agentsclimarketplace

The catalog

609,856 rows, by stacks then stars

  • Dining places skill

    ddalgrande/dining-places-skill Skill

    2★

    Turns a user's exported Google Maps saved places (starred places + custom Lists from a Google Takeout "Saved" + "Maps" export) into a personal dining knowledge base, then gives eating-out advice that (1) surfaces relevant places they already saved, (2) infers their taste, and (3) supplements with fresh web/Places research — clearly labelling what is "yours" vs "new", plotting results on a map, summarising them in a comparison table, and offering a booking link per place. Use whenever the user asks where to eat / drink, for restaurant or bar recommendations, for somewhere near a location, or references their saved places / want-to-go list / starred spots. Works at home and while travelling. Trigger phrases: "where should I eat", "dinner rec", "good restaurant near", "from my saved places", "my want to go list", "somewhere for drinks", "book a table", "what's good in this area", "use my saved spots".

  • Mac disk cleanup

    Mateeb11/skills/skills/mac-disk-cleanup Skill

    2★ repo

    Scan a Mac for reclaimable disk space — caches, duplicate editor extensions, package-manager caches (npm/gradle/uv/pnpm/Homebrew), Docker images and build cache, iOS simulators, node_modules and Python venvs, app caches, and old downloads — then present what was found grouped by size and safety, and let the USER choose what to delete. Use this skill whenever the user wants to free up disk space, clean up their Mac, says their disk is full or storage is low, asks "what can I delete", "what's taking up space", "clean my caches", or wants to reclaim gigabytes — even if they don't use the exact words "cleanup" or "cache". Always show findings before deleting and never delete real user data without explicit confirmation.

  • Fastbound api

    FastBound/skills/skills/fastbound-api Skill

    no license2★ repo

    Build, debug, and reason about integrations with the FastBound API — the REST API behind FastBound's electronic A&D (acquisition & disposition) bound book and ATF Form 4473 software for FFL holders. Use this skill whenever the user mentions FastBound, FFL software, electronic bound book, A&D book, ATF compliance APIs, ATF Form 4473 automation, NFA dispositions, firearm acquisition/disposition records, FastBound webhooks, or asks about integrating a POS, e-commerce, ERP, range, or manufacturing system with FastBound. Also use when the user is calling endpoints under cloud.fastbound.com, working with OAuth authorization_code or device_code flows for FastBound, handling FastBound webhook signatures, or troubleshooting FastBound API errors. Even if the user does not say "FastBound" explicitly — for example "I need to log a firearm acquisition with serial number X to our bound book" — invoke this skill.

  • Product completion wrap

    pamiray-m/product-completion-wrap Skill

    2★

    Apply a vendor-neutral post-build completion standard to an existing product repository. Use when explicitly asked to finish, harden, package, validate, prepare, or launch a substantially completed product. Covers functional closure, engineering, security, branding, legal drafts, UI, website, SEO, payments, email, testing, operations, documentation, and evidence-based release readiness.

  • Debug protocol

    adityaarakeri/senior-agent-skills/skills/debug-protocol Skill

    no license2★ repo

    A disciplined, scientific method for diagnosing bugs, failing tests, crashes, and regressions. Use this whenever something is broken and the cause is not already known: error messages, stack traces, "it worked before", flaky tests, wrong output, weird behavior, or after two failed fix attempts on the same problem. Reach for this instead of guess-and-check editing.

  • Conversion accessibility polish

    divyanshu-iitian/agent-website-design-skills/conversion-accessibility-polish Skill

    2★ repo

    Improve an existing website or web app's decision clarity, trust, forms, UX copy, and accessibility without dark patterns. Use when an agent must polish CTAs, navigation, pricing, onboarding, empty or error states, keyboard behavior, semantic HTML, focus, contrast, or the end-to-end conversion path.

  • Agent sandbox

    ariana-dot-dev/cloud-sandbox-vm-skills/skills/agent-sandbox Skill

    2★ repo

    Give an AI agent its own sandboxed cloud machine to work in — a full root Ubuntu VM (SSH, Docker, IPv4, all toolchains) where the agent can edit code, run commands, and host services without touching the user's host. Claude Code and Codex harnesses are preinstalled. Per-second billing, ~10x cheaper than E2B/Modal. Use as the execution environment for an autonomous agent.

