The catalog
608,119 rows, by stacks then stars
gtm-shaan/claude-skill-builder/create-skill Skill
no license0★ repoHow to create Claude Code skill files. Use this skill when the user asks to convert learnings, playbooks, frameworks, or knowledge into a skill file, or when they say "make this a skill", "store this as a skill", "create a skill for this", or "let's build this as a skill".
Architecture decision framework
agustinusnathaniel/skills/skills/software-engineering/architecture-decision-framework Skill
no license0★ repoMake architecture decisions using decision matrices and iterative refinement. Use when comparing implementation approaches, evaluating trade-offs, selecting technology, or facing multiple viable paths. Prioritizes business context over technical purity — clarifies the problem before deciding, presents options with trade-offs, documents decisions as lightweight ADRs.
cbrunnkvist/agent-skills/skills/katana-web-crawl Skill
0★ repoAuthorized ProjectDiscovery Katana crawling for owned apps, approved pentest or bug-bounty targets, and CTF labs. Use to inventory URLs, endpoints, JavaScript routes, forms, XHR, or scoped headless routes; enforce scope, limits, secret-safe authentication, and hostile-content handling.
SoftwareOneHN/dev-kit Skill
0★Full-stack Development Kit — structured workflows for brainstorming, planning, implementation, debugging, testing, and code review. Use when the user mentions: plan, implement, code, cook, fix, debug, test, review, scout, brainstorm, feature, bug, refactor, architecture, pipeline, CI, performance, root cause, or asks to build/ship/deploy features.
tjrice42/design-judgment-skills/build-journal Skill
no license0★ repoAutomatically maintain a build journal during any prototyping, design, or development session — capturing attempts, failures, pivots, verbatim prompts, decisions, and visual state changes as they happen, so the work documents itself into future case-study material. Use this skill at the start of EVERY session where the user is building a prototype, portfolio piece, app, or design artifact, even if they don't mention journaling — and especially if they say "start a journal," "document this build," "track what we try," or reference their build journal. Also use it to retroactively convert an existing manual journal or chat transcript into the structured format.
NovateStudioGit/novate-studio-skills/advisors/hormozi Skill
0★ repoChannel Alex Hormozi as a live advisor — offers, pricing, lead generation, sales, scaling, and mindset. Draws from $100M Offers, $100M Leads, $100M Money Models, and the full body of his teachings.
newtonapple/remote-machine-access Skill
0★Manage and access remote machines via SSH or Tailscale. Use when the user references a remote machine, node, server, or host — e.g., "run this on the remote box", "check GPU usage on the node", "deploy to the cluster", "access the remote node", "SSH into the machine". Triggers on any request involving remote execution, remote commands, remote file operations, or cluster/node management.
muqian2026-rgb/qian-public/book-learn-distill Skill
no license0★ repo读书蒸馏:学习方向 → 权威选书 → 知识骨架 → PDF 校验 → 人机思辨 → 双交付物(Domain Skill + 知识图谱 HTML)。口令:「学一下」「读书蒸馏」「/book-learn」。续跑:「补了 PDF」「继续 learn/<slug>」。
uaandesign/muninn-skill-leveler/skills/muninn Skill
0★ repoMuninn(穆宁)——Skill练级系统:你的Skill经常该触发没触发、或者干完总要你返工?Muninn翻你的 历史会话记录,找出每个Skill实际掉链子的地方,帮你修好,并把每次翻车变成测试用例,保证同样的 问题不再犯第二次。 名字来自奥丁的记忆渡鸦:每天清晨飞遍世界,黄昏带回真实发生过的事。 Muninn对你的Skill做同样的事:飞进本地会话历史做"会话考古",带回每个Skill在实战中的真实表现 (漏触发、误触发、被用户当场纠正、每次都要重复补充的指令),把这些证据折算成经验值, 给Skill定级(Lv1雏鸦→Lv5神使),并通过"试炼"让它逐级升上去。每一次实战失败都会被铸成一道 回归考题,永久留在该Skill的考题集里——升级只能靠通过考题,掉链子就会掉级。 产出三样东西:一份持续维护的成长档案(saga)、一张可截图的等级符文石(runestone)、 一套随Skill资产沉淀的回归考题(evals)。 当用户想给自己的Skill练级、升级、定级、体检、看实战表现、建立评测集、或想知道 "我这一堆Skill哪个最值得先改"时使用。 触发词包括但不限于:用muninn看看、给这个skill练级、skill lvup、升级我的skill、 我的skill实战表现怎么样、给skill定个级、skill考古、挖一下这个skill的使用记录、 给skill建评测集、盘点我的skill库、哪个skill最该修、放飞渡鸦。 不要用于:从零创建新Skill(用skill-creator)、普通代码review(用code-review)、 一次性美化README文案、与Skill资产无关的提示语改写。
jae-labs/skills/skills/api-and-interface-design Skill
0★ repoGuides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
wangnan0916/cursor-like-debug-mode/skills/debug-mode Skill
0★ repoDiagnose one reproducible runtime bug with temporary probes, NDJSON evidence, manual checkpoints, and mechanical cleanup.
