The catalog
608,253 rows, by stacks then stars
stef-k/agent-loc-guard/skills/loc-guard Skill
0★ repoUse when creating, editing, reviewing, or refactoring source files to enforce a deterministic file-length policy across agent-assisted coding workflows. Run the bundled LOC checker, warn at 400 counted LOC, and hard fail at 600 counted LOC unless explicitly exempted.
hsinhan-h/hh-claude-skills/commit-msg Skill
no license0★ repoGenerate a conventional commit message from staged git changes. Use this skill whenever the user asks to generate, write, or produce a commit message — including phrases like "幫我產commit message", "generate commit message", "根據staged changes產commit message", "commit訊息", "幫我寫commit", "產生commit", "寫commit message", "commit 怎麼寫", or any request to commit staged changes. Always invoke this skill before writing commit messages yourself.
vivian254338489/agent-skills-openai-compatible-pack/skills/codex Skill
0★ repoUse when a Codex task needs to configure, diagnose, or migrate an AI coding project to an OpenAI-compatible API endpoint without leaking credentials.
aby-studio-works/garelier/skills/garelier-artisan Skill
0★ repoGarelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/artisan invocation, not on generic implement/research/harden/merge wording. Artisan is the artisan lane — a SINGLETON doing the combined Dock+Worker+Scout+Smith+Librarian scope BY ITSELF for one task: plan, investigate/web-research, implement+commit, harden, knowledge/registry/runbook work, own quality gate + coverage audits, pass Guardian then Observer, integrate its satchel branch into studio, report to PM. Never merges to target, never delegates; mutually exclusive with the dock lane (runtime/lane.lock). Activate in a `__garelier/<pm_id>/_artisan/` worktree, when an assignment.md appears for the Artisan, when answers.md arrives after BLOCKED, when a lane.lock names the artisan lane, or on Artisan / satchel branch / single-agent end-to-end work. Requires garelier-core.
gcunharodrigues/xp-icm-workflow Skill
0★One-shot bootstrap ICM (Interpretable Context Methodology) that creates the L0/L1/L2/L3 structure + git branch + hooks in a project and exits; subsequent sessions read L1+L2 from the current stage. Supports 5 active stages (v4.0: 00 recon → 01 discovery → 02 design+plan → 04 implementation waves → 08 feedback intake), 11 profiles × 4 tiers (incl. fullstack), subagents via Agent Tool stage 04, deterministic Wave Planner (runs inline in stage 02), Recovery Wizard, AGENT-BRIEF protocol, ubiquitous language layer, ADR 3-criteria gate, diagnose protocol, triage state machine, OUT-OF-SCOPE knowledge base, DESIGN.md format for frontend/fullstack. Use when starting a new ICM workspace, multi-stage project with human review between steps, complex feature requiring discovery+design+implementation+review+merge, or implementation that benefits from parallelism via subagents. Skip when task is trivial (1 file), simple bug fix, cosmetic refinement, or continuing an existing workspace (fresh session reads L1+L2 on its own — do not re-invoke).
rayhan30/seo-audit-skill/seo-audit Skill
0★ repoPerform a comprehensive SEO audit of any website and generate a structured branded report. Use this skill whenever the user mentions auditing a website, checking SEO health, finding SEO problems, reviewing on-page SEO, or asking why a site ranks poorly. Also trigger for requests like "check my site's SEO", "what's wrong with my website SEO", "run an SEO report", or "audit this URL". Covers technical SEO, on-page elements, structured data, page speed, local SEO, internal linking, plugin audit, and keyword targeting. Always use this skill for any SEO-related website review, even if the user doesn't say "audit" explicitly.
Skill identity access management
zavora-ai/skill-identity-access-management Skill
no license0★Orchestrate identity and access management — user lookup, group membership, MFA verification, entitlement management, access requests, and emergency revocation. Use when looking up users, checking permissions, managing group membership, verifying MFA status, processing access requests, or revoking access.
Hosseinkm89/figma-skills/accessibility-contrast-audit Skill
0★ repoAudits color contrast on a Figma page against WCAG 2.1 AA and AAA, then writes a clean, designed report onto a brand-new page in the same file. For every top-level frame it scores text contrast (1.4.3 AA and 1.4.6 AAA, with the large-text exception) and flags low-contrast UI strokes/borders (1.4.11, 3:1), giving each frame a PASS/FAIL verdict. The report lists one row per frame with pass/fail badges and a clickable link that jumps straight to that frame, plus its node address printed underneath — so findings are easy to act on without cluttering the layout. Triggers when a designer wants to check contrast or accessibility before handoff — phrasings like "check the color contrast on this page", "run a WCAG contrast audit", "is this design AA compliant?", "which frames pass AA and AAA?", "audit contrast and write up the results", "are my text colors accessible?", "find low-contrast text", "contrast check before handoff", or "make me an accessibility contrast report". Reads the designs and creates a report page only — it never restyles or modifies the audited frames. Do NOT use this to FIX contrast (it reports, it doesn't recolor), to run a full accessibility review beyond contrast (keyboard, alt text, focus order), or to build new components (use figma-generate-library).
