agentsclimarketplace

The catalog

608,666 rows, by stacks then stars

  • Review until clean

    lzehrung/review-until-clean-odw/skills/review-until-clean Skill

    no license1★ repo

    Portable pre-PR review-until-clean workflow and agent skill

  • Tools accessibility audit

    ed1son99/skills/skills/agent-tools/tools-accessibility-audit Skill

    1★ repo

    无障碍审计和测试

  • Changelog generator

    zgroves24/agent-operator-skills/skills/changelog-generator Skill

    1★ repo

    Create user-facing changelogs and release notes from git history by identifying meaningful changes, filtering internal noise, grouping by user impact, and preserving an evidence trail back to commits.

  • 2slides ppt generator

    Ghosteken/agent-harness/archive/skills-community/2slides-ppt-generator Skill

    1★ repo

    AI-powered presentation generation via the 2slides API — create slides from text, match a reference image style, summarize documents into decks, add AI voice narration, and export pages/audio. Use for any "make slides", "create a deck", or "slides from this document" request.

  • Anti slop design

    hu553in/skills/anti-slop-design Skill

    no license1★ repo

    Design, build, refactor, or review distinctive user interfaces that avoid generic AI-generated visual patterns while preserving usability, accessibility, responsiveness, and working interactions. Use for web pages, mobile or desktop app screens, product UI, landing pages, design systems, components, visual polish, frontend implementation that changes rendered behavior or presentation, UI audits, screenshot reviews, or any request to make an interface premium, creative, cohesive, less generic, or explicitly free of AI slop.

  • Alex writing style

    AlexStormwood/agentic-skills/alex-writing-style Skill

    1★ repo

    Alex Stormwood's writing voice for professional, educational, technical, portfolio, blog, project documentation, and code-adjacent writing. Use when asked to draft, rewrite, polish, or review text so it sounds like Alex Stormwood: practical, first-person when appropriate, Australian English, technically grounded, candid, friendly, resistant to generic AI slop, and supported by real references.

  • Mira coach

    eidos11/mira-adultedge/skills/mira-coach Skill

    no license1★ repo

    Run coaching (stage 4) on a MIRA diagnosis JSON produced by mira-diagnose-verify and emit the same JSON with a structured `coaching` key added. Unsupported patterns receive an explicit out-of-scope note — never a silent skip. Use when the user has a diagnosis JSON and wants coaching output, or wants to chain diagnose → coach in a pipeline.

  • Seaworthy

    AmirHosein-Lotfi/Seaworthy/skills/seaworthy Skill

    1★ repo

    Pre-deploy security and secrets gate for AI-built ("vibe-coded") web apps. Scans the repo for the exact disaster pattern behind real 2026 breaches — hardcoded secrets, .env files committed to git history, Supabase Row Level Security disabled or unconfirmed, exposed service-role keys, API/serverless routes with no auth check before a database read or write, wildcard CORS combined with credentials, debug mode left on in production config, publicly-writable storage buckets, and unprotected admin routes. Produces a blunt, plain-English SAFE-TO-SHIP / SHIP-WITH-CAUTION / DO-NOT-DEPLOY verdict instead of an engineer-style audit report — built for someone who mostly prompted an AI to build their app and may not know what RLS or CORS even mean. Use this whenever the user asks "is this safe to deploy", "can I push this to production", "is my app secure enough to launch", "is my app seaworthy", "pre-launch check", "security check before deploy", "am I about to get hacked", or anything adjacent — and proactively run it before any deploy-shaped action (vercel deploy, git push to main/production, "let's launch") even if the user didn't explicitly ask for a security check.

  • Monthly compilation

    conside-ray/llm-journaling-system/skills/monthly-compilation Skill

    1★ repo

    Compile weekly reviews into a strategic monthly review and consolidate promotion candidates using cross-week evidence.

