Agent skills

Other skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
21,420 found
1,4411,488 · page 31 / 447
CBT认知重构微干预:修正完美化投射认知偏差引导来访者识别、检验并替代关于偶像的绝对化、完美化自动思维,代之以基于努力、现实能力与具体领域的适应性信念;适用于来访者表达‘我永远比不上他’‘天生不如’等自我贬低式比较时。ECNU-ICALKCBT资源取向自我效能感激活技术在CBT咨询中段,系统引导个案回溯成长史中持续付出的努力与适应性应对策略,通过具象化叙事识别、命名并锚定其既有能力,削弱习得性无助认知,增强对生活的掌控感体验。ECNU-ICALKCBT阶段性认知-情绪-行为进展三方校验在咨询结束阶段,结构化核查抑郁情绪缓解、生活节律规律性、社会功能重建(如主动兼职)三项指标,结合来访者自述与咨询师观察,确认CBT干预已达临床稳定阈值,支持安全结案。ECNU-ICALKCBT非理性信念识别与辩论帮助来访者识别并修正对'威信'的单一化、极端化认知,通过多维度比较与自我评估,引导其建立更平衡、现实的自我评价框架。适用于来访者将威信等同于权威压制(如大吼大叫)并因此产生焦虑的情境。ECNU-ICALKCBT思维-情绪关系 psychoeducation向来访者简明解释认知行为疗法中事件、思维与情绪三者之间的因果关系,帮助其建立初步的元认知觉察框架。用于咨询初期建立治疗联盟和心理教育基础。ECNU-ICALKcc-submissionUse when running the final pre-submission preflight for Cancer Cell (Cell Press) — file completeness, STAR Methods / Key…brycewang-stanfordgolden-chat-emptyUse when testing the golden_chat_empty golden buildyusufkaraaslangolden-chat-singleUse when testing the golden_chat_single golden buildyusufkaraaslanchronology-builder-andrew-birdBuilds a litigation chronology from the disclosure bundle itself — every entry attributed to its source document, behind a CPR…lawve-aiclay-multi-env-setupConfigure Clay integrations across development, staging, and production environments. Use when setting up per-environment Clay…jeremylongshorewritesclay-reliability-patternsBuild fault-tolerant Clay integrations with circuit breakers, dead letter queues, and graceful degradation. Use when building…jeremylongshorewritesclickhouse-multi-env-setupConfigure ClickHouse across dev, staging, and production with environment-specific settings, secrets management, and…jeremylongshorewritesbio-atac-seq-co-accessibilityInfer cis-regulatory connections (peak-to-peak co-accessibility) from scATAC-seq using Cicero, ArchR getCoAccessibility, or…BioTender-maxcobrapyConstraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and…FreedomIntelligencecobrapyConstraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and…K-Dense-AIwritescobrapyConstraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and…LeonChaoXcompany-intelResearch a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel…deanpeterscompany-researchCreate a company research brief with executive quotes, product strategy, and org context. Use when preparing for interviews…deanpeterscompetitive-analysisCompetitive landscape analysis: positioning, scorecards, moat assessment, market share trendsginlix-aicompetitive-intelSystematic competitor tracking that feeds CMO positioning, CRO battlecards, and CPO roadmap decisions. Use when analyzing…alirezarezvaniconstant-time-testingConstant-time testing detects timing side channels in cryptographic code. Use when auditing crypto implementations for timing…trailofbitscontinuous-discoveryHelp users build a sustainable habit of regular customer interaction to ensure product development is driven by real-world needs…RefoundAIevaluating-cosmos-policyEvaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot…Orchestra-Researchcre-submissionUse when running the final pre-submission preflight for 《中国农村经济》 — format, word