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
4,0334,080 · page 85 / 447
orcaflex-post-processingPost-process OrcaFlex simulation results using OPP (OrcaFlex Post-Process). Use for extracting summary statistics, linked…majiayu000orientationOrients agents in new projects by scanning entry documents and discovering capabilities. Use at session start, when entering…majiayu000orthogonal-yc-batch-evaluatorEvaluate YC batch companies for investment — scrapes the YC directory, researches each company and its founders (work history…majiayu000osakassopimusOsakassopimuksen laatiminen ja riskitarkistus Suomen oikeuden mukaan. Käytä tätä skilliä, kun käyttäjä laatii, neuvottelee…akunikkolaOSINTOpen source intelligence gathering. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate.…majiayu000OSINTOpen source intelligence gathering. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate.…majiayu000OSINTOpen source intelligence gathering. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate.…majiayu000oss-evaluate-repoEvaluate whether an OSS repo is worth long-term investment before committing time. Assesses project health, governance…majiayu000oss-explore-repoGuided codebase exploration for understanding a repo's architecture, patterns, and domain language before contributing. Not…majiayu000oss-find-issueFind unclaimed open source issues that match the user's skills and experience level. Searches for issues created by…majiayu000outbound-prospecting-engineEnd-to-end outbound prospecting: detect intent signals, research companies, find decision-maker contacts, personalize messaging…gooseworks-aioutput-style-selectorAutomatically choose the best output style (tables, bullets, YAML, HTML, concise) to improve scanability and save tokensmajiayu000output-waehlenOutput wählen im KI-Governance: Diese Output-Weiche für Ki Governance entscheidet, ob Memo, Antrag, Schriftsatz, Tabelle…majiayu000overall-planning触发:当你需要在多个目标、利益方或相互制约的指标之间做动态平衡时调用;常见信号包括 trade-offs、目标冲突、系统性约束、优化一项会伤害另一项。HughYauovercome-problemStructured problem-solving framework for complex issues.majiayu000overloaded-modeUse when the user asks for overloaded-mode or burnout-mode, describes burnout or being burned out, or is overwhelmed, frozen…softcaneownUse when the user asks for a debrief on recent work, wants to check what they actually own versus what AI carried, or asks to be…majiayu000p10-context-windowingApply P10 Context Windowing to define explicit boundaries in time, space, and scope for analysis or action.majiayu000p12-temporal-framingApply P12 Temporal Framing to organize understanding across past causes, present states, and future implications.majiayu000p13-spatial-framingApply P13 Spatial Framing to scale perspective from local details to global patterns and back.majiayu000p3-identity-stackApply P3 Identity Stack to recognize that individuals operate from multiple nested identities simultaneously.majiayu000p4-lens-shiftingApply P4 Lens Shifting to deliberately adopt different interpretive frameworks to reveal hidden aspects.majiayu000p5-empathy-mappingApply P5 Empathy Mapping to systematically capture what stakeholders see, think, feel, and do in their context.majiayu000p8-narrative-framingApply P8 Narrative Framing to structure information as causal stories with conflict, choice, and consequence.majiayu000法律咨询助手协助律师处理微信渠道法律咨询和线下咨询,提供口语化回复建议、智能反问引导、软性销售植入,并在用户明确要求或总控确认需要时更新复盘台账。支持客户编号识别、咨询入口路由、线下咨询事实补全等功能。pa1nrui1破产法律分析基于《企业破产法》及司法解释,进行破产案件的系统性法律分析,支持管理人、债权人代理、债务人代理三种角色视角,生成标准化破产法律分析报告Word文档。当用户发送客户编号并提及"破产法律分析"、"破产分析"指令时触发使用,或在破产案件流程中自动衔接(BP1→BP2…pa1nrui1破产清算覆盖破产清算程序全流程,从宣告破产到程序终结。主要为R1(管理人)工作,R2/R3参与监督。当用户发送客户编号并提及"破产清算"、"财产变价"、"财产分配"、"终结程序"等指令时触发使用。pa1nrui1破产申请与受理覆盖破产申请全流程,包括申请书起草、附件准备、提交跟踪、受理后初步工作。当用户发送客户编号并提及"破产申请"、"重整申请"、"和解申请"等指令时触发使用。pa1nrui1债权人会议系统化支持债权人会议的筹备、召开、表决、纪要全流程工作,覆盖管理人、债权人代理、债务人代理三角色。支持第一次及后续多次债权人会议。当用户发送客户编号并提及"债权人会议"、"召开会议"、"准备会议"、"会议通知"、"会议议程"、"会议纪要"等指令时触发使用。pa1nrui1pacing-analysisAnalyze narrative pacing and identify slow or rushed sectionsmajiayu000package-publisherPublish packages to language-specific registriesa5c-aiwritespackmind-onboardRead-only codebase analysis to identify non-linter architectural patterns and generate draft Packmind Standards and Commands.majiayu000pact-contract-testingConsumer-driven contract testing with Pact framework. Generate consumer contracts, configure Pact Broker publishing, execute…a5c-aiwritespagentGuide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or…majiayu000bio-alignment-pairwisePerform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner. Use when comparing two sequences, finding optimal…majiayu000pallet-loadingWhen the user wants to optimize pallet loading, arrange boxes on pallets, or maximize pallet utilization. Also use when the user…majiayu000panelHost interactive expert panel discussions on any topic. Dynamically generates master-level expert personas, facilitates…majiayu000paper-discoverUse when searching for academic papers related to a topic, finding papers similar to one already in the vault, or discovering…majiayu000writespaper-polishProofread and verify academic papers in LaTeX. Runs 19 sequential checks covering titles, consistency, citations, formatting…brycewang-stanfordwritespaper-styleRestructure an academic paper's title and section structure to match a target journal's house style. Asks the user to specify the…brycewang-stanfordwritespapersSearch academic literature via arXiv, Semantic Scholar, and open-access PDFs.majiayu000parallel-search使用多組關鍵字並行搜尋,提高文獻覆蓋率。觸發:並行搜尋、parallel search、批量搜尋、擴展搜尋、多組搜尋、同時搜、找更多、廣泛搜尋、comprehensive search。majiayu000paretoIdentify the vital 20% of activities that produce 80% of results using real case studies and proven patterns. Use when optimizing…majiayu000parse-ai-analysisParse GitHub AI analysis comment sections for architectural alignment, technical feasibility, implementation suggestions, and…majiayu000party-depositionBuilds element-driven deposition outlines and witness preparation plans for U.S. party depositions (plaintiff or defendant)…majiayu000patent-claims-analyzerAutomated analysis of patent claims for USPTO compliance with 35 USC 112(b) requirements - antecedent basis, definiteness, claim…majiayu000patent-landscapeUse when analyzing biotech patent landscapes, identifying white spaces in pharmaceutical IP, tracking competitor patents, or…majiayu000writespatent-reviewerExpert system for reviewing utility patent applications against USPTO MPEP guidelines.majiayu000
← Prev85 / 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