HaloForgeAI/adac-skills/skills/adac Skill
0★ repoUse this skill when planning, executing, reviewing, or formalizing AI-assisted coding work that needs acceptance-first delivery controls: complex module changes, production behavior changes, performance work, concurrency/resource lifecycle work, regression-sensitive refactors, release/rollback decisions, or requests to turn an AI coding method into a reusable spec, skill, or engineering workflow.
marsloting/product-thinking-pack/skills/decision-matrix Skill
0★ repoApply Pugh matrix + Multi-Criteria Decision Analysis (MCDA) when choosing among multiple options across multiple weighted criteria. Use whenever 用户 says "几个方案选哪个" / "怎么决定" / "团队意见不一致" / "vendor 选型" / "技术选型" / "供应商对比" / "decision matrix" / "比较 X 和 Y 和 Z". Forces criteria definition with explicit weights, scores each option per criterion, identifies dominant solutions, surfaces hidden disagreements (when team scores diverge significantly). Stops "感觉 X 比较好" decision by structure. Distinct from RICE (RICE = single-dimension prioritization, this = multi-criteria comparison). Self-contained methodology — no external docs required.
anyshift-io/annie-skills/skills/annie Skill
0★ repoUse the Anyshift MCP server (and the Annie CLI as the user-facing chat client) to investigate infrastructure: discover resource types, search the graph, track changes, audit a single resource's timeline, and inspect resources in detail. Use when the user asks about a resource, a deploy, an impact analysis, or wants to compare infra state across time. Keywords: annie, anyshift, mcp, infrastructure, resource graph, change tracking, audit timeline, temporal diff.
slogsdon/skills-vault-knowledge/skills/backlinks Skill
0★ repoUse when asked to audit backlinks or repair the knowledge graph structure, or when /backlinks is invoked. Do NOT use for finding conceptual bridges between ideas — use /connect for that.
kalyvask/pm-evaluation-framework/.claude/skills/pm-context-loader Skill
0★ repoLoad the PM agent's persistent context — personal style and preferences from `you.md`, the active project list, cross-project stakeholders, and the relevant project's state. Use as the first step in any PM workflow when you need the agent to understand the user's current work before doing anything else. The other operate-stage skills (pm-morning-brief, pm-meeting-prep, pm-meeting-debrief, pm-weekly-review, pm-stakeholder-tracker) chain to this skill first.
cportka/claude-plugins/plugins/app-website-evaluator/skills/app-evaluation Skill
0★ repoEvaluate an app or website and produce a prioritized, evidence-backed report — SEO and crawlability, AI-readiness, social/sharing assets, security and standards, performance/load-time, accessibility, and growth (which communities to join or submit to, PR/advertising wins). Use when the user asks to audit/review/evaluate/grade a website or app, improve its SEO/reach/discoverability, get it ready to launch or submit, or asks "how good is my site and what should I fix?"
php-opcua/ai-skills/skills/laravel-opcua Skill
no license0★ repoLaravel 11/12/13 integration for OPC UA. Provides a Facade (Opcua::*), service provider, .env-based named connections, an Artisan daemon command (opcua:session), and transparent session persistence via the opcua-session-manager daemon. Use this skill whenever the user is working with OPC UA from a Laravel application — controllers, jobs, Livewire components, Filament panels, broadcasting, Horizon queues, Octane workers, scheduled tasks, or Pest tests.
blammectrappora/synthwave-art-generator Skill
no license0★Generate stunning synthwave and retrowave art with neon grids, 80s retrofuturism, chrome sunsets, and palm tree silhouettes. Perfect for album covers, music video backgrounds, gaming streams, Twitch overlays, retro band posters, vaporwave alternative aesthetics, and 1980s nostalgia content via the Neta AI image generation API (free trial at neta.art/open).
kugamon/kugamon-skills/plugins/kugamon/skills/kugamon-full-qtc-submgmt Skill
no license0★ repoManage the full Kugamon Quote-to-Cash lifecycle in Salesforce — opportunities, quotes, orders, invoices, payments, shipments, and assets, which uses the kugo2p namespace (Kugamon Quote to Cash). And optionally Managed the full Kugamon Subscription Billing lifecycle in Salesforce - opportunities, quotes, orders, invoices, payments, shipments, contracts, subscriptions, and assets, which requires the kuga_sub namespace (Kugamon Subscription Management). Detects which packages are installed and adapts accordingly. Use when users request operations on any Kugamon object.
slogsdon/skills-meta-utils/skills/compress-prompt Skill
0★ repoUse when about to write a long prompt, include verbose text in context, or when any block of text needs to be made token-efficient before use. Delegates compression to a local model via the LiteLLM proxy (ollama-agent MCP).
JunbaoLiang/audit-with-plans/skills/audit-with-plans Skill
0★ repoAudit any planning-with-files project — spawn independent fresh-context subagents that check code ↔ `.planning/*.md` discrepancies in both directions, require entry-point execution, and only exit on a fresh 0/0/0/0. Use when asked to audit, code-review, or check whether a project is consistent.
Spacetime-Technology/chia-skills/skills/address-daily-digest Skill
0★ repoCompose and deliver a daily (or weekly) summary of activity at one or more Chia addresses — inflows, outflows, ending balance, USD value at receive time. Use when the user wants a recurring report instead of per-event alerts, or asks for a "daily summary" / "weekly digest" of their wallet. Accepts addresses, period_hours, currency, channel as arguments for programmatic invocation.
kwouz/skillsforge-free Skill
0★FREE TEASER — Generate Google-perfect title tag (50-60 chars) and meta description (140-160 chars) for any URL or topic. Honor character limits, include primary keyword naturally, add brand suffix, optimize CTR with proven copy patterns. Use when user asks for "title tag", "meta description", "page meta", "SEO meta", or pastes content to optimize.
alabenkhlifa/codex-stitch-designer/claude/stitch-designer/skills/stitch-designer Skill
0★ repoUse Google Stitch MCP from Claude Code to create, inspect, refine, and hand off high-quality UI designs. Use when the user asks for Stitch projects, screen generation, design-system work, variants, mockup-to-prompt conversion, or implementation handoffs from Stitch output.
Naz1anmak/claude-code-notifications Skill
0★Use when the user wants desktop notifications for the Claude Code CLI (terminal) — alerts when a turn finishