Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when an agent keeps relearning the same correction, CLAUDE.md has grown unreadable, or you need to trace where a remembered rule came from. Promotes facts through four tiers only on recurrence across sessions and days, with memory_promote.py and a human adopt step.
Delegates non-trivial engineering work to an `explorer` (investigation, research) and a `fixer` (implementation) in a Herdr session, while the current top-level agent keeps strategy and review. Use when a root cause is unclear, code or architecture is unfamiliar, an external API, SDK, or specification needs research, or an implementation spans several files — even when the user never mentions agents, delegation, or orchestration. Do not use when the current agent was itself delegated work as an `explorer` or `fixer`. Requires HERDR_ENV=1. Handle trivial, local, low-risk work directly.
Set up an AI-driven changelog system in any project, code or not. Suitable for both software projects and for non-code projects. Creates a CHANGELOG.md and instructions for agents to log changes. Use when the user wants to add or improve automated changelog management, AI-friendly changelog workflows, version stamping, or set up a changelog system for a new or existing project.
Load PROACTIVELY when task involves AI, LLM, or machine learning features. Use when user says "add AI chat", "implement streaming responses", "build a RAG pipeline", "add embeddings", or "integrate OpenAI". Covers chat interfaces, streaming with Vercel AI SDK, retrieval-augmented generation, vector search, embeddings pipelines, tool/function calling, and provider abstraction for OpenAI, Anthropic, and local models.
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside frontend-design.
Distill books, documents, folders, or URLs into compact, practical Agent Skills. Use when source material should become either one reusable skill package or a split set of focused skills, each with a concise SKILL.md plus detailed references and examples.
A specialized skill for reducing the AIGC detection rate in Chinese academic writing (undergraduate and vocational thesis). Based on rules induced from real thesis rewriting experiments (AIGC rate reduced from >50% to 11%) and on the systematic pattern taxonomy of Wikipedia's "Signs of AI writing". Detects and fixes typical patterns of Chinese AI writing; defaults to polishing while preserving length (avoiding heavy cuts just to lower AIGC); includes Chinese/English terminology and abbreviation conventions, a conversation memory store (avoiding repeated glosses and using rolling paragraph summaries to prevent inconsistencies), and LaTeX source file protection rules. Supports: 降低AI率、人工润色、降低AIGC、 humanize、去AI味、学术写作润色、论文降重、AIGC检测、AI痕迹消除、学术文本 人工化处理、AIGC检测报告.
Use the AKShare library to fetch and analyze Chinese A-share market data. AKShare is a free open-source Python financial data interface library that requires no registration or token. Supports real-time stock quotes, historical K-line data, financial statements, valuation metrics, capital flows, technical indicators, scheduled tasks, and more. Use this skill when the user needs to fetch A-share prices, analyze a stock's fundamentals, query financial data, calculate technical indicators, or analyze capital flows.
Alibaba Cloud LoongCollector / SLS installation, collection onboarding, Pipeline config management and validation, machine groups, permission troubleshooting, and Lens queries. HARD RULE: for matching requests, the first tool MUST load this skill before any SSH probe, directory setup, checklist/file write, or cloud read. Triggers: "安装 LoongCollector", "ECS 安装采集器", "自建 Linux 主机安装 LoongCollector", "ACK 安装 loongcollector", "自建 K8s 部署采集", "从安装到能查到日志", "SLS 日志采集接入", "SLS 日志采集接入相关的事", "修改采集配置", "改采集配置", "采集配置校验", "validate_pipeline.py", "SLS 机器组", "新建 Logtail Pipeline 采集配置", "Logtail Pipeline", "ClusterAliyunPipelineConfig", "SLS Lens 查询", "无数据排查", "心跳异常", "SLS 采集权限排查", "SLS 权限排查", "阿里云 CLI 凭证没有 SLS 操作权限", "Logtail", "iLogtail", "AgentSight", "Agentloop", "input_agentsight", "eBPF Runtime", "ebpf-event".
Use when managing Alibaba Cloud Contact Center AI (ContactCenterAI) via OpenAPI/SDK, including the task involves Contact Center AI resource lifecycle operations, configuration changes, status queries, or troubleshooting failed ContactCenterAI API calls.