  • Roblox best practices

    andrian-syh/roblox-best-practices-skill/roblox-best-practices Skill

    2★ repo

    Framework-agnostic Roblox/Luau coding standards. Use when writing, reviewing, or refactoring any Luau code (Script, LocalScript, ModuleScript) in a Roblox project, or when the user asks to keep best practices in mind as standing guidance — enforces the VARIABLES/FUNCTIONS/INITIALIZATION section layout, naming rules, performance, memory, networking, and security best practices regardless of the project's framework, folder structure, or game genre. Supports two modes — Default (apply this skill's conventions as-is) and Adaptive (study the project's existing coding conventions first, confirm with the user, then apply best practices in the project's own style) — adapts to community libraries (ProfileStore, Packet, Trove, Knit, Fusion, ...) when the project uses them, and honors user-selected supervision levels (!ask / !bal / !go) controlling how often the agent confirms before acting.

  • Hotel booking assistant

    ran-net/hotel-booking-assistant Skill

    2★

    Research, compare, and shortlist lodging from current evidence using normalized stay totals, independent reviews, room-only/meal-plan comparisons, cancellation, availability confidence, and booking-site options. Analyze a supplied hotel shortlist or JSON dataset and produce an evidence-backed HTML hotel report. Prepare booking decisions and assist the user's booking steps, but never transact. Use for "find me a hotel", "cheapest booking site", "ホテルを探して", "ホテル予約を比較して", or "最安サイトを調べて". Not for long-term rentals or residential property searches.

  • Event outbound

    luminik-io/event-outbound-skill/skills/event-outbound Skill

    2★ repo

    Create validated email and LinkedIn outreach sequences for B2B events, from pre-event to post-event, grounded in buyer priorities and checked by a local validator.

  • Aml kyc kryptodienstleister

    kryptobesteuern/claude-fuer-krypto-und-steuern/krypto-aufsichtsrecht-blockchain/skills/aml-kyc-kryptodienstleister Skill

    no license2★ repo

    Prueft welche Sorgfalts- und Identifizierungspflichten nach Geldwaeschegesetz einen Kryptowertedienstleister treffen. Methodik Risikoanalyse Kundensorgfalt Verdachtsmeldung. Output ausformulierte Pruefung mit konkreten Pflichten und Schwellenwerten.

  • Dotagents standard

    zaventh/dotagents-standard-skill/skills/dotagents-standard Skill

    2★ repo

    Set up, author, and navigate the dotagents standard — a slim AGENTS.md "router" at the repository root plus a hidden .agents/ directory (rules, context, memory, personas, skills, specs, logs, tasks) that splits agent context into small per-topic files loaded on demand (progressive disclosure). Use this WHENEVER the user mentions dotagents, dotagentsprotocol.com, the .agents/ directory, or an "AGENTS.md router"; wants to organize, split, slim down, or migrate a monolithic AGENTS.md / CLAUDE.md / .cursorrules into structured context; wants vendor-agnostic agent configuration that every tool (Claude, Cursor, Gemini, Copilot, local LLMs) can read; or is working inside a repository that ALREADY contains an AGENTS.md or a .agents/ directory and needs to know how to discover and load the right context. Also covers the broader ".agents Protocol" superset (global ~/.agents/ layer, mcp.json, structured sub-agents / tasks / memories, and the .agents Hub for sharing configs).

  • Hina

    RamanaNani/agent-router/assets/hina Skill

    2★ repo

    Your conversational personal assistant for Claude Code. Use when the user types /hina or talks to Hina by name. She remembers you across sessions (file-based memory), asks before acting when context is missing, routes the work to the best installed specialist via agent-router, does it, and gets better from your feedback. Runs in the main loop so she can pause and ask you questions.

  • Safe greeting

    charliechenye/SkillGate/examples/preinstall-starter/skills/safe-greeting Skill

    2★ repo

    Returns a short greeting without using tools or external resources.

  • Institutional 13f tracker

    SentiSenseApp/skills/skills/institutional-13f-tracker Skill

    2★ repo

    13F institutional ownership tracker: quarterly hedge fund and mutual fund holdings from SEC 13F filings, by ticker or by manager, with top institutional holders per stock, quarter-over-quarter buying and selling deltas, and activist investor positions across thousands of managers. Use for 13F filings, 13F holdings changes, hedge fund holdings, institutional ownership by ticker, who owns this stock, activist fund positions, and superinvestor portfolios. Read-only. No trading, no purchases, no write operations, no wallet access.