  • Agent self audit

    Xxt-XN/agent-self-audit Skill

    no license1★

    AI coding assistant health check and configuration audit. Detects bloat, drift, security issues, skill gaps, and pipeline violations. Quick mode (6+1 items, under 500 tokens) or Full mode (13 items with trend analysis, predictive warnings, and market intelligence). Use for: system health check, config audit, diagnostic, drift detection, compliance review, self-optimization. 用于:系统健康检查、配置审计、诊断、漂移检测、合规审查、自我优化。

  • Audit config

    Teddy563/mcwrench/skills/audit-config Skill

    1★ repo

    Audits a Minecraft server's configuration tree for performance, security and footgun issues and reports a prioritised fix list. Use whenever the user asks to "audit my config", "check my server config", "review paper-global.yml", "why is my server set up wrong", "is this config safe", "lint my server", or points at a folder containing server.properties, paper-global.yml, paper-world-defaults.yml, paper-world.yml, spigot.yml, bukkit.yml, purpur.yml or velocity.toml. Also use proactively after the user shares any of those files or pastes their contents. Flags online-mode/forwarding mismatches, exposed RCON, YAML tab characters, view-distance/simulation-distance mismatches, missing entity limits, and unsafe unsupported-settings. Reports findings as critical, high, medium and low.

  • Csv validator

    studiomeyer-io/skilldoctor/examples/skills/csv-validator Skill

    1★ repo

    Validates CSV files against an expected header schema and reports row-level mismatches. Use when the user mentions CSV validation, header checks, or cleaning up tabular data exports.

  • Recruiting contact investigator

    Mergemat/recruiting-contact-investigator/skills/recruiting-contact-investigator Skill

    no license1★ repo

    Investigate a vacancy, company, or person to find verified direct routes to people who can influence a hire.

  • Clean skill

    tolztoy/skillci/fixtures/clean-skill Skill

    1★ repo

    Generates a clean, grouped CHANGELOG entry from a list of git commit messages. Use when the user asks to draft release notes or a changelog from recent commits.

  • Axion

    EternisAI/axion-skill/skills/axion Skill

    1★ repo

    Axion forecasting skill: ask the odds of a future event, get a probability backed by research. Portable across Claude Code, OpenClaw, Hermes, and the agentskills.io standard.

  • Ai claim audit

    schizo16/opencode-skillforge/.opencode/skills/ai-claim-audit Skill

    1★ repo

    OpenCode skill that creates, adapts, and audits agent skills from vague user requests. Generates SKILL.md files with spec, audit, and safety boundaries.

  • Skill recommend

    kthxbyte/skill-recommend/skills/skill-recommend Skill

    no license1★ repo

    Silently watches your session for recurring workflows and repeated friction, then gently mentions a relevant skill from the Anthropic official marketplace if one exists. Activate at the start of a Claude Code session. Triggers when the user repeats the same instructions, pastes similar boilerplate more than once, or corrects Claude on the same issue twice. Never interrupts, never installs anything, never suggests more than once per pattern per session. Just a quiet nudge at the right moment.

  • Skill creator

    udohjeremiah/skills/.agents/skills/skill-creator Skill

    1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Project bug hunter skill

    wildanfadh/project-bug-hunter-skill Skill

    1★

    Use this skill whenever the user asks to find bugs, audit a project, review code for defects, scan the currently opened directory, investigate hidden errors, prepare a project before deployment, or check why a project might fail. This skill is for broad bug-hunting across the current working directory and should trigger on phrases like "cari bug di project ini", "cek project ini", "audit bug", "review kode", "temukan error tersembunyi", "scan direktori sekarang", "check this repo for bugs", or similar requests even if the user does not specify a language/framework. It produces an evidence-based bug report first and must not modify files unless the user explicitly asks to fix them.

  • Cli as harness

    jesse-black/skills/skills/cli-as-harness Skill

    1★ repo

    Author CLI surfaces as agent-facing documentation, especially `--help` and actionable error messages. Use with any language or parser design when adding or changing a CLI interface, improving help text or validation errors, moving command reference out of AGENTS.md / CLAUDE.md / a README / a skill and into CLI surfaces, or making errors suggest the corrected command line or tool call.