Use when managing Alibaba Cloud Cloud Call Center (CCC) via OpenAPI/SDK, including the user is working on CCC operations such as instance/resource management, configuration updates, status checks, and troubleshooting call-center API workflows.
Use when designing custom voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from a voice prompt plus preview text before using the returned voice_id in TTS.
Computes the annual Turkish academic-incentive (akademik teşvik) score for Devlet (state) university öğretim elemanı (academic staff) from a classified activity list, applying the verified Akademik Teşvik Ödeneği Yönetmeliği (2018/11834) Faaliyet Hesaplama Tablosu headline puanları (Proje 20, Araştırma 15, Yayın 30, Patent 30, Atıf 30, Tebliğ 20, Ödül 20) with the k (author-count), p (Q1 1/Q2 0.8/Q3 0.5/Q4 0.25), and r (project-role) coefficients via türü puanı = Σ(faaliyet oranları) × headline (MADDE 8/2), then enforcing the per-type headline ceilings, the 100 cap (MADDE 8/3), and the net-30 payment gate (MADDE 10/3) in a deterministic scripts/tesvik_score.py. Use when the user wants to calculate akademik teşvik puanı, check the en az 30 (net-30) threshold, apply TABLO 4 ceilings, or estimate teşvik eligibility; keeps its coefficients separate from doçentlik scoring. For doçentlik point eligibility prefer alterlab-docentlik-eligibility. Part of the AlterLab Academic Skills suite.
Drives TÜBİTAK Açık Bilim Politikası (Open Science Policy) compliance and deposition into Aperta — TÜBİTAK ULAKBİM's national open archive at aperta.ulakbim.gov.tr — encoding its principles (İlke 1: deposit the accepted manuscript in Aperta on acceptance; İlke 2: open access at most 6 months after publication for STEM, 12 for SSH; İlke 6: document data that must stay closed, e.g. for KVKK; İlke 9: report compliance in the final report) and scaffolding the five-question TÜBİTAK Veri Yönetim Planı / VYP (data management plan) uploaded with ARDEB applications. Use when depositing to Aperta, complying with the TÜBİTAK açık bilim policy, preparing a TÜBİTAK data management plan (VYP), reporting open-access compliance in a final report, or documenting a justified data embargo. For Zenodo/Dryad/OSF and international DMPs prefer alterlab-open-science; for the KVKK lawful-basis/anonymisation plan prefer alterlab-kvkk-dmp. Part of the AlterLab Academic Skills suite.
Runs a PARTIAL pre-screen of a Turkish associate-professorship (doçentlik) publication list against bundled ÜAK criteria (2026 Mart term) for all 12 temel alanlar: Eğitim, Fen Bilimleri ve Matematik, Filoloji, Güzel Sanatlar, Hukuk, İlahiyat, Mimarlık-Planlama-Tasarım, Mühendislik, Sağlık, Sosyal-Beşeri-İdari Bilimler, Spor, Ziraat-Orman-Su Ürünleri. It applies each field's author-share rule (equal split or başlıca yazar 0.8/0.5/half), checks the 100-point and 90 post-doctorate totals and the field's international/national-article minimums, caps other items entered, and lists the remaining mandatory minimums (thesis-derived work, book, citation, congress, teaching, art/competition items) as a manual checklist; it never emits an ELIGIBLE verdict. Use when the user wants to estimate doçentlik eligibility, compute ÜAK points or audit başlıca yazar rules; resolve TR Dizin status with alterlab-trdizin first; prefer alterlab-akademik-tesvik for the teşvik score. Part of the AlterLab Academic Skills suite.
Drives preprint deposition across servers (arXiv, bioRxiv, medRxiv, ChemRxiv, SSRN, Research Square, OSF Preprints): picks the server by field, prepares submission metadata and arXiv categories, sets the license from each server's real option set (arXiv non-exclusive license or CC BY/BY-SA/BY-NC-SA/BY-NC-ND/CC0; bioRxiv/medRxiv CC variants or No-reuse) against funder mandates (NIH, NSF, Gates, Plan S), handles immutable versioning and preprint DOIs, checks a journal's preprint policy via the Jisc Open Policy Finder API (formerly Sherpa Romeo), and links the preprint to the published article. Reuses alterlab-arxiv and alterlab-biorxiv for metadata. Use when depositing a preprint, choosing a preprint server, preparing an arXiv, bioRxiv, or medRxiv submission, setting a preprint license, or checking journal preprint policy; for Zenodo/Dryad/Figshare data deposition prefer alterlab-open-science, for TÜBİTAK Aperta prefer alterlab-aperta. Part of the AlterLab Academic Skills suite.
