-thinking, and communication m
• thinking-trizWhen two design requirements seem mutually exclusive, name the contradiction, separate conflicting states, the
• thinking-via-negativaUse when the reflex is to add a feature, layer, or process. Prefer removing harmful or nonessential elements f
• third-party-bloatInventory third-party scripts on a page — analytics, tag managers, chat widgets, ads, A/B tools — and rank the
• third-party-skill-intakeReview third-party skill repos for format fit, provenance, and first-party adoption paths without treating the
• this-is-marketing-godinApply Seth Godin''s marketing framework. Trigger on: "find my smallest viable audience", "position this offer"
• this-name-is-way-too-long-and-exceeds-the-sixty-four-character-limit-for-skill-namesA skill with a name that is too long
• thisaay-reviewTurn an implementation plan, tech spec, or existing codebase into an interactive architecture diagram the deve
• thisispaper-mcpSearch 2,500+ curated architecture, design, photography and art projects. Free tier, no signup.
• thistripbtw-mcpTurn a trip planned in conversation into a private, editable map link you hand the person.
• thomas-kilmannUse when the user has a specific conflict, disagreement, or dispute to navigate and needs to decide how to han
• thorlabs-blender-optical-pathBuild, audit, and revise complete physically plausible Blender optical-table systems from 2D schematics and ma
• thorlabs-blender-optical-path-ja2D 光学回路図とメーカー CAD から、単一の end-to-end run、writer、scene lineage、fail-closed ledger を通じて完全で物理的に妥当な Blender 光学システムを
• thorlabs-blender-optical-path-zh从二维光路示意图与厂家 CAD 通过一个端到端运行、writer、场景谱系和 fail-closed 证据账本构建、审核和修订完整且具有物理可信度的 Blender 光学平台。适用于 Thorlabs 兼容器件、完整光路
• thoroughness-scoringScore every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things prope
• thothOfficial Codex public surface for the Thoth authority runtime. Use this skill when the user wants to operate T
• thought-leaderTurning everyday professional experience into shareable insight. Use when events at work contain lessons worth
• thought-leadershipTransforms technical answers into polished, shareable insights with professional reach. Use when the user asks
• thoughtbot-explainExplain what a piece of code does — a specific file, class, or method in close detail, or a user-facing flow a
• thoughtbot-git-commitTurn the working changes into one or more atomic commits with well-written messages. Use whenever the user run
• thoughtbot-rubber-duckThink out loud about a problem, decision, or approach — Socratic friction to help you find clarity, not sympat
• thoughtful-assistantA curious, direct, and technically sharp assistant with strong reasoning. Engages deeply on making, coding, ga
• thoughtproof-mcpPre-action gate: verify before pay/trade/write/deploy. execute=true only on ALLOW.
• ThousandFacedHero/crewai-a2aA2A-compliant multi-agent research crew built with CrewAI. Hierarchical team (Coordinator, Researcher, Writer)