xylvvv/agent-skills/skills/engineering-journal Skill
no license0★ repoUse when work in a Git repository needs a persistent engineering dossier, work item, investigation record, quick handoff, topic ledger, analysis report, or reusable evidence across projects or sessions.
hakityc/tapd-skill/tapd Skill
no license0★ repoTAPD 与 Flow 研发工作流总入口。用户提到 TAPD、Story、Task、Bug、产品 Git Repo、发布需求、同步产品文档、产品评审、规格版本、.flow/spec.json、需求 intake、原型读取、编码前审核、拆任务、实现、测试、收尾、日报、今日待办、团队盘点、工时、排期、评论、分支绑定或 tapd-context 时必须使用。产品规格请求先读取 Flow Manifest;工作项请求解析本轮输入或恢复分支绑定;日报、今日待办和团队盘点只读汇总 Provider。
mabyko/AgentSkills/skills/docs-sync Skill
0★ repoUse when documentation and implementation may be out of sync, docs may define intended behavior, code changes need docs updates, or the user asks for 문서 체크, 문서 갱신, 문서 동기화, or 문서 기준.
ahmad2point0/feature-base-folder-structure/skills/feature-base-folder-structure Skill
0★ repoSets up a feature-based (modular) folder architecture for Next.js (App Router) and React Native Expo (Expo Router) TypeScript apps — self-contained feature modules, a thin routing layer, a shared global layer, plus naming conventions, barrel exports, and path aliases. Use when starting, scaffolding, or restructuring such an app, adding a feature, or deciding where a component, hook, service, store, type, or screen/page belongs — even when the user doesn't say "architecture" or "folder structure" and only asks where to put a file or how to organize the project. Also use when route files hold business logic, features cross-import, or imports use deep ../../ relative paths. Not for non-React/TypeScript stacks; not a styling or state-management guide.
holzerjm/SkillsDemo/Claude/audience-analyst Skill
0★ repoAnalyze an audience list and generate a personalized event brief with insights, icebreakers, and networking recommendations. Use when given a list of attendees, a CSV of participants, or when asked to analyze an audience.
Throughproof/throughproof/skills/compliant-logging Skill
0★ repoUse when writing or modifying code that performs a SENSITIVE ACTION — authentication or authorization changes, creating/updating/deleting records that hold personal, financial, or health data, permission/role changes, data exports, or admin operations. Ensures every sensitive action emits a structured, tamper-evident AUDIT EVENT (control key `log.audit`) and that secrets and PII never leak into logs (control key `hygiene.no-secrets`). The neutral control keys map to SOC 2, ISO 27001, PCI-DSS v4, and HIPAA at once via the Throughproof crosswalk (compliance/control-keys.yaml). Applies in any stack; do not invent a new logging library — use the project's logger.
justinneuman-coder/unicornkick-skills/unicornkick-dreamer Skill
0★ repoThe Unicorn Kick mindset coach. Turns the agent into a dream coach who helps people name bigger ambitions, face their fears, and take the next honest move within 24 hours. Use this whenever someone says they feel stuck, bored, restless, or smaller than they want to be; wants to set goals or New Year's resolutions; says "I want more but I don't know what"; mentions a dream they keep postponing (the novel, the race, the business, the instrument); asks for motivation, accountability, or help getting started; or asks the agent to help them "dream bigger." Trigger even when they don't use the word "goal." Do NOT use for executing the dream itself... this coach plans, provokes, and celebrates, but never does the user's work.