  • Body text and reading

    jpoindexter/typography-skills/skills/body-text-and-reading Skill

    2★ repo

    Typography skills for AI coding agents — 20 focused skills + a /type router, extracted from 10 canonical typography books and reconciled against WCAG 2.2 and current browser behavior.

  • Melsec iqr simple cpu comm csv

    mokouliszt/iQRSimpCPUCommSkill/skills/melsec-iqr-simple-cpu-comm-csv Skill

    2★ repo

    MELSEC iQ-Rシリーズ(三菱電機シーケンサ)のCPUユニット内蔵Ethernetポート部「シンプルCPU通信機能」の設定CSVファイルを生成・検証・解析する。GX Works3 が "シンプルCPU通信設定" 画面でインポート/エクスポートする UTF-16LE BOM付タブ区切りCSV(バイト一致レベル)を生成する。ユーザが「シンプルCPU通信」「Simple CPU Communication」「内蔵Ethernet」「GX Works3 のCSVインポート/エクスポート」「機器種別」「定期交信」「要求時交信」「実行間隔」「通信開始待ち時間」「初回交信設定」「異常監視時間」「交信相手IPアドレス」「対象号機」「シンプルCPU通信診断」などに言及した場合、または iQ-R から iQ-R/Q/L/iQ-F/iQ-L/A/AnS/FX3/SLMP対応機器 とのEthernet経由デバイス送受信パラメータの設定ファイルを作成・編集・検証したい場合は必ずこのSkillを参照すること。デバイスそのものの分類体系・命名規則は姉妹Skill `melsec-iqr-device-overview`、個別デバイスの数値スペックは `melsec-iqr-device-specifications` を併用すること。

  • Fable thinking

    uladzemer/fable-thinking Skill

    2★

    Operating discipline distilled from Claude Fable 5 for sessions and subagents on weaker models (Opus 4.x, Sonnet 5/4.x, Haiku 4.5) doing agentic coding. Load it at the START of any non-trivial task when not running on Fable 5: debugging, refactoring, changes across 2+ files, or unfamiliar code; and instruct a subagent on Opus/Sonnet/Haiku to read this skill with a non-trivial assignment. Triggers include "think like Fable", "fable-mode", "turn on discipline", "work carefully", dispatching a subagent on a weaker model, and repeated mistakes or rework in the session. NOT needed for trivial edits (rename, typo, one-liner) or purely conversational answers.

  • Hekouwang claude skill doctor skill

    huiyonghkw/hekouwang-claude-skill-doctor-skill Skill

    2★

    会勇禾口王的AI笔记 · Agent Skill(SKILL.md)体检器。检查一个 Claude/Agent Skill 是否 符合"按需加载的指令包,不是单文件巨石"的最佳实践——评 description 触发质量、SKILL.md 篇幅、渐进披露(references/ 拆分)、脚本外置、可移植性(无硬编码绝对路径)、安全(无硬编码 密钥),给出评分卡 + 按优先级的修复建议,并可代为重构。触发:用户说「检查我的 skill / SKILL.md 体检 / 这个 skill 规范吗 / claude-skill-doctor / audit skill / lint SKILL.md / 我的 skill 太长了 / skill 拆分 / 看看我的 skill 合不合规 / skill 对齐官方规范」。 任何"评估/审查/优化某个 Agent Skill 质量或结构"的请求都应触发。

  • Designing postgres schemas

    pumarogie/claude-postgres-skills/skills/designing-postgres-schemas Skill

    2★ repo

    Guides Postgres schema design when creating tables, choosing keys and data types, defining foreign keys and deletion behavior, modeling JSONB, or planning retention for unbounded event and log data.

  • Screening alert adjudication

    amir-the-sanctions-guy/screening-alert-adjudication Skill

    no license2★

    Adjudicates whether a hit generated by sanctions, PEP, or adverse-media screening is a true positive, false positive, or requires human escalation. Use whenever a user presents a screening alert, a name match against a watchlist (OFAC SDN, EU consolidated list, UK OFSI, UN list, PEP list, adverse media hit, etc.), or asks to clear a screening hit / reduce false positives / determine whether a flagged name is actually the listed party. Use even when the user describes the task casually — "is this person actually on the sanctions list", "did we get a real match", "clear this alert", "I have a hit on X" — these are all screening-adjudication tasks. Produces a deterministic determination with full audit trail (structured JSON + human-readable narrative). Designed for use by compliance analysts and screening systems.