  • Capture competitor promotions

    ljh1097912305-wq/competitor-promo-agent-kit/skills/capture-competitor-promotions Skill

    1★ repo

    Capture current promotional actions from competitor official websites, collect evidence screenshots, and create an Excel comparison table with screenshots embedded in each brand row. Use for competitor promotion audits, official-site campaign monitoring, current sale checks, 竞品官网促销截图、官网活动对比、Prime Day 或节日大促监测, and evidence-backed promotion spreadsheets.

  • Domain learn

    shangjunyang1986/ai-learning-skills/skills/domain-learn Skill

    1★ repo

    Research an open topic / field across the web and turn it into an offline, visual, beginner-to-hands-on learning page — a single self-contained HTML file with a left table of contents, a learning roadmap, sourced explanations, the field's real images and videos downloaded locally, and (when the topic admits it) an interactive in-browser demo that teaches the core intuition. Use this whenever the user wants to LEARN, STUDY, RESEARCH, "get into", or "做个从入门到实践的教程" for a TOPIC or FIELD that is NOT a single GitHub repo — e.g. "我想学习 3DGS / 帮我研究下扩散模型 / 给我做个 RAG 从入门到实践的 学习教程 / I want to get up to speed on reinforcement learning / explain CRDTs end to end". Triggers on a topic name + intent to learn/understand it, even without the words "website" or "HTML". Distinguish from siblings: a GitHub URL → use github-project-learn; a specific book/PDF → use textbook-learn; a bare topic/field → THIS skill. Not for: answering a quick factual question (just answer it), or building generic web apps.

  • Taskforge

    Heedful-ai/taskforge/skills/taskforge Skill

    1★ repo

    Build a bounded, self-contained candidate coding take-home from one of the user's real GitHub pull requests, plus a grading guide. Use this whenever the user wants to create, prepare, or generate an interview / take-home / candidate coding task, hiring task, or evaluation task from their repo or a PR. Collaborative and fail-closed: it scores the PR's suitability, carves a standalone runnable project, and turns it into a PROBLEM the candidate must design and solve (problem-first, not a spec to transcribe), verified to run offline, and packages a task-bundle.zip.

  • Liaowang skill

    DENGYUFAN0/liaowang-skill Skill

    1★

    触发:当需要判断方向、预测趋势、评估一个事物的前途,或为未来变化提前布局时调用;常见信号包括 方向选择、要不要入场/退出、X 有没有前途、未来会怎样、现在该为将来准备什么。 English: Trigger when the task is to judge where things are heading, assess the future of a project, technology, or market, or position early for coming change. Use this skill to deduce trends from fundamental factors, define stage-transition signals, and place small bets before the trend is obvious.

  • Agentskillshub cli

    zhuyansen/agentskillshub-cli Skill

    1★

    Use when the user wants to find, evaluate, audit, or install an open-source AI agent skill or MCP server — e.g. "find an MCP server for Postgres", "is this skill safe to install", "what should I use to scrape a website". Searches a quality-scored, security-graded catalog of ~20K skills locally (cached index, zero backend load) and returns each result's security grade, quality score, and install commands so you can check trust BEFORE installing.

  • Design auto

    dlaumets/agent-design-pack/design-auto Skill

    1★ repo

    Designs, builds, audits, polishes, prototypes, and reviews frontend interfaces through one integrated workflow. Use for UI/UX work, visual design, accessibility, responsive behavior, design systems, animation, motion audits, gesture-driven interfaces, and final product polish. Add --deep only for exhaustive phase-gated work.

  • Loop it

    fhajjej-ship-it/loop-it/skills/loop-it Skill

    1★ repo

    Choose, compile, launch, or run bounded AI-agent goals with explicit deliverables, proof rubrics, verifier gates, iteration caps, stop conditions, and approval boundaries. Includes a categorized Loop goals library for product, design, research, content, data, and operations plus advanced engineering loops for Codex, Claude Code, Cursor, and other SKILL.md-compatible agents. Use when the user says "loop it", asks for a loop goal, asks what should be looped next, or wants iterative improvement with proof. Do not use for simple one-shot edits unless the user asks for a repeatable loop.