klittle32/handoff-skill Skill
0★Goal-directed session handoff for a fresh agent thread (Amp-style extraction, not lossy compaction). Use when the user runs /handoff, asks to hand off context, start a new session with a focused goal, split work to another thread, or preserve continuity before ending a session. Argument is the goal for the next session — e.g. "/handoff implement phase one of the plan" or "/handoff debug the checkout 400 error".
gabriel-f-santos/gen-skill/skill-gen Skill
0★ repoGenerate AND iteratively improve production-grade Agent Skills through a guided interview. Use whenever the user wants to create, scaffold, author, or design a new skill or set of skills — "create a skill", "gera uma skill", "skill para X", "turn this workflow into a skill" — OR to improve/fix an existing one ("this skill mis-fired", "it didn't trigger", "improve this skill", "optimize the trigger"). Interviews to decide target runtimes (Claude Code, Codex, opencode), single vs multiple skills, execution shape, and tools, then writes a portable SKILL.md plus references/scripts and per-platform sidecars (Codex openai.yaml), tunes the description, and validates. Do not use to run, install, or security-review an existing skill (that's skill-scanner), or to tweak non-skill prose — only to author or improve a skill.
The same file is in 1 other repository
SwiftyJourney/swift-language-expert-skill Skill
0★Use this skill for non-obvious Swift LANGUAGE and standard-library techniques -- features that make code clearer, safer, or faster but that developers routinely miss. Covers pattern matching (if/guard-case, switch over tuples); functions, closures, and key paths (variadics, autoclosures, rethrows); value semantics and custom types (copy-on-write, ~Copyable, callAsFunction, recursive enums, property wrappers); protocols and generics (associated types, opaque some vs existential any, phantom types); collections (lazy, RangeSet, InlineArray, sorting); strings and Unicode (grapheme-correct iteration, custom interpolation); concurrency and errors (async/await, task groups, AsyncStream, typed throws); and debugging and code organization (assertions, dump, enum namespaces, directives). Trigger for "how do I do X in Swift" and idiomatic refactors. Do NOT use for SwiftUI (swiftui-expert), app architecture or actor isolation in a layered app (ios-architecture-expert), or Swift Testing syntax (swift-testing-expert).
benmilne-com/agents/skills/content-search Skill
no license0★ repoFull-text search across all published posts on benmilne.com.
MOZARTINOS/claude-kahoot-skill Skill
0★Design high-quality Kahoot quizzes and, when the user explicitly asks for it, enter them into the Kahoot web editor with browser automation. Use when the user asks to create Kahoot content, classroom or training trivia, an interactive multiple-choice quiz, or to put existing questions into Kahoot. Default to producing a reviewable quiz document; only modify the user's Kahoot account after explicit confirmation.
bcmyguest/baton/skills/handoff Skill
no license0★ repoWrite a concise handoff summary of the current troubleshooting/debugging activity so the next agent (or a future session) can continue without re-deriving anything. Use whenever the user invokes /handoff, says "summarize where we are", "write this up for the next agent/session", "capture the current state before we stop", or when a long troubleshooting session is winding down with the problem unsolved. Also use before context runs out on a gnarly multi-step investigation.
ojesusmp/voz Skill
0★Use whenever writing or editing prose a person will read (docs, READMEs, emails, landing-page copy, chat messages, reports, social posts, UI text, commit messages) and in normal conversation. Makes writing read as human by killing AI-writing tells (the word list like "delve/tapestry/underscore/boasts", the rule-of-three, "not X but Y" negative parallelism, em-dash and bold-bullet overkill, forced significance), and lets you switch voice register to fit the audience: empathetic-neutral by default, or salesman, corporate, lawyer, journalist, marketing, technical, teacher, or motivational on request.