  • Deep read web

    TieZhuzhu/deep-read-web/skills/deep-read-web Skill

    2★ repo

    使用 Playwright 读取公开网页或登录后网页的最终 HTML。适用于用户想要网页 HTML、需要在手动登录后继续读取页面,或希望分析登录后最终渲染内容的场景。优先使用本地 exe;如果只有 skill 且没有 Python,则优先运行 skill 自带的二进制安装脚本并默认下载精简 small 包,不够时再升级为 full 包。

  • Agent cross handoff

    Rivercoco/agent-cross-handoff-skill/.agents/skills/agent-cross-handoff Skill

    2★ repo

    Cross-agent project migration and handoff workflow for Codex, Claude Code, and other coding agents. Use when the user wants to package, export, hand off, transfer, resume, inherit, import, or take over a Git project across machines, OSes, Codex CLI/App, Claude Code, or other agents. Also use for short Chinese requests such as 打包项目, 准备移交项目, 接手项目, 继承项目, 迁移到 Claude, 迁移到 Codex, 检查能否迁移, or 打包本地 Agent 配置.

  • Lattice swarm

    sectersion/lattice/skills/lattice-swarm Skill

    2★ repo

    Orchestrator-side guidance for running a Lattice agent-threading server and driving multiple worker agents against it as their real coordination channel. Use when spinning up a multi-agent swarm test/demo against Lattice, seeding roles/threads before agents start, or writing an ultracode Workflow script that fans out fixer/reviewer-style agents over Lattice. Companion to the `lattice` skill, which is written for the workers themselves (register/reply/claim/subscribe) — this one is written for whoever summons them.

  • Claude code deep review

    aksheyw/claude-code-deep-review Skill

    2★

    Iterative deep review using 14-lens methodology. Use when reviewing ANY plan, code review, architecture doc, test plan, or security assessment — before claiming it is complete. Runs multiple passes from different analysis angles until no new findings emerge. Each lens catches issues invisible to previous lenses. Found 14 production bugs (2 ship-stoppers) in its first use. ALWAYS use this when the user asks to review something thoroughly, verify completeness, audit a document, or check if anything was missed. Also triggers on "did you miss anything", "is this thorough", "are you sure", "check again", or similar phrases.

  • Dont kick me out

    De-Cri/dont-kick-me-out/skills/dont-kick-me-out Skill

    2★ repo

    Keeps the developer actively in the loop while Claude writes code, instead of letting them slip into autopilot. Use this skill for any non-trivial coding task — implementing a feature, fixing a bug, refactoring, designing a system — where the user would otherwise just accept whatever Claude produces without understanding it. Trigger it whenever code is being written or modified, not just when the user explicitly asks to "explain" or "teach."

  • Viral post distiller

    lichenyan0901-lgtm/viral-post-distiller Skill

    2★

    拆解抖音爆款作品,提炼"爆款基因",并基于基因为新主题生成同款笔记。给一条抖音链接,自动通过 TikHub API 抓取数据,从封面标题、内容结构、情绪需求、爆款基因四个维度做严谨拆解;用户给出新主题后,skill 直接产出 5 个标题备选 + 完整正文 + 话题标签 + 封面建议。当用户提供抖音链接、提到"拆爆款""分析这条""为什么这条火了""帮我拆解""挖一下博主信念""我也想写一条同款",或想理解某条作品成功原因 + 想立刻复刻发布时,必须使用本 skill。即使用户没有明确说"拆解"或"复刻",只要意图是想搞清楚某条抖音视频成功的原因或想做同款,也使用本 skill。本 skill 在 Claude Code 本地运行,需要 TikHub API Key 和 Python 3.9+。v0.2 仅支持抖音。

  • Skill

    Hectelion-SA/claude-investor-shortlist/skill Skill

    2★ repo

    Build a structured Excel investor shortlist (M&A or fundraising mandate) by combining local investor databases, Outlook contacts, web search (Firecrawl) and email enrichment (Dropcontact). Output is a 2-tab .xlsx (branded cover page + 31-column investor table with full transaction pipeline). Trigger when the user says "build an investor list", "investor shortlist", "shortlist for X", "M&A target list", or invokes /investor-shortlist.

  • Skill crm customer management

    zavora-ai/skill-crm-customer-management Skill

    no license2★

    Orchestrate CRM workflows across Salesforce, HubSpot, Zoho, and Pipedrive — customer 360 lookups, deal pipeline management, activity logging, and customer onboarding. Use when looking up a customer, checking deal status, logging a call or meeting, reviewing pipeline health, onboarding a new customer, finding stalled deals, or preparing for a customer meeting.

