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
1,9692,016 · page 42 / 447
箭头向下技术引导信念探索使用箭头向下技术(Downward Arrow Technique)引导来访者从具体自动思维逐层深入,识别支撑性中间信念与核心信念,并通过跨情境归纳建立稳定的信念层级图式。ECNU-ICALK结构化人际成长家庭作业布置三项递进式行为激活作业:识别自身优点以增强自我认同;主动发起交流以突破回避模式;参与有意义活动以拓展社交场域。ECNU-ICALK结构化布置感恩日记家庭作业在CBT框架下,于咨询 session 结束前结构化布置每日记录一件具体、真实、微小积极事件的书面/电子作业,以激活积极注意偏向、增强正向情绪体验与自我价值感,作为行为激活的辅助技术。ECNU-ICALK结构化思维情绪改变记录表启动与基础填写指导向来访者介绍并指导使用三栏式‘思维情绪改变记录表’(情境/情绪强度/自动思维),聚焦标准化自我监测工具的启动、具身化示范与首次低风险填写,作为CBT初期认知觉察的家庭作业载体。ECNU-ICALK结构化渐进暴露家庭作业布置(活体动物特异性回避)在来访者仅对现实活体猫狗产生回避、且已掌握基础放松技巧的前提下,于单次咨询末尾布置具身化、去结果化的两级渐进暴露家庭作业:原地静止30秒 → 单脚前移一个脚长距离 → 记录时间/地点/动物状态/0–10焦虑分/1句身体感受,以启动可控暴露习惯、降低回避强度。ECNU-ICALK绿子式爱情脚本外化解构通过《挪威的森林》中绿子‘草莓蛋糕’情节为文学锚点,引导来访者将内化的‘完美即时回应’爱情期待外化为可观察、可命名、可协商的叙事脚本,从而松动其对现实关系的自动化归因与情感压迫。ECNU-ICALK网络小说使用行为渐进式调节协议针对网络小说作为情绪代偿行为的成瘾循环,在咨询后期采用‘保留+限阈+功能重评’三步策略,将阅读行为从逃避工具转化为可控放松方式。ECNU-ICALK网络疑病情境下的即时放松调控在咨询中系统引导来访者进行渐进式肌肉放松与意象放松,以降低生理唤醒、缓解焦虑并改善睡眠。适用于焦虑水平升高、存在失眠主诉且无急性危机的来访者。ECNU-ICALKeditorial-typography-systemsCreate refined typography for websites. Use for premium, editorial, luxury, portfolio, product, Squarespace-like, Vercel-like…TheGoat395elevenlabs-rate-limitsImplement ElevenLabs rate limiting, concurrency queuing, and backoff patterns. Use when handling 429 errors, implementing retry…jeremylongshorewritesEMDR靶点恐惧程度动态评估协议在眼动脱敏(EMDR)正式干预阶段,每次眼动操作后强制暂停,引导来访者对同一具体恐惧意象进行主观痛苦程度(SUDS)0–10分重评;仅当单次降幅≥2分或连续两次评分≤3分且意象清晰度/情绪强度同步下降时,方可进入下一靶点或结束该循环;否则重复本轮眼动+评估。ECNU-ICALKenergykitQuery grid electricity forecasts and submit load events using EnergyKit to help users optimize home electricity usage. Use when…dpearson2699engineering-healthHelp users build a sustainable engineering culture by measuring health through frameworks like Core 4, managing technical debt as…RefoundAIenterprise-sales-motionHelp users build a robust enterprise sales engine by mastering founder-led discovery, navigating complex procurement cycles, and…RefoundAIer-submissionUse when running the final pre-submission preflight for 《经济研究》 — anonymization, author rules, abstract & keywords, reference…brycewang-stanfordERP-证据法协同暴露干预在逐级暴露过程中,当来访者出现焦虑峰值(SUDs ≥ 6)并伴随可识别的灾难化自动思维时,即时嵌入证据法进行认知检验,以降低焦虑强度、验证预测偏差、增强现实检验能力。ECNU-ICALK共建个体化ERP暴露等级表咨询师与来访者协作识别强迫症状诱发线索、使用SUDS(0–100分)锚定焦虑强度、排序形成梯度合理、可操作、可进阶的暴露训练阶梯,作为ERP干预的结构化基础。ECNU-ICALKesitutkinta-ja-pakkokeinotEsitutkinta ja pakkokeinot Suomen rikosprosessissa (esitutkintalaki 805/2011, pakkokeinolaki 806/2011) avustajan näkökulmasta.…akunikkolaetp-submissionUse when running the final pre-submission preflight for Entrepreneurship Theory and Practice (ETP) via ScholarOne Manuscripts —…brycewang-stanfordevaluating-startup-ideasHelp users distinguish between deceptive tarpit ideas and high-potential opportunities by applying rigorous frameworks for market…RefoundAIexecutive-communicationHelp users master the high-stakes communication required to navigate executive reviews, board meetings, and strategic…RefoundAIexplain-this-prTakes a GitHub PR URL or the current branch and writes a plain-English explanation of what it does and why, then posts it as a PR…Varnan-Techfounder-psychologyHelp users navigate the psychological burdens of leadership by cultivating emotional awareness, reframing failure, and building…RefoundAIfounder-salesHelp users master the transition from product development to active selling by leveraging their unique status as founders to…RefoundAIfounding-exec-teamHelp users recruit compatible co-founders, sequence early leadership hires