Tar-ive/agent-skills/skills/nextjs-figma-conversion Skill
0★ repoConverts a running Next.js / React + Tailwind web app into a faithful, editable Figma design file — design tokens as Figma variables, shared UI as components, and every route as a pixel-matched screen frame. Use when the user wants to export, convert, recreate, mirror, or "preserve" a Next.js / React app's design in Figma, or turn code/screens into a Figma design file.
itoldis/docs-first-skill Skill
no license0★Consult official documentation BEFORE answering any question that involves a specific third-party library, framework, package, SDK, CLI tool, API, or program. Use this whenever the user asks how to use, configure, install, or call something (e.g. "how do I do X in vLLM", "what's the flag for Y", "does library Z support W", version/compatibility questions, error messages from a tool, API signatures, config schemas). Trigger this EVEN WHEN you feel confident you know the answer — training knowledge goes stale for fast-moving software, and confidence is exactly the failure mode this skill exists to catch. Search the official site and the official repository first, then answer grounded in what you found, with links and the version you relied on. Skip only for purely conceptual questions ("what is a hash map") that name no specific tool.
marketingskills/open-source-growth/skills/ecosystem-inclusion-operator Skill
0★ repoFind relevant open-source ecosystems, directories, awesome lists, templates, examples, and integration repos where a project genuinely belongs. Score targets, prepare useful PRs, open issues or PRs, and maintain a durable progress log so the workflow can continue through repeated /loop runs. Use when the user wants to grow an open-source repo through ethical ecosystem inclusion.
tomhuaijbig/aaa-bundler-skill/skills/aa-bundler-skill Skill
0★ repo自动整理已安装的 Codex 技能,生成更容易调用的 aa-* 技能包入口,运行前会询问你是否需要汉化。仅用于安装技能后打包、整理历史技能、翻译说明或维护技能列表。
xiehan/medium-to-ssg-skill/.agents/skills/medium-publication-export Skill
0★ repoUse this skill to export every post from a multi-author Medium publication into a ZIP of HTML files that matches Medium's personal "Download your information" export, so it can feed the medium-to-ssg skill. Triggers whenever a user wants to migrate or archive a whole Medium publication that they cannot export from Settings — for example a company or team engineering blog where many people published from their own personal accounts. Also use this skill when a user says Medium won't let them export a publication, asks to scrape or crawl all posts from a Medium publication or custom domain, wants to back up a Medium publication, or needs to produce a Medium-export-compatible ZIP for a multi-author blog before running medium-to-ssg.
ifylab/skillmeld/skills/skillmeld Skill
0★ repoDiscovers existing community skills for a described use case and merges the best two or three into one coherent, deduplicated, security-scanned skill set tailored to the user's project. Use when someone wants to assemble or compose skills for a workflow, combine existing skills instead of writing one from scratch, or build a tailored skillset from community sources. Grounds in the user's repo, scans every candidate before use, and shows provenance plus a review before installing.
AGilbertDev/agilbertdev-recipes/skills/my-backend-conventions Skill
no license0★ repoMy reusable coding-agent conventions and a curated skill set, pulled into any project like a versioned package.
shihabshahrier/claude-antigravity-orchestrator/skills/antigravity-delegate Skill
0★ repoOffload work to the local Antigravity CLI (agy) — search, downloads, scanning, validation, AND first-draft code/UI generation — so Claude stays the orchestrator and burns far fewer tokens. agy runs on the user's Google/Antigravity quota, so anything it produces is tokens Claude didn't spend. Invoke /antigravity-delegate "<task>" or apply automatically. Returns only agy's distilled answer.
w3rdist-creator/agent-intelligence-economy/skills/action-packet-executor Skill
0★ repoTurn a report recommendation list into bounded verified actions instead of another plan.
eyupcanbodur/agent-knowledge-hub/skills/hub-doctor Skill
0★ repoDiagnose and repair the knowledge-hub installation itself. Use when hub retrieval returns wrong or missing notes, a hub skill seems absent or stale, store-to-hub writes land in the wrong place, results mention an unexpected hub name, or the user says "hub is broken", "wrong hub", "hub-doctor", "/hub-doctor". Runs a deterministic diagnosis first (env vars, symlinks, matcher resolution, machinery), then fixes safe issues on confirmation or proposes exact commands for the rest.