  • Behuman

    w3nabil/behuman Skill

    2★

    "BeHuman" intends to assist AI in thinking and writing like a human statistically using the novel Penta-State Probabilistic Model.

  • Oracle apex ptbr

    Maxwbh/oracle-skills-ptbr/skills/oracle-apex-ptbr Skill

    2★ repo

    Oracle APEX 24.2 — desenvolvimento e dicionário de metadados. ATIVE em Dynamic Actions, Interactive Report, Interactive Grid, Classic Report, Page Process, AJAX Callback, Validations, Authorization Schemes, pagination, LOV, APEX_APPLICATION_*, APEX_APPLICATION_PAGE_*, APEX_WORKSPACE_*, APEX_APPL_*, Workflows, Tasks, AI configs, ACL, JSON Sources, APEX_ACTIVITY_LOG. Frases — "página APEX", "region IR", "IG editável", "process no submit", "qual view APEX usar", "auditar paginação APEX". NAO ATIVE em PL/SQL puro, ORDS endpoints, DBA operacional. Para naming use oracle-trivadis-ptbr. Templates em assets/.

  • Brand voice

    0xelitesystem/claude-skills-templates/skills/brand-voice Skill

    2★ repo

    Apply a configured brand voice and tone guide to drafts, rewrites, and edits. Use whenever the user wants text edited to match their team's voice, asks for tone adjustments, or wants drafts brought into compliance with a style guide. Triggers on "rewrite in our voice", "apply our tone", "edit this draft", "make this sound like us", "fix the voice", or any rewrite request where consistency with a brand style is the goal. Always read references/brand-voice.md before making edits, and use this skill rather than free-form rewriting when style consistency matters.

  • Competitive intelligence

    SkillMedev/gtm-launch/skills/competitive-intelligence Skill

    2★ repo

    Map competitors across positioning, product, pricing, proof, and weaknesses, then turn the research into sales-ready battlecards with an update cadence. Use when someone asks "what are our competitors doing", "build a battlecard", "how do we compare to X", "why are we losing deals to X", or before a pricing or positioning decision. Do NOT use for designing long-term defensibility strategy - use competitive-moat instead; for a public comparison landing page use comparison-page-builder; for rep-facing objection scripts beyond the battlecard use objection-handler.

    The same file is in 2 other repositories

  • Backtest expert

    xonevn-ai/xone-trading-skills/skills/backtest-expert Skill

    2★ repo

    Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

    The same file is in 2 other repositories

  • Animate roblox characters

    dillydog580/animate-roblox-characters/animate-roblox-characters Skill

    2★ repo

    Create, revise, polish, inspect, export, and preview complete stylized Roblox R6 and R15 character animations on authentic Studio-derived Blender rigs through MCP. Use when Codex must make Roblox walks, runs, idles, attacks, emotes, jumps, or other full-body actions; import or validate a real Roblox Motor6D/control or skinned rig; repair foot sliding or robotic motion; polish Graph Editor curves; export through the correct .rbxanim or FBX pipeline; produce a verified animated GIF; or optionally validate playback in Roblox Studio.

    The same file is in 2 other repositories

  • Geo seo agent skill

    CodingCossack/geo-seo-agent-skill Skill

    no license2★

    Use for a site-specific GEO / AI-search audit or implementation task on a real URL or domain. Covers crawler access, renderability and indexability, answer-level citability, llms.txt, structured data and entity signals, platform-specific AI search issues, and report generation from those findings. Do not use for generic SEO chat, generic copywriting, or agency CRM / proposal work unless the user explicitly asks for those inside a GEO engagement.

  • Submit an issue

    yegor256/bugscribe/skills/submit-an-issue Skill

    2★ repo

    Files one already-identified bug as a GitHub issue against one named repository. Use when the user, a code review, or an audit hands over a single finding to file and says "file this bug", "open an issue", "report this defect", "log this on GitHub", or "raise a ticket for this". Confirms the finding is fresh against the codebase, writes a concise report that names the symptom and points at the code, suggests a fix, and pings the repository owner in one comment.