  • Html as cli panel skill

    rob163/html-as-cli-panel-skill Skill

    1★

    Agent skill for creating offline HTML command panels from project CLI workflows.

  • Improve code comments

    wufei-png/improve-code-comments/improve-code-comments Skill

    no license1★ repo

    Use when auditing, adding, removing, or improving code comments, docstrings, JSDoc/TSDoc, TODO/FIXME/HACK notes, public API comments, inline rationale, stale/comment rot, redundant comments, documentation gaps, or "why not what" comment quality.

  • Openspec apply change

    ayrtonvwf/skills/.claude/skills/openspec-apply-change Skill

    1★ repo

    Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

  • Criar post

    thiagoxikota/ai-collective-content-lab/.claude/skills/criar-post Skill

    1★ repo

    Monta um post do Instagram (imagem de fundo + overlay editorial na identidade visual do The AI Collective) e renderiza um PNG 1080x1350 em out/. Use quando a pessoa disser "cria um post", "monta um post", "faz um post pro instagram", "arte do post", "post de divulgacao", "post de anuncio do evento", "capa do carrossel", "make a post", "create an instagram post", "post cover".

  • Labview to python industrial

    k-telux/Labview2Python/skills/labview-to-python-industrial Skill

    1★ repo

    Industrial workflow for converting, auditing, optimizing, or packaging LabVIEW measurement VIs as Python applications. Use for LabVIEW to Python, LabVIEW-to-Python, LabVIEW转Python, VI migration, pump-probe or laboratory control software, PyQt/PySide industrial UI, hardware driver and SDK migration, simulator/data parity, performance regressions, screenshot UI review, supervisory gatekeeping, or Windows EXE delivery.

  • Bear hours

    loursCreatif/ours-stack/bear-hours Skill

    1★ repo

    School of the Bear topic framing — five forcing questions before deep learning. Defines scope, wedge (via entry angle), and success criteria; source material defaults to TBD (or inserted from the opening message). Asks consent before optional local scan; never reads source material during framing. Use when the user starts a new study, asks what to learn, wants to frame a topic, or says "bear hours", "cadrer mon apprentissage", "what should I study". Outputs studies/<slug>/brief.md.

  • Ai coding review

    batur/ts-baseline-docs/.agents/skills/ai-coding-review Skill

    1★ repo

    Meta skill for AI coding agents and reviewers in TypeScript software projects. Use when planning, implementing, refactoring, reviewing, or approving AI-generated code; when deciding which project skill to apply; when enforcing architecture, API, security, testing, documentation, CI/CD, validation, error handling, persistence, auth, logging, and OpenAPI standards together.

  • Youtube traffic grabber

    MrBridgeHQ/youtube-traffic-grabber-claude/skills/youtube-traffic-grabber Skill

    1★ repo

    Use when planning authentic YouTube marketing to drive referral traffic to your own assets - launching or growing a channel, video/YouTube SEO (titles, descriptions, tags, thumbnails), faceless content formats and scripts, Shorts, CTAs/end-screens/cards/pinned comments, value-first external engagement, or measuring clicks-to-site. Triggers on "YouTube marketing", "drive traffic from YouTube", "grow/launch a YouTube channel", "YouTube/video SEO", "title/description/tag/thumbnail", "Shorts strategy", "end screens / cards / CTAs", "promote my site/product/tool on YouTube", EN or FR markets. Earned engagement only - never buying/botting views/subs/likes/comments or sub4sub. Distinct from off-page link building, prose humanization, on-page SEO, and bulk data pulls.

  • Daily news digest

    Komagon/hermes-production-patterns/examples/daily-news-digest Skill

    1★ repo

    定时抓取 RSS 源,用 LLM 生成中文新闻摘要,遵循 STATE.md 状态管理和 Maker/Checker 验证

  • Arming thought

    DENGYUFAN0/qiushi-skill/skills/arming-thought Skill

    no license1★ repo

    触发:在每次新的顶层对话开始时自动调用,用于建立“实事求是”的总原则,并在明确适用时为后续任务选择下游 skill;如果你是被派遣执行单一具体任务的子 agent,则跳过此 skill。 English: Trigger at the start of each new top-level conversation to establish the core methodology and select downstream skills only when clearly useful. Skip this skill when you are a delegated sub-agent handling a narrow, concrete task.