web3blind/hermes-skill-wallet Skill
no license0★Controlled disposable wallet helper for x402 and small payment flows with strict private-key redaction. Use when the user needs to load a local wallet secret, verify wallet-tool readiness, or run a dry-run payment helper without exposing credentials.
qa-veritas/skillpack/skills/analyze_cluster_health Skill
0★ repoTurn a cluster health snapshot into a verdict, degraded components, and the next checks worth running. Use for health questions and pre/post-change checks.
dadamsuk/browserhost/.claude/skills/browser-via-browserhost Skill
0★ repoDrive a real, visible Chrome browser running on the user's desktop (Windows/macOS) from this remote/headless machine, over the Chrome DevTools Protocol via BrowserHost + agent-browser. Use this whenever you need to load a live web page from a real browser and your own built-in fetch/search isn't enough — e.g. pages that need JavaScript, a real (residential/office) IP, a logged-in session, or human handoff for login/CAPTCHA/2FA — and whenever you need to test a web app you are building by clicking through it in a real browser (open it, snapshot the DOM, fill forms, take screenshots, assert behaviour). Trigger on requests like "open this URL in a real browser", "scrape this site", "log into X and grab Y", "test my app / dev server in a browser", "click through the signup flow", "screenshot this page", or any web automation that needs an actual browser rather than an HTTP fetch. Prefer this over plain WebFetch when the page is JS-rendered, gated behind auth, or IP-sensitive.
Mkhira/flutter-clean-architecture/skills/flutter-clean-architecture Skill
0★ repoUse this skill when creating a new Flutter project, implementing Flutter or Dart features, writing code in an existing Flutter project, refactoring Flutter/Dart code, or reviewing Flutter code. Trigger whenever the user asks to create a Flutter project/app by name, or when the current workspace is a Flutter project and the task involves implementation, coding, API integration, models, Bloc/Cubit, UI, theming, localization, dependency injection, networking, tests, or code review — even if the user does not explicitly say "clean architecture". For new project creation, ask the user for the directory and project name before running flutter create.
sesamehut/appstore-connect-skill/.claude/skills/app-store-connect Skill
0★ repoOperates Apple App Store Connect through a bundled CLI. Lists apps and App Store versions; reads and updates store metadata and localizations (description, keywords, what's new, promotional text, app name, subtitle, privacy policy); adds new locales; reads customer reviews and posts or replaces developer responses; downloads sales, finance, and analytics reports to disk; uploads, lists, reorders, and deletes App Store screenshots and preview videos; manages TestFlight beta groups, testers, test info, beta review detail and submission, and reads/downloads beta feedback; lists builds, resolves the latest processed build, edits build distribution and notes, and expires builds; runs an App Store submission-readiness preflight, sets review contact/demo detail, configures release timing and the export-compliance flag, reads submission status, and submits, cancels, or releases a version for App Review; verifies credentials against the live App Store Connect API. Use when the user asks about App Store Connect, ASC, app metadata, store listings, localization, customer reviews, review replies, sales or download numbers, finance reports, analytics, TestFlight, beta testers, beta groups, beta feedback, builds, App Store reports, screenshots, preview videos, submitting an app for review, App Review, release timing, export compliance, releasing a version, or checking that App Store Connect API credentials work.
yashpatil582/agent-skills/clinical-note-eval Skill
0★ repoEvaluates whether an LLM's structured extraction of a clinical note (problems, medications, plan) is actually grounded in the note's own text, using a two-pass extract-then-ground design whose grounding score is computed deterministically in code — by re-checking every cited span against the note — so the model cannot inflate it. Use this whenever asked to score, grade, audit, or fact-check an LLM's extraction or summary of a clinical note for hallucination or grounding; to verify that cited supporting spans really appear in the source; to build a faithfulness or grounding eval; or to catch unsupported clinical claims and inference "lures." Triggers on clinical note eval, grounding score, hallucination check, faithfulness, span verification, extract-and-ground, supporting quote, structured extraction grading, code-side scoring. Runs offline in fixture mode with no API key; live scoring works against any OpenAI-compatible endpoint.