  • Claude md

    dootask/skills/skills/claude-md Skill

    2★ repo

    创建或优化仓库的 CLAUDE.md。

  • Visual explainer

    Cyber-Gen/visual-explainer-skill/skills/visual-explainer Skill

    2★ repo

    This skill should be used when the user asks to "explain," "teach," "walk me through," "help me understand," "break down," or "visualize" something multi-step, when they self-identify as a visual learner, or when they ask for an explainer, primer, field guide, deep-dive, or learning artifact. Also use proactively when the natural answer to a question would be a long-form conceptual explanation the user is likely to read once and refer back to. Produces editorial-grade, scrollable HTML visual explainers that thread a single concrete example through every stage of a multi-step concept (process, lifecycle, framework, journey, mental model, taxonomy, decision tree, or layered topic). Do NOT use for short factual answers, code generation, or single-screen reference cards.

  • Kora v1

    kora-projects/kora-skills/plugins/kora-v1 Skill

    2★ repo

    Build Java/Kotlin services on Kora Framework (ru.tinkoff.kora). Compile-time DI, reflection-free, annotation-processor (Java) or KSP (Kotlin) driven. Triggers - any Kora task, @KoraApp, @Component, @Module, @KoraSubmodule, @HttpController, @HttpClient, @Repository, @Query, @KafkaListener, @KafkaPublisher, gRPC, SOAP/WSDL, @S3.Client, MapStruct, @KoraAppTest, Testcontainers, @ConfigSource HOCON/YAML, OpenAPI codegen, @Json, metrics (Micrometer/Prometheus), tracing (OpenTelemetry OTLP), logging, probes, @Valid/@Validate, @Log/@Mdc, @CircuitBreaker/@Retry/@Timeout/@Fallback, @Schedule*, @Cacheable/@CachePut/@CacheInvalidate, JDBC/Hikari/Undertow. Use when - Kora build/setup/project/dependency/services/concept/asks mentioned.

  • Budget vs actual

    Uhudsavasindankacanokcu2/finance-skills-for-claude/budget-vs-actual Skill

    no license2★ repo

    Compare planned budget against actual spending/revenue, compute variances, and explain what drove them. Produces a variance report with over/under flags and a forward forecast. Use when the user has a budget plus actuals, asks "are we on budget", "where did we overspend", monthly/quarterly review, or wants a simple forecast.

  • Signadot plan

    signadot/agent-skills/skills/signadot-plan Skill

    2★ repo

    Use this skill to author and iterate on Signadot plan specs: discover schema/actions, compose params and steps, create/run plans, inspect outputs and logs, and tag validated plans. It is not for conceptual explanations or running existing tagged plans to validate code changes.

  • Aircraft research

    WPTK/aircraft-research-claude-skill/aircraft-research Skill

    2★ repo

    Use this skill whenever the user wants to research aircraft ownership, trace who owns a plane, or investigate the entity behind a tail number / N-number. Triggers include: any mention of 'who owns this plane', 'look up this tail number', 'research this aircraft', 'N-number lookup', or when the user shares ADS-B data, FAA registry screenshots, adsbdb output, or typed registration info and wants to know more about the owner. Also trigger when the user pastes aircraft details (registration, operator, type) from any source and asks about the business, person, or entity behind it. This skill is about going beyond the FAA record, tracing shell LLCs back to real people, finding related businesses, and building an ownership picture. Do NOT use for general aviation trivia, aircraft performance specs, or flight tracking without an ownership research angle.

  • Advisories

    ecosyste-ms/skills/skills/advisories Skill

    2★ repo

    Query advisories.ecosyste.ms for security vulnerability metadata aggregated from GitHub Security Advisories, OSV, RustSec, ErlEf and others. Use when checking a package or repo for known CVEs, listing recent advisories for an ecosystem, or fetching CVSS/EPSS scores and patched version ranges.

  • Dostoevsky psychological drama

    ideas-no996/literary-skills/skills/dostoevsky-psychological-drama Skill

    2★ repo

    Use this skill when a user wants a plain fiction premise, scene, dialogue, character sketch, outline, or psychological paragraph transformed into morally charged psychological drama. The skill diagnoses flat writing, extracts hidden shame, desire, fear, public pressure, self-justification, confession pressure, and polyphonic conflict, then rewrites or outlines the material without copying source texts or imitating translation diction.