  • Android project standard

    VoldemortGin/AI-Coding-Skill-Bible/android-project-standard Skill

    1★ repo

    Enforce a strict, model-agnostic, AI-navigable Kotlin/Android project standard: the Kotlin compiler's null-safety + sealed/`when` exhaustiveness as the static guarantee, plus `allWarningsAsErrors` + library-module `explicitApi()` + a detekt static-analysis gate as a one-command zero-warning gate, the escape hatches (`!!` non-null assertion / unchecked `as` / `lateinit` abuse / platform-type leaks / `GlobalScope`) shut via detekt-as-error, kotlinx.serialization + `@JvmInline value class` newtypes at boundaries (parse don't validate), a Gradle multi-module module-per-domain structure, a zero-SDK zero-framework `:domain` module behind provider interface seams with a default `MockProvider`, Hilt composition-root injection in `:app`, a version catalog pinning every version, an ktlint + detekt double lint gate, a CLAUDE.md in every module, and scaffold/conformance scripts. Use whenever starting or scaffolding a Kotlin or Android project; setting up Gradle / settings.gradle.kts / libs.versions.toml / detekt / ktlint / CI; deciding module structure; adding an LLM / embedding / vector-store dependency; wiring providers or adapters with Hilt; or checking that an existing Android project conforms. Apply it even when the user only says "start an Android project", "set up the structure", "add an LLM", or "wire up CI" without naming the standard. This skill governs the Kotlin host's internals; it is complementary to polyglot-core-standard, which governs the cross-language seam (generated UniFFI/JNI bindings).

  • Kano model strategist

    monikazapisek/design-engineering-playbook/.cursor/skills/kano-model-strategist Skill

    1★ repo

    Classify product features into Kano categories. Cut waste. Build MDP over MVP. You have 30 features and 6 weeks. Sort them into Kano's six categories (Must-be, Performance, Attractive, Indifferent, Reverse, Questionable) so you ship the ones that earn their place and cut the rest.

  • World cup digest

    RogerioSobrinho/world-cup-digest-skill/skills/world-cup-digest Skill

    1★ repo

    Use when the user wants FIFA World Cup match summaries, daily recaps, weekly digests, group context, player/team performance takeaways, or "what happened today" tournament briefings. Runs a bundled research script to fetch match data from configured football providers, then guides the agent to verify and synthesize sourced recaps without inventing statistics.

  • Connect domain

    vineetu/simple-host/simple-host-website/skills/connect-domain Skill

    1★ repo

    Connect a user's own custom domain (subdomain e.g. recipes.brand.com via CNAME, or apex e.g. brand.com via A record) to a site already deployed on simple-host. Use when a user wants their site served from their own domain with automatic HTTPS, or wants a private/password-protected site (privacy is offered only on a connected domain). Drives the bind → DNS → verify → live flow; the agent does the API work and relays the one DNS record the human must add at their registrar.

  • Goal task prompt

    zitao4588-create/goal-task-prompt/skill/goal-task-prompt Skill

    1★ repo

    Use this skill when the user wants to turn a rough idea, project ask, debugging request, or large task into a concise, copy-ready Codex /goal prompt. Also use it for Loop Cards, delegation briefs, multi-agent orchestration, and prompt or skill evaluation when the user explicitly needs those advanced formats.

  • Yggdrasil

    voluminor/skill-yggdrasil/skills/yggdrasil Skill

    1★ repo

    Use when building, reviewing, or debugging Go applications that embed Ratatoskr for Yggdrasil TCP, UDP, HTTP, SOCKS5, forwarding, peers, NodeInfo, sigils, topology diagnostics, or load handling.