Andiedie/skills/skills/ai-native-development/and-claim Skill
no license0★ repoClaim an executable delivery unit without changing its scope.
clankercode/agent-file-chat/skills/simple-agent-comms Skill
no license0★ repoTwo-way streaming comms with a long-running background subagent via a pair of append-only files + a Monitor, when you need its intermediate updates/questions (not just its final report) and inter-agent messaging (c2c / SendMessage-to-coordinator) is unreliable. Use when coordinating with a spawned Agent that runs for a while. The "simple" variant picks a single cache directory and stable script names so the agent never needs to know file paths.
code-peekr/peek-skill Skill
no license0★Use whenever the user wants to understand how a codebase fits together rather than look up a single line — e.g. "how does X work", "understand the architecture", "how is the indexer organized/architected", "how does a request flow from A to B end to end", "where is feature Y implemented", "what depends on this", "trace what happens when a user signs in", or getting oriented in an unfamiliar or large repo before editing. Reads peek's precomputed map of the repo: local `.peek/` summaries when present (instant, free), escalating to peek's hosted research engine (the ask_repo MCP tool) for cross-cutting, cross-repo, or end-to-end questions — instead of reconstructing the structure yourself with grep and read.
JAlex1201/pr-presubmit/.github/skills/pr-presubmit Skill
0★ repoUse this skill to run a structured pre-submit checklist on a change before it goes out for review, helping the author catch everything catchable before a reviewer ever looks. Activate when a user is about to open or push a pull request, is getting ready to submit or merge changes, wants to know whether their PR is ready, asks for a pre-submit or pre-flight check, or describes a change and asks whether anything is missing before requesting review. Do not use this skill for writing or improving a PR title and description (use pr-best-practices for that), reviewing someone else's code (use pr-review for that), or running automated tests or linters directly on behalf of the user.
qwqqwqis666/agent-skill-arena/selecting-best-skill Skill
0★ repoUse when comparing competing Agent Skills, selecting from uploaded skills, discovering GitHub candidates, or deciding which skill best satisfies a concrete task. 也用于同类 Skill 评选与 GitHub 候选筛选。
openjck/agent-skills/skills/create-ics Skill
0★ repoHelp add one or more events to a digital calendar by providing a valid ICS file for the event(s) that are described.
HighBridgeDragon/jp-diet-minutes-skill/jp-diet-minutes Skill
0★ repoSearch and retrieve Japanese National Diet (国会) meeting minutes via the official NDL Kokkai API (no auth required). Covers all Diet sessions since 1947, supports keyword search, speaker lookup, meeting-level retrieval, and date/session/issue filtering. Useful for political research, legislative tracking, speech analysis, and any task involving Japanese parliamentary records. 国会発足(1947 年)以降の日本の国会議事録を NDL 国会会議録検索システム API 経由で検索・取得するスキル。発言・会議・キーワード検索および期間/回次/会派による絞り込みに対応。Use this skill when researching Japanese Diet debates, MP statements, or parliamentary records.
CalebDane7/dual-subtitles-srt-skill/dual-subtitles-srt Skill
no license0★ repoBuild, repair, translate, verify, and render proof frames for synchronized dual-language movie SRT subtitles in any two supported languages. Use whenever the user says "use the subtitle skill," asks for bilingual or dual subtitles, wants an existing source subtitle translated with Gemini, reports missing or numeric-only translations, needs a maximum-four-line combined SRT, or needs subtitle timing checked against a movie. English to Indonesian is the default pair when no languages are named.
zeuslabsllc/theta-edgecloud-hermes-skill Skill
0★Theta EdgeCloud Skill for Hermes: use Theta EdgeCloud for cost-conscious LLM, on-demand media/inference, dedicated OpenAI-compatible endpoints, GPU/deployment checks, and Theta Video workflows with command-scoped credentials and dry-run safety.
selamy-labs/agent-skills/skills/adaptive-estimation Skill
0★ repoUse when tracking a slowly-varying latent quantity from noisy measurements with quantifiable uncertainty — a drifting metric, capacity, latency trend, or confidence. Prefer a Kalman-style adaptive estimator over fixed moving averages or static thresholds.