count, double-blind, references, anti-plagiarism…brycewang-stanfordcryptokitUse Apple CryptoKit for Swift cryptographic primitives. Use when hashing with SHA-2 or SHA-3, generating HMACs, encrypting with…dpearson2699culture-architectBuild, measure, and evolve company culture as operational behavior — not wall posters. Covers mission/vision/values workshops…alirezarezvanicustomer-interviewsHelp users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional…RefoundAIcustomer-researchWhen the user wants to conduct, analyze, or synthesize customer research. Use when the user mentions "customer research," "ICP…sickn33customerio-advanced-troubleshootingApply Customer.io advanced debugging and incident response. Use when diagnosing complex delivery issues, investigating campaign…jeremylongshorewritescustomerio-reliability-patternsImplement Customer.io reliability and fault-tolerance patterns. Use when building circuit breakers, fallback queues, idempotency…jeremylongshorewritesDBT目标作业单1引导式填写使用标准化DBT目标作业单(作业单1),通过结构化提问引导来访者在首阶段具象化‘一个最想减少的可观察行为’与‘一项匹配的DBT替代技能’,完成行为-技能配对,聚焦具体、可操作、逻辑自洽的目标共建。ECNU-ICALKDBT个案概念化三步闭环协议一个结构化、可迭代、符合DBT辩证逻辑的宏观治疗框架,用于系统化组织临床信息、确立目标层级并基于实证反馈动态调整治疗方案。ECNU-ICALKDBT第一阶段关系建立与正念锚定在咨询初期(第1–4次)通过结构化正念作业单帮助来访者锚定当下、稳定注意力,同步建立安全治疗联盟。适用于来访者存在注意力涣散、情绪不稳、关系信任度低的初始阶段。ECNU-ICALKDBT自伤行为安全优先响应规则当DBT来访者报告或呈现新近自伤行为时,必须立即暂停技能教学,启动结构化三级响应:①确认当前安全状态;②完成行为链分析;③共同制定并签署24小时安全行为契约。ECNU-ICALKDBT预承诺阶段四次结构化会谈在DBT个体治疗起始阶段,执行标准化的四次50分钟会谈,依次完成治疗关系建立与个案概念化、DBT模型教育与问题行为界定、行为链分析建模、日记卡定制与使用演练,确保青少年来访者理解治疗逻辑、认同合作框架并掌握首个核心工具。ECNU-ICALK日间病房DBT五日团体技能训练框架在辩证行为疗法(DBT)早期阶段,结构化执行包含DBT心理教育、问题行为界定(依DBT优先级)、行为链分析、辩证认可介入及日记卡协同制定的五环节session,旨在建立技能学习动机并启动行为自我监控。ECNU-ICALKDBT团体准备中的技能锚定安抚当来访者对首次参与DBT团体表达社交焦虑与回避倾向时,用于将具体DBT技能与团体情境不适感直接锚定,提供即时可用的心理支持脚手架。ECNU-ICALKDBT技巧四步闭环教学在单次咨询中,以结构化、协作式、行为导向方式教授一个DBT核心技巧(正念/人际效能/情绪调节/痛苦耐受),通过讲解-示范-角色扮演-家庭作业四步闭环,确保来访者完成一次可观察的行为练习并提交具象化作业。ECNU-ICALKDBT日记卡功能澄清与情绪联想重构当来访者将日记卡体验为‘作业’并引发烦躁、回避等强烈负性情绪反应时,用于澄清日记卡的观察性功能,并协助来访者解构其与过往创伤性学业经历的情绪联结。ECNU-ICALKDBT行为链分析启动(自伤冲动阶段)当来访者报告存在自伤冲动但未实施时,用于结构化探索该冲动前后的环境线索、情绪、想法、行为及后果,以识别可干预节点。ECNU-ICALKDBT辩证认可回应在行为链分析完成后,使用DBT特有辩证认可技术回应来访者情绪体验:既验证自伤行为的功能性(‘是面对问题时所采用的策略’),又对比技能路径的长期获益(‘副作用很小’),以降低改变阻抗、增强技能学习动机。ECNU-ICALKDBT五模块结构化节奏规划协议依据问题形成与解决的时序逻辑,将12次50分钟DBT咨询划分为两阶段强度节奏:前4周(8次)双频次聚焦阶段1–2技能奠基;第4周起单频次推进阶段3–5并同步强化生活迁移,确保技能从咨询室向真实高频情境系统性泛化。ECNU-ICALKDBT问题行为优先界定依据DBT临床优先级规则(生命威胁行为 > 治疗干扰行为 > 质量-of-life干扰行为),与来访者协作将当前最紧迫问题行为锚定为自伤行为,并书面确认。ECNU-ICALKDBT五阶段目标共建协议基于DBT框架,与青少年来访者在首次关系建立后协作完成结构化、递进式五阶段目标设定:每阶段严格配对‘减少1个可观测不适行为’与‘增加1个DBT核心技能’,最终锚定于自我认同强化与复原力提升。产出双方签署的可测量、可练习、可验证的目标作业单。ECNU-ICALKDBT五阶段结构化咨询框架一个基于辩证行为疗法(DBT)的跨阶段、可复用的长程个体咨询全流程骨架,覆盖关系建立、活在当下、问题链分析、危机生存技能训练到生涯整合与结束,强调协同作业、具身化产出与效果锚定。ECNU-ICALKDBT生物社会理论心理教育在治疗同盟稳固后,以协作、隐喻化方式向来访者传授DBT生物社会理论核心图式(先天情绪敏感性 × 无效环境回应 → 调节技能发展受阻),促发归因重构与自我接纳,避免病理化自责。ECNU-ICALKDBT疗法初始适配性评估与知情启动在首次咨询前20分钟内,完成结构化保密说明、咨询原则传达、半结构化访谈、SCL-90/EPQ施测与简要反馈、四维自杀自伤风险探询,并基于中国常模与临床判断,协同来访者决策是否启动DBT取向咨询,签署知情同意。ECNU-ICALKDBT四模块结构化导入会谈在首次咨询中,以非评判、具身化、生活化语言系统介绍DBT四大核心模块(正念、人际效能、情绪调节、痛苦耐受),依托标准化讲义进行视觉协同,锚定来访者当前困扰,激发技能习得动机,建立治疗同盟与结构化干预共识。ECNU-ICALK
← Prev31 / 447Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going