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
2,1132,160 · page 45 / 447
REBT自助表结构化引导(青少年版)引导青少年来访者使用标准化REBT自助表(ABC模型)完成A→C→B→D→E五栏填写,聚焦具体事件锚定、可观察后果记录、非理性信念识别、现实性辩论激发与自我支持性理性理念生成;全程保持合作性、非评判性、具身化互动,不替代表达、不跳过顺序、不限时超载。ECNU-ICALKREBT不合理信念辩论技术在认知重构的修通阶段,通过苏格拉底式提问引导来访者识别、检验并修正绝对化、以偏概全、灾难化等非适应性核心信念;聚焦信念的实证基础、逻辑一致性与功能后果,促成弹性、实证、促进行动的替代性合理信念。ECNU-ICALKREBT主干-SFBT辅助双轨咨询框架在青年高功能失恋来访者中,以合理情绪疗法(REBT)为核心处理不合理认知,辅以焦点解决短期治疗(SFBT)的赞美技术激活自我价值感与成长资源;要求严格匹配适用性信号、动态调控主辅比例,并产出结构化书面方案。ECNU-ICALKrecovering-from-failureHelp users navigate product failure by diagnosing root causes, evaluating conviction, and executing successful pivots or…RefoundAIreferralsWhen the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use…Infrasity-Labsreferrals-word-of-mouthHelp users build sustainable growth engines by transitioning from accidental word-of-mouth to structured referral programs and…RefoundAIrelevancekitIncrease widget visibility on Apple Watch using RelevanceKit. Use when providing contextual relevance signals for watchOS…dpearson2699research-product渐进式研究当前产品,并把已经稳定、可追溯的产品认知增量写入根目录 SOUL.md。首次接入产品代码、原型或线上 URL,需要确认产品形态与已有能力,或某个增长 loop…tsingyuairesource-planner-scott-margettsTeam structure, gearing analysis, continuity planning, and competing demand management for legal matters. Use when setting up a…lawve-airesume-modernModern minimal resume, single A4 page, ready for print or PDF export.nexu-ioRET自助表填写指导与ABC信念修正在理性情绪疗法(RET)框架下,结构化指导求助者填写自助表(事件A、信念B、结果C),并在后续咨询中系统检查、反馈并协作修正其识别的不合理信念,强化对ABC模型的理解与内化。ECNU-ICALK合理情绪疗法(RET)四阶段治疗框架一个结构化的认知行为治疗宏观协议,按确定问题、心理诊断、领悟与修通、巩固与评价四个阶段推进,用于系统干预由不合理信念引发的情绪与行为障碍。ECNU-ICALKRET咨询阶段性目标校准协议每次第二次及后续RET咨询开场时,用严格限时3分钟的结构化流程复盘:①核查上阶段家庭作业完成质量;②确认原定咨询目标是否仍适配当前困扰;③与求助者共同协商并具象化本次唯一核心焦点(如‘今天重点练习反驳‘我考不好=人生失败’这句话’)。确保目标动态适配、焦点清晰…ECNU-ICALKRET引导性认知发现会谈在合理情绪疗法(RET)第二阶段中,通过开放式提问与苏格拉底式对话,协助来访者识别其关于自我价值或亲密关系的具体不合理信念(如'我必须被爱才值得存在'),并建立情绪反应与认知之间的因果联结。ECNU-ICALKRET自助表填写与反馈修正指导求助者在咨询间隙填写理性情绪疗法(RET)自助表(事件A、信念B、结果C),并在下一次咨询中系统检查、共同讨论并修正其不合理信念条目,完成从觉察到初步修正的认知重构闭环。ECNU-ICALKRET不合理信念识别与归因澄清在第二次咨询中通过引导式提问与归因分析,帮助求助者识别‘糟糕至极’类非理性信念,并将其与具体情绪反应(如焦虑)建立因果联结。ECNU-ICALKRET框架下嵌入式放松训练在合理情绪疗法(RET/ABC)框架中,于单次咨询会谈中结构化嵌入一次≤5分钟的标准化放松练习(腹式呼吸4-6-8或上肢渐进放松),以降低当前生理唤醒水平,增强求助者对不合理信念(B)的觉察清晰度,服务于认知重构目标。ECNU-ICALKRET自助表布置与使用指导向来访者清晰说明RET自助表填写要求:记录负性情绪事件、对应不合理认知,并尝试生成替代性合理认知。确保来访者理解ABC逻辑并能独立完成一周记录。ECNU-ICALKRET非理性信念结构化辩论在第三次咨询中,以苏格拉底式提问、逻辑归谬与实证检验为支柱,系统松动求助者已识别的‘杞人忧天式’非理性信念(如‘我复习→爸爸感冒→爸爸死亡’),协同生成功能导向的替代性合理信念。ECNU-ICALKretention-engagementHelp users identify the drivers of long-term retention and implement behavioral mechanics that keep customers coming back. This…RefoundAIrikosvastuun-perusteetRikosvastuun yleiset edellytykset Suomen rikosoikeudessa (rikoslaki 39/1889, yleinen osa). Käytä tätä skilliä, kun arvioidaan…akunikkolabio-reporting-rmarkdown-reportsCreate reproducible bioinformatics analysis reports with R Markdown including code, results, and visualizations in HTML, PDF, or…BioTender-maxRSA作业反馈与强化结构化反馈来访者提交的合理自我分析报告(RSA),确认事件-信念-情绪对应关系,正向强化其对合理信念的初步尝试,巩固认知行为改变动机。适用于RSA已提交且内容基本完整的情境。