  • Repo beautify

    LaughingisLaughing/repo-beautify Skill

    1★

    Use when the user asks to beautify, redesign, polish, or professionalize a GitHub repo storefront/README; compare README styles; improve repo metadata, topics, social preview, or package manifest; add a Chinese edition of the README; audit a repo for secrets before open-sourcing; or says README 美化, 美化仓库, 仓库门面, repo 门面, 项目主页包装, 徽章, badges, social card, star history, 中文 README, 中文介绍页, 双语 README, bilingual README, README.zh-CN, 开源前检查, 敏感信息扫描, 私钥检查, secrets scan, publish audit. Covers README visual redesign (hero banner, badges, mermaid diagrams, collapsible docs), GitHub description/topics, manifest enrichment, parity-checked Chinese editions, and publish-safety audits, all fact-verified. Do NOT use for GitHub profile READMEs, full API docs, CONTRIBUTING generation, or GitHub Pages sites.

  • Mac setup bundle builder

    jakowicz/skills/skills/mac-setup-bundle-builder Skill

    no license1★ repo

    Create personalized AI-agent-driven Mac rebuild bundles from a user's current Mac. Use when asked to inventory a Mac and generate a tailored setup/rebuild bundle covering whatever is actually installed: apps, package managers, runtime/version managers, dotfiles, system settings, app settings, private migration notes, containers, virtual machines, local services, AI tools, repos, live progress logs, verification checks, and final HTML reports for recreating that user's Mac setup on a new machine.

  • Memory card studio

    wuA-zs/memory-card-studio/memory-card-studio Skill

    1★ repo

    Use when the user asks to create or update persistent local memory-card projects, generate flashcards or spaced-repetition card libraries from files, URLs, web pages, or other readable sources, create a zero-install card-review frontend, start today's due-card review, or study an existing local card library in conversation.

  • Api docs writer

    Da-loong/agent-skill-os/skills/api-docs-writer Skill

    1★ repo

    A reusable Agent Skill OS skill that helps AI coding agents complete api docs writer work with a reliable workflow.

  • Arc to zen migration

    shub-rajput/arc-to-zen-migration Skill

    1★

    Use when migrating Arc browser spaces/workspaces into Zen Browser, or bulk-creating Zen workspaces, folders, essentials, or pinned tabs by editing the session store. Covers reading/writing Zen's mozlz4 session file and its folder/group/space schema.

  • Creative frontend

    talesworld/skill-cauldron/examples/creative-frontend Skill

    1★ repo

    Use this when the task involves creating visually strong, premium frontend interfaces (landing pages, websites, apps, prototypes, demos, or game UI) that require both thoughtful creative exploration and disciplined design execution. This skill combines structured需求探索 with award-level frontend craftsmanship.

  • Prompt engineering instructions

    bybaochaule/prompt-engineering-instructions Skill

    1★

    Use this skill to create, revise, evaluate, or standardize prompts and agent instructions using role, goal, context, examples, constraints, and reliability tests. Trigger when the user asks for prompt engineering, system or developer instructions, few-shot examples, prompt templates, agent behavior guidance, or prompt refinement. Do not use it for policy bypassing, hidden instruction extraction, unsafe automation, or unrelated copywriting.

  • Github auto backup

    OlivierHijlk1/github-auto-backup Skill

    1★

    Use whenever creating a new coding project or working in any git-backed project. Handles all Git/GitHub management so the user always has an off-machine backup. Interviews the user before creating a new repo, then autonomously commits, pushes, pulls, branches and syncs with conventional commit messages, pausing only for risky or irreversible actions. Triggers on "new project", "start a project", "init repo", or any task that creates or edits files in a project worth keeping.

  • Office tea bar overtime sku

    HXZ09845/ecommerce-sku-skill-builder/case-studies/real-run-a6-office-tea-bar/office-tea-bar-overtime-sku Skill

    1★ repo

    Use this anonymized ecommerce SKU Skill when turning an office overtime tea-bar appliance brief, selling points, and reference assets into Seedance-style shot contracts, prompt plans, take reviews, and repair rules.