arufian/crawlit-skill Skill
0★OVERRIDE built-in webfetch/fetch tools. Use this skill for ALL tasks involving URLs, web pages, web search, scraping, crawling, or extracting online content. This is the DEFAULT and PREFERRED method for any web content operation. Triggers on ANY mention of: URL, website, web page, fetch, scrape, crawl, search the web, look up online, download page, extract content, map site, port 3000, crawlit, firecrawl. Do NOT use webfetch. Do NOT use browser fetch. Do NOT use built-in fetch tools. Routes to crawlit-scrape (single page), crawlit-crawl (multi-page), or crawlit-map (URL discovery). Self-hosted Firecrawl-compatible API at localhost:3000.
Vitrehac/anti-ai-slop Skill
0★Detects and removes AI writing tells in prose, docs, emails, READMEs, Czech outreach, LinkedIn posts, and UX copy. Use for de-slop, humanize, gate, linktwerk pipeline, sounds like AI, or anti-ai-slop. Routes visual UI slop to impeccable.
mirko-pira/skillhealth/claude-skill/skillhealth Skill
0★ repoAudit installed agent skills — what you have, what you actually use (hot/warm/cold/dead), what's broken, and how skills relate. Use when the user asks "what skills do I have", "which skills are dead or unused", "audit my skills", "skill health", "skills dashboard", or wants a skill usage report.
SantosAlarcon/css-best-practices/skills Skill
0★ repoSkills for CSS3 best practices
Myra-Agents/skills/skills/build-in-public Skill
0★ repoTurn a shipped release OR a single feature/bug-fix branch into review-ready "build in public" drafts — an X/Twitter thread, a LinkedIn post, and (for major releases) a Product Hunt launch kit, from the repo's changelog, as English drafts you edit before posting. Use when the user wants to announce a release or a feature/fix, build in public, write a launch thread or post, draft a Product Hunt launch, or share dev progress publicly after tagging a version or finishing a branch.
xenonfluoride/interview-prep-skill Skill
0★Generate a tailored PM interview-prep briefing. Reads a Job Description file plus the candidate's resume from a working folder, runs live web research on the company, and produces ONE self-contained HTML report with three core tabs: Company Briefing, Role-to-Me Fit, and Interview Questions + tailored talking points. If a domain-knowledge gap is detected (e.g. post-trade ops, insurance, credit risk, healthcare payments), a fourth Domain Primer tab is auto-generated. An independent checker reviews the report before it is presented. Optionally takes an interview round to weight the questions. Say "make PDF" after the report is delivered to export a print-ready version. Triggers: "interview prep", "prep for interview", "run interview prep", "build interview brief", "prep me for this interview", "interview briefing".
Yurcek/wcag22-audit/wcag22-audit Skill
no license0★ repoAudit and fix web application accessibility against WCAG 2.2 (level A/AA, with AAA recommendations), with deep Angular-specific coverage. Use this skill whenever the user mentions accessibility, accessibilità, a11y, WCAG, screen readers, keyboard navigation, color contrast, ARIA, axe-core, pa11y, or asks to audit/verify/fix accessibility of components, pages, forms, dialogs or an entire app — even if they don't say "WCAG" explicitly. Also use it when reviewing or generating Angular templates/components where accessibility correctness matters (custom controls, dialogs, forms, routing focus management).
alexbanda08/clmm-command-center/skill Skill
0★ repoMonitor, backtest, rebalance, and tax-track Solana concentrated-liquidity LP across Orca Whirlpools, Raydium CLMM, Meteora DLMM/DAMM v2, and Kamino vaults; realtime out-of-range gRPC/websocket alerts, IL-vs-HODL + fee-APR backtest, cross-DEX yield routing, simulate-first human-confirm rebalance, and a FIFO/HIFO/SPECID tax-lot ledger.
Hermes skill portfolio news monitor
web3blind/hermes-skill-portfolio-news-monitor Skill
no license0★Weekly X/Twitter digest по существенным активам портфеля. Использует curated watchlist, categories сигналов и короткий weekly summary без hourly flood.