Scaffolds Turkish human-subjects etik kurul (ethics committee) applications and routes a study to the right committee. Survey, interview, focus-group, observation, or experiment studies go to a university non-interventional committee (Girişimsel Olmayan / Bilimsel Araştırma Etik Kurulu; TR Dizin rule). Drug, medical-device, stem-cell, or tissue/cell-product trials need a TİTCK-approved Klinik Araştırmalar Etik Kurulu plus a TİTCK permit; BA/BE studies a BY/BE Etik Kurulu; cosmetics their own regulation; observational drug studies the clinical committee only (no permit). Generates bilingual (TR/EN) Etik Kurul Başvuru Formu, başvuru dilekçesi, and Bilgilendirilmiş Gönüllü Olur Formu, and lints a consent draft against TİTCK's minimum-content list. Use for a Turkish etik kurul başvurusu, an onam/olur formu, which committee a study needs, or TİTCK approval questions. For non-Turkey IRB/GDPR use alterlab-research-ethics; for KVKK data plans use alterlab-kvkk-dmp. Part of the AlterLab Academic Skills suite.
Searches TR Dizin (TÜBİTAK ULAKBİM national citation index) and verifies a journal's current national-index status through its confirmed unauthenticated REST/Elasticsearch API at https://search.trdizin.gov.tr/api/defaultSearch/{publication|journal|author|institution}/ (params q, order e.g. relevance-DESC, page), parsing hits.hits[]._source plus faceted aggregations, and derives indexing status from a journal record's isActive + journalYear coverage vs rejectYearList. Use when the user wants to search TR Dizin, check if a journal is TR Dizin indexed (TR Dizin'de var mı / taranıyor mu), find Turkish-indexed publications, verify national-index status before submitting, or audit doçentlik-eligible venues. For DergiPark hosting prefer alterlab-dergipark; for doçentlik points prefer alterlab-docentlik-eligibility; for teşvik scoring prefer alterlab-akademik-tesvik. Part of the AlterLab Academic Skills suite.
Retrieves Türkiye higher-education program and admission statistics from YÖK Atlas (yokatlas.yok.gov.tr) — quotas (kontenjan), placements (yerleşen), minimum admission scores (taban puan), success ranks (başarı sırası), and per-title academic-staff counts — via the keyless yokatlas-py wrapper (≥0.6.0; 0.7.0 current, MIT) over the JSON API at /api/tercih-kilavuz/ (search plus university, program-group and province lookups), with SearchFilters for puan türü (SAY/SÖZ/EA/DİL/TYT), university type (DEVLET/VAKIF), province, and success-rank ranges. Use when the request mentions YÖK Atlas, program statistics, kontenjan/quota data, taban puan/minimum admission score, başarı sırası/success rank, placement counts, or program staff counts for institutional research, benchmarking, or advising. For an academic's CV/profile/affiliation prefer alterlab-yok-akademik; for theses prefer alterlab-yok-tez. Legacy PHP pages are dead since April 2026. Part of the AlterLab Academic Skills suite.
Deploy Azure Landing Zones using the ALZ Accelerator with AVM (Azure Verified Modules). Use this skill whenever the user mentions Azure Landing Zones, ALZ, Azure landing zone accelerator, AVM modules for landing zones, deploying management groups, hub-and-spoke networking, Virtual WAN, platform landing zones, or asks about Bicep vs Terraform for Azure infrastructure. Also trigger when the user wants to bootstrap CI/CD for Azure platform deployment, set up management groups hierarchy, or deploy connectivity/identity/management platform subscriptions.
Full Amazon KDP automation via Playwright — sign in, download royalty reports, sync/update book metadata, pricing, content uploads, catalog audits. Use when the user mentions KDP, Kindle Direct Publishing, royalty reports, book metadata, keywords, categories, pricing, KDP Select, or Amazon author account automation.