ECNU-ICALKRSA自我分析报告指导指导来访者使用理性情绪疗法(RET)中的RSA(Rational Self-Analysis)表格,系统识别、记录并辩驳非理性信念,用于认知重构作业阶段。ECNU-ICALKRSA作业结构化反馈与认知-行为桥接基于ABC模型对来访者完成的合理自我分析报告(RSA)进行结构化反馈,通过产婆式辩论澄清非理性信念,协同构建可复述的合理替代信念,并自然衔接至配套行为训练(如渐进性放松),适用于CBT中期认知巩固向行为调节过渡阶段。ECNU-ICALKRSA报告引导与认知内化训练在CBT咨询第三阶段(巩固期),依托来访者已完成的合理自我分析(RSA)报告,通过结构化指导与自我奖惩技术,强化新认知模式的稳定性与可及性,推动其内化为自动化的信念系统。ECNU-ICALKS-O-R模型驱动的当下问题聚焦在首次咨询中,运用刺激-有机体-反应模型快速识别并结构化当前最紧迫的生活问题(如情绪低落、失眠),明确可操作的问题清单与初始目标。ECNU-ICALKsandbox-sdkBuild sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems…cloudflareSAS测验引导式反馈与问题锚定在首次咨询中,将SAS焦虑量表结果转化为具体、非标签化的临床观察,并与求助者共同确认1–2个最扰人的焦虑表现作为后续工作锚点。ECNU-ICALKSBQ-R临界分值触发转介协议当自杀行为问卷修订版(SBQ-R)得分≥7时,启动精神科转介流程:征得来访者同意后联系其辅导员与监护人,并建议前往精神类医院进行医学评估。ECNU-ICALKSCL-90与EPQ联合解释脚本(中文常模版)依据中国常模对SCL-90与EPQ结果进行结构化解读,聚焦因子分临床意义与人格维度关联,用于向来访者通俗反馈评估发现并建立共同理解基础。ECNU-ICALKscrna-preprocessing-clusteringStandard scRNA-seq preprocessing and clustering with Scanpy. Use for QC, normalization, HVG selection, PCA, neighbor graph…BioTender-maxSDS/SAS标准化抑郁焦虑基线测量在CBT初始评估阶段,规范施测抑郁自评量表(SDS)与焦虑自评量表(SAS),严格遵循指导语、计分规则与临床解释标准,生成可量化、可追踪的情绪症状基线数据,作为后续疗效评估的锚点。ECNU-ICALKself-media-trend-radar安全追踪热点、研究关键词和拆解竞品内容,并将结果转成原创选题和证据包。用于用户要求找热点、看趋势、分析爆款、研究竞品账号、拆标题或开头、比较内容结构、发现评论需求和判断时效窗口。只做公开信息研究和只读采集,不自动互动、发布或使用主账号登录态抓取竞品。yanhua1010SFBT咨询阶段:资源激活与小步目标共构在焦点解决短期疗法第二至三次咨询中,以行为基线为锚点,结构化运用赞美技术、例外事件探索与小步目标设定,引导来访者识别可控资源、增强希望感、建立可测量的渐进路径。ECNU-ICALKSFBT结束与巩固阶段:资源取向型关系收尾在焦点解决短期疗法(SFBT)咨询末期,以资源取向、未来导向和合作性语言,系统回顾来访者自主行动与微小例外,强化其自我效能感与处境耐受性,并自然、平稳地结束咨询关系。ECNU-ICALKSFBT首次咨询结构化开场一个五步结构化流程,用于焦点解决短期疗法(SFBT)取向的首次咨询开场,旨在快速建立合作性咨访关系、澄清角色共识、识别既有资源并共同锚定具体、可观察的正向目标。ECNU-ICALKshareplay-activitiesBuild shared real-time experiences using GroupActivities and SharePlay. Use when implementing shared media playback…dpearson2699skypilot-multi-cloud-orchestrationMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs…OpenRaiserSMART价值导向目标制定协助来访者将自身学习特质与护理学专业要求相匹配,明确短期学习目标与长期职业规划路径,增强专业投入动机。ECNU-ICALKsmj-submissionUse when running the final pre-submission preflight for a Strategic Management Journal (SMJ) manuscript via ScholarOne — format…brycewang-stanfordspark-environment-setupSet up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing…wshobsonspritekitBuild 2D games and animations using SpriteKit. Use when creating game scenes with SKScene and SKView, adding sprites with…dpearson2699starknet-defiExecute DeFi operations on Starknet including token swaps via avnu aggregator, DCA recurring buys, STRK staking, and…internet-courtwritesstata-resultsFetch and display stored r(), e(), and s() results from the last Stata command.brycewang-stanfordstata-runRun arbitrary Stata code or a .do file and display the result.brycewang-stanfordstb-bwa-sus-bilanz-pruefungWenn es um BWA-, SuSa- und Bilanzpruefung bei Krisensignalen in Steuerrecht – Steuerberater und Anwälte geht: ordnet Akteninhalt…Klotzkettestock-correlationAnalyze stock correlations to find related companies and trading pairs. Use when the user asks about correlated stocks, related…himself65
← Prev45 / 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