  • Dream

    timoncool/dream-skill/dream Skill

    2★ repo

    Режим сна Claude — РЕФЛЕКСИВНОЕ ЧТЕНИЕ памяти, заметок и проектов с консолидацией предложений и синтезом insights. **ТОЛЬКО ЧТЕНИЕ** — никаких изменений файлов кроме записи отчёта. Output — два файла: `DREAM-REPORT-<date>.md` (детальный audit trail с JSON-блоками для каждого proposal) и `DREAM-REPORT-<date>.html` (UI в браузере с чекбоксами для выбора что применить). Пользователь открывает HTML, выбирает галочками, нажимает Save → создаётся `DREAM-CHOICES-<date>.json`, потом запускает `wake` skill для применения. Auto mode («поспи сам», «автосон», «autodream») — независимый агент-валидатор проверяет proposals вместо юзера и сразу запускает wake; full auto («полный автосон», «поспи сам полностью») — валидатор решает всё включая delete/purge_trash, ничего не остаётся на ручное решение. Use whenever the user wants to "поспи", "сон", "режим сна", "dream", "поспи сам", "автосон", "autodream", "разберись с памятью", "пройдись по памяти", "обработай заметки", "консолидируй память", "audit memory", "consolidate memory", "reflect on", "что нового я узнал", "что забыл", "synthesize", "сделай выводы из". Reads memory directory + scattered notes in working folder + skims project READMEs/docs as context. Does NOT modify anything except writing the two report files. Расширенная версия autoDream из утечки Claude Code.

  • Accessibility audit

    Nordic-AI/production-readiness-skills/skills/accessibility-audit Skill

    2★ repo

    Reviews web and application accessibility against WCAG 2.2 AA and the European Accessibility Act (EAA, enforceable June 2025). Covers semantic HTML, ARIA usage, keyboard navigation, focus management, color contrast, screen-reader compatibility, form labels and errors, alternative text, motion and animation preferences, internationalization and localization quality, and testing tool integration (axe, pa11y, Lighthouse, Playwright a11y). Use when the user asks about "accessibility", "a11y", "WCAG", "screen reader", "EAA", "keyboard nav", invokes /accessibility-audit, or when the orchestrator delegates on user-facing applications. Stack-agnostic on the approach; framework-specific heuristics for React / Vue / Angular / Svelte / plain HTML.

  • Pricewin booking assistant

    Price-Win/pricewin-skills-hub/skills/pricewin-booking-assistant Skill

    2★ repo

    Recommend hotels and rooms, generate direct OTA booking links for Agoda and Booking.com. Use when booking a hotel, getting room recommendations, or generating booking links.

  • Calibration guard

    ByteStack-Labs/claude-plugins/agent-reliability/skills/calibration-guard Skill

    2★ repo

    Detects and quantifies confidently-wrong behavior: where a model, classifier, agent, or LLM judge is highly confident and incorrect, and where the coupling between confidence and correctness breaks down under distribution shift. Measures calibration on the in-distribution set and again on the production distribution, builds reliability diagrams, reports expected calibration error and the high-confidence error rate, and produces a selective-prediction or escalation rule you can wire into monitoring. Use this whenever someone says a system is "confident but wrong," "sure of itself and failing," or "silently wrong," when accuracy looks fine but trust is eroding, when an LLM judge's scores stop tracking human labels, or when production errors arrive at high confidence with nothing flagging them. Trigger on mentions of calibration, reliability diagram, ECE, overconfidence, false reassurance, abstention, selective prediction, or confidence thresholds. This is the deep confidence workup that production-autopsy hands off to. Every number must be verified, never asserted.

  • Prove done

    xiaogeli/claude-prove-done/.claude/skills/prove-done Skill

    2★ repo

    Before claiming a task is done/fixed/added/scanned, verify with a tool call. Triggers on completion claims ("done", "fixed", "added", "scanned", "committed", "all set", "wrapped up") and forces a verification checklist. Also catches negative-existence claims ("X doesn't exist", "no tests for Y", "missing", "0 tests"). Use this skill whenever you are about to assert that something has been completed, that something exists, or that something does not exist.

  • Ng22 architecture composition

    PavanAnguluri/angular22-agent-skills/skills/ng22-architecture-composition Skill

    no license2★ repo

    Guides Angular 22 architecture toward standalone composition, narrow services, and feature boundaries.