  • Pg extension lab

    ysys143/pg-extension-lab/skills/pg-extension-lab Skill

    1★ repo

    Develop, test, benchmark, and operate PostgreSQL extensions with reusable harnesses and reference protocols. Use for C/PGXS or Rust/pgrx extension work, planner hooks, CustomScan or index AM design, pg_regress/pg_isolation_regress TDD, filtered ANN/vector benchmarks, matched-recall and pages-per-query analysis, bounded parameter-space exploration, Pareto curves, hypothesis/evidence/report management, accelerator-vs-CPU crossover, resource Pareto tuning, Shape B microservice extensions, Shape C sidecar daemons, service-boundary contracts, async outbox workers, and SECURITY hardening. Balances docs, code evidence, and execution results. Includes copy-ready test, benchmark, contract, and ops assets. Not for projects without a PostgreSQL extension layer.

  • Broken skill

    Hayatelin/skillhub/examples/skills/broken-skill Skill

    1★ repo

    The package manager for AI agent skills - lint, search, scaffold and install SKILL.md skill packs across Claude Code, Cursor, Codex and Gemini. Zero dependencies.

  • Senderkit email deliverability

    senderkit/senderkit-skills/skills/senderkit-email-deliverability Skill

    1★ repo

    Diagnose and fix email deliverability and domain authentication so transactional email lands in the inbox instead of spam. Use whenever emails go to spam or are not arriving, or a user wants to set up, fix, or verify SPF, DKIM, DMARC, MX, or DMARC alignment, authenticate a sending domain, improve sender reputation, reduce bounces, or check why mail is rejected or filtered. Works whether mail is sent directly via SenderKit or routed through a provider (Resend, SendGrid, Postmark, Mailgun, SES, SMTP). Diagnoses current DNS with standard tools (dig/nslookup), generates the exact records to add, then verifies them. For wiring sends into code use senderkit-integration; for live test sends use senderkit-mcp-messaging-operations.

  • Architecture blueprint

    yiyaw-lab/agent-armor/architecture-blueprint Skill

    1★ repo

    Maintains an Architecture Blueprint so builders track what agents built across sessions. In Continuum repos, defer to X-3 (`.continuum/blueprint/`, BlueprintPanel) — do not duplicate. In other repos, use markdown `ARCHITECTURE.md` + append-only change feed. Invoke explicitly when the user mentions schema drift, lost track of architecture, what agents built, mental model sync, or architectureImpact.

  • Auditing skills

    AdrianParedez/capability-fabric/skills/auditing-skills Skill

    1★ repo

    Scores and improves an existing Agent Skill against a spec + quality rubric, then proposes or applies concrete refactors (split monoliths, sharpen descriptions, fix portability). Use to review, grade, lint, or improve a skill, or to maintain a skill library at scale. Justifies each finding with verifying-reasoning and routes fixes back to authoring-skills.

  • Hermes skill ozon product picker

    web3blind/hermes-skill-ozon-product-picker Skill

    no license1★

    Pick the best Ozon product for a user query or Ozon URL via the Apify actor zen-studio/ozon-scraper-pro. Use when the request is about finding, comparing, or choosing products on Ozon/Ozon.ru/Озон/Озоне, especially Russian phrasing like «найди в Ozon товар», «найди в Озоне», «поищи на Озоне», «подбери товар в Озоне», «подбери на Ozon», «сравни товары на Ozon», «что лучше взять на Озоне», «посмотри на Ozon и выбери лучший вариант». Search Ozon, compare multiple product candidates, weigh price, rating, review count, seller quality, and practical trust signals, then return one best option plus 1-2 backups with a short rationale in Russian.

  • Skillforge repo to skill

    xiaokillua/skillforge/skills/skillforge-repo-to-skill Skill

    1★ repo

    Use this skill when the task is to turn a GitHub repository or local codebase into a portable agent skill for Claude, Codex, GitHub Copilot, OpenClaw, Hermes, or other Agent Skills compatible runtimes.

  • Quant oral to code

    2033121/quant-oral-to-code/skills/quant-oral-to-code Skill

    1★ repo

    把口述或抽象策略想法转换成可回测代码骨架、回测入口和结果报告,并在生成前做 DSL 提炼与风险护栏审查。Invoke when 用户希望把量化思路直接写成策略代码。