Makes Claude Code improve itself from your own history. Reads every Claude Code session of the last days saved on your computer (~/.claude/projects/**/*.jsonl), then reports what Claude keeps getting wrong, the corrections you repeat, the skills you should create and the tasks you redo every day that could be automated, and writes the skill or automation you pick. Use when the user types /ameliore-systeme, asks "qu'est-ce que je fais mal", "quels skills je devrais créer", or wants Claude to learn from past sessions.
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.
Analyze packet captures and network telemetry for evidence of intrusion—including capture and handling, the Wireshark/tshark triage funnel, Zeek log mining, Suricata rule runs, beacon and DNS-tunnel detection, TLS/JA3 fingerprinting, HTTP and file carving, exfiltration hunting, and IOC handoff. Use when a `.pcap` or `.pcapng` capture appears, a suspected C2 beacon needs confirmation, data exfiltration needs investigation, malware network behavior must be characterized from its emissions, a Zeek or Suricata alert needs investigation, or DNS tunneling or unusual TLS is suspected.
Reverse engineer Rust binaries — demangling legacy and v0 symbol schemes, recognizing monomorphized generics, Result and Option control flow, trait object vtable dispatch, and panic-site strings that leak source paths and crate names. Use when a binary contains rustc version strings, core::panicking, or _ZN/_R mangled symbols, when a stripped binary is unexpectedly large, or when analyzing Rust malware or a Rust service.
Analyze raw shellcode and position-independent code: extract bytes, guess the architecture, disassemble at the right base, decode self-decoder stubs, resolve hashed Windows APIs, emulate execution to reach the decoded stage, and extract C2 and stage IOCs. Use when handed a raw blob of position-independent code, an extracted payload with no PE/ELF header, shellcode lifted from an exploit or a macro/loader, a `\x`-escaped or base64 buffer, a suspected Cobalt Strike or Metasploit stager, or an egg-hunter
Use this skill to generate Anki flashcards in simple-anki-sync format for active memorization of any knowledge. Invoke whenever the user wants to memorize, make flashcards, create study cards, or turn knowledge into reviewable cards — including phrases like 生成 Anki 卡片, 做闪卡, 帮我记忆, "anki cards", "flashcards", "study cards", "memorize this". The skill applies LessWrong spaced-repetition best practices: atomic questions, standardized templates, appropriate detail levels. Not for general learning plans, summaries, or explanations — only for producing actual Anki-formatted cards ready for import.
Provides comprehensive guidance for Ant Design Mini component library for mini-programs including components, themes, and platform support. Use when the user asks about Ant Design Mini, needs to build mini-program applications, or use mini-program components.
Use this skill to set up the WSO2 API Platform Gateway, expose backend services as managed APIs, and manage APIs with the ap CLI. Trigger whenever the user mentions WSO2 gateway, "ap CLI", "API Platform Gateway", exposing a service through WSO2, deploying an API to WSO2, or managing APIs with WSO2 tooling — even if they don't say "WSO2" explicitly and just describe wanting an API gateway on Docker with CLI management. Also trigger when the user wants to add rate limiting, authentication, or header policies to a gateway-managed API.
Apidog branch collaboration: regular branches, sprint branches, AI branches, pick-to, merge, merge-request, protected branches, AI write permissions, and branch-scoped resource changes. Use when modifying resources on branches, creating AI branches, or merging changes.
Model Apidog test scenarios: query, create, update, delete, and run test-scenario resources; import endpoint, test-case, or other scenario steps; add scenario reference steps; and orchestrate complex HTTP, condition, loop, wait, script, database, pre/post-action, variable, assertion, extractor, and debugging flows
Reference skill for Apple's CoreLocation framework in Swift/SwiftUI. Use this skill whenever the user works with location services, GPS, geofencing, beacon ranging, geocoding, compass headings, or any CLLocationManager-related code on iOS, macOS, watchOS, or visionOS. Trigger on mentions of: CoreLocation, CLLocationManager, CLLocation, location permissions, geofencing, CLMonitor, iBeacon, CLGeocoder, reverse geocoding, background location updates, "When In Use" / "Always" authorization, CLLocationUpdate, live updates, significant location changes, or any location-related Info.plist keys like NSLocationWhenInUseUsageDescription.