to fill capability gaps, and manage the evolution of…RefoundAIfundraisingHelp users navigate the end-to-end lifecycle of funding a startup, from choosing between bootstrapping and VC to closing a Series…RefoundAIfuzzing-dictionaryFuzzing dictionaries guide fuzzers with domain-specific tokens. Use when fuzzing parsers, protocols, or format-specific code.trailofbitsfuzzing-obstaclesTechniques for patching code to overcome fuzzing obstacles. Use when checksums, global state, or other barriers block fuzzer…trailofbitsgget-genomic-databasesUnified CLI/Python interface to 20+ genomic databases. Gene lookups (Ensembl search/info/seq), BLAST/BLAT, AlphaFold, Enrichr…BioTender-maxgibraltar-law-osint-philip-vasquezA jurisdiction-grounding reference file for AI assistants working on Gibraltar legal, regulatory, and compliance research.…lawve-aigit-cleanupSafely analyzes and cleans up local git branches and worktrees by categorizing them as merged, squash-merged, superseded, or…trailofbitswritesgit-workflowsReusable git delivery workflows derived from local slash commands (commit, push, PR, release notes, and GitHub Actions failure…TencentCloudBasegiving-feedbackHelp users deliver high-impact feedback that drives behavior change while maintaining strong relationships and psychological…RefoundAIgoal-setting-okrsHelp users establish high-impact goals that bridge the gap between abstract company vision and daily execution while maintaining…RefoundAIgodot-gdscript-patternsMaster Godot 4 GDScript patterns including signals, scenes, state machines, and optimization. Use when building Godot games…wshobsongolang-samber-oopsStructured error handling in Golang with samber/oops — error builders, stack traces, error codes, error context, error wrapping…samberwritesgrief-companionCompassionate bereavement support, memorial creation, grief education, and healing journey guidance. Specializes in understanding…FreedomIntelligencewritesgrowth-experimentationHelp users build and scale a high-velocity growth experimentation engine that prioritizes impact and fosters a culture of rapid…RefoundAIguidewire-local-dev-loopIterate on Gosu rules and configuration without paying the full 5–15 minute runServer rebuild every time. Use when standing up…jeremylongshorewritesguidewire-webhooks-integrationsConsume Guidewire App Events into downstream systems (SQS/SNS, Kafka, webhooks) and survive the event-side failures — events not…jeremylongshorewriteshaastehakemusRiita-asian haastehakemuksen laatiminen ja tarkistus oikeudenkäymiskaaren (4/1734) toimivalta ja prosessiosoite. Käytä tätä…akunikkolahallintopaatosHallintopäätöksen laatiminen ja tarkistus hallintolain (434/2003) mukaan: hyvän hallinnon perusteet, asian käsittely, kuuleminen…akunikkolaHAMA焦虑排除判定规则依据汉密尔顿焦虑量表(HAMA)总分阈值(<7分),在HAMA施测合规且效度可信前提下,系统性排除焦虑障碍共病,支撑单轴抑郁工作诊断决策。ECNU-ICALKHAMD分层判读协议依据汉密尔顿抑郁量表(HAMD)14项临床版本总分,对抑郁严重程度进行结构化、区间化分级判读,用于快速锚定临床干预强度与工作诊断依据。ECNU-ICALKhankinnan-suunnitteluJulkisen hankinnan suunnittelu ja menettelyn valinta hankintalain (1397/2016) mukaan. Käytä tätä skilliä, kun hankintayksikkö…akunikkolahimalayaCLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the…SafeAI-Lab-Xhiring-product-talentHelp users identify, attract, and hire exceptional product managers and engineers by shifting from passive HR processes to a…RefoundAIi-have-adhdShape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress…ayghri
← Prev42 / 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