  • Analyzing competitors

    danielkinneyspears/govcon-pursuit-brain/skills/analyzing-competitors Skill

    2★ repo

    Produces a Black Hat competitive assessment for a US Federal opportunity as a wiki of competitor entities. Use when the user needs competitive analysis, a Black Hat review or session, competitor profiling, an incumbent assessment, or to understand the competitive field for a federal bid. Creates and enriches one competitor entity page per likely bidder (modeling each competitor's probable solution, price posture, and win themes from that competitor's point of view) records the team's exposures as risk entities, and renders the competitive-assessment view.

  • Vulnerable skill

    jassics/agentscanner/tests/fixtures/bad/.claude/skills/vulnerable-skill Skill

    2★ repo

    fixture skill with a pinned vulnerable dependency

  • Maestro

    rodovalhofs/maestro/skills/maestro Skill

    2★ repo

    Meta-orchestrator that analyzes the user prompt, searches local skills via hybrid BM25 routing (intents, tags, synonyms, P0-P3), builds an editable dependency graph, and spawns focused subagents after user confirmation. Use when the user invokes $maestro, asks which skills to use, wants optimal skill routing, or has a complex task spanning multiple domains and does not know which skill to call.

  • A skill to do anything in douyin

    JMY2003/a-skill-to-do-anything-in-douyin Skill

    no license2★

    Browser-based Douyin automation for any web-supported operation: persistent-login browser control, reusable CDP sessions, search and browsing, video/detail collection, comments, likes, favorites, notification/message interaction, batch operation plans, content drafting, cover/card generation, and Creator Center publishing. Use when Codex should operate Douyin through the web version with the user's default browser where possible, first-run login, later saved-session reuse, and scripted workflows instead of screenshot/computer-use control.

  • Editorial ai

    Qiyao313/editorial-ai Skill

    2★

    Use this skill whenever the user asks Claude to write long-form content (articles, reports, business writing, industry analysis, corporate communications, op-eds, white papers, deep takes) and needs the output to be source-grounded, fact-controlled, and structurally disciplined — not free-wheeling AI prose. Triggers on requests like "write me a report on...", "draft an article about...", "give me an analysis of...", "I need a piece on...". Especially trigger when the user mentions journalism, editorial standards, industry research, corporate PR, B2B content, white papers, or expresses frustration about AI making up numbers, AI cliches, or AI writing without giving actionable advice. Trigger regardless of length for serious content (crisis statements, press releases, even short op-eds). Do NOT trigger for casual chats, creative fiction, poetry, pure personal essays, or short marketing copy where AI fluency is the goal (Xiaohongshu种草, ad headlines, Douyin captions).

  • Codex council

    ehzawad/codex-council/plugins/codex-council/skills/codex-council Skill

    2★ repo

    Adaptive, context-driven Codex council for project implementation, computer science, software/ML engineering, DevSecOps, research, and other complex work: Claude orchestrates role-framed `codex exec` agents to collaborate and reconcile toward one shared goal. Use for direct invocation `/codex-council:codex-council` or when the user invokes "codex council," "codex coterie," or "codex team." For nearby agent-team language, infer the intended workflow from the live conversation and project state; ask a brief disambiguation only when OpenAI Codex and Claude Code's built-in Agent workflow remain genuinely plausible. On invocation, reconstruct what the user is actually doing, autonomously ask and answer contextual working questions, compose task-specific roles with no built-in catalog, share the decision-complete context, announce the panel, and launch without a manual approval gate.

  • Insider radar

    makeev/alphai-claude-skills/skills/insider-radar Skill

    2★ repo

    Scan SEC Form 4 insider trades and 13F ownership moves for a ticker or a watchlist using the AlphaAI MCP. Use when the user asks about "insider buying", "insider selling", "Form 4 activity", "who's buying <ticker>", "institutional ownership changes", or wants an insider-activity sweep.

    The same file is in 1 other repository

  • Analytics interpreter

    moses607/socialforge/skills/analytics-interpreter Skill

    2★ repo

    Turns raw platform analytics into a funnel diagnosis instead of a data dump. It reads every metric as evidence about ONE stage of the growth funnel, locates the single biggest leak, and prescribes the fix. Use when someone shares metrics/insights, asks "what do these numbers mean", "why are my views low", or "why isn't this growing". Works with any capable model.

  • Authos backend integration

    drmhse/authos_skill/authos-backend-integration Skill

    2★ repo

    Secure backend APIs with AuthOS-issued JWTs and the AuthOS Node server adapter. Use when building an API that must verify AuthOS bearer tokens, enforce JWT claims, add Express middleware, validate JWKS keys, or create a backend-owned session after a browser OAuth callback.