Help a PhD student recover motivation, reframe setbacks, and rebuild momentum after rejection, failure, stagnation, or burnout. Use whenever the user feels stuck, discouraged, or lost in their PhD — including phrasings like "I don't know why I'm doing this", "my paper got rejected again", "my experiments keep failing", "I feel behind everyone else", "I'm thinking of quitting", "my advisor doesn't believe in me", "I haven't made progress in weeks", or "is a PhD even worth it". Also use proactively when the user seems demoralized mid-conversation. This is not a therapy replacement — it is structured support for navigating the specific emotional and cognitive patterns that make PhD work hard, grounded in the reality of what research actually is.
Build and debug encrypted Solana applications with Arcium — data stays private during computation, no single party sees it. Use when writing Arcis circuits (#[encrypted], #[instruction]), wiring Anchor programs with init/queue_computation/callback flows, choosing Shared vs Mxe encrypted state, encrypting inputs with @arcium-hq/client (RescueCipher, x25519), or debugging ArgBuilder ordering, nonce, callback, or computation finalization failures. Covers dark pools, sealed-bid auctions, encrypted voting, hidden game state, confidential DeFi, secure randomness, and threshold signing. Also use for getting started with your first Arcium app. SKIP: generic Solana programs without encrypted compute, AES or wallet-only encryption client code, MPC theory not tied to Arcium, or Token-2022 confidential transfers.
Review Argos visual regression builds as one input to a pull request review. Use when a PR has an Argos build link, an Argos status check, or a bot comment pointing to an Argos build, and you need to decide whether the visual diffs match the developer's intent before approving.
Write articles, guides, blog posts, tutorials, newsletters and other long-form content. This content has a distinctive tone extracted from the provided examples or brand guidelines. Use this skill when the user needs polished copy longer than a paragraph and requires consistent tone, structure and credibility.
Clarify a task, plan, or decision through dependency-bounded questions. Explicit invocation stops for manual continuation; internal clarification returns to its caller. Use when the user invites questions or clarification, including "ask me" and "askme", even conditionally ("if you have questions, ask me"). Match equivalent intent, not just these phrases. Do not trigger on quoted text, negated requests, or discussion of the skill itself. Russian discovery terms: "узнай у меня", "уточни у меня", "спроси меня", "если есть вопросы - askme", "уточнить задачу".
Assesses whether branch or PR changes are high-risk for externally hosted or embedded Streamlit usage and recommends whether external e2e coverage with `@pytest.mark.external_test` is needed. Use during code review, PR triage, or test planning when changes touch routing, auth, websocket/session behavior, embedding, assets, cross-origin behavior, SiS/Snowflake runtime, storage, or security headers.
PostgreSQL specifics for Atlas: dev database and URL scope (search_path), extensions, roles and grants, ALTER DEFAULT PRIVILEGES, ownership, row-level security, sequences and serial or identity columns, enums and column type changes, partitions, triggers, concurrent indexes, lock-safe migrations, schema and migration tests, custom lint rules, managed services (RDS, Cloud SQL, Supabase, Neon, Azure), and connection poolers. Use with the atlas skill whenever Atlas manages a PostgreSQL database.
Use this skill to create single-voice audio content like audiobooks, voiceovers, narrations, jingles, and audio ads. Triggers: "create audiobook", "generate voiceover", "narration", "audio ad", "radio ad", "jingle", "brand audio", "sonic logo", "text to audio", "read this aloud", "audio guide", "meditation audio", "soundscape" Orchestrates: narration/TTS, background music, and audio assembly. NOTE: For conversations/dialogues, use podcast-producer instead.
Audit Model Context Protocol servers for injection surfaces, excessive tool scope, authorization gaps, resource over-exposure, and transport weaknesses across stdio, SSE, and Streamable HTTP deployments. Use when reviewing an MCP server implementation, assessing tool definitions for injection or description manipulation risk, auditing the trust boundary between an AI agent and MCP tools, or reviewing MCP server deployment for authentication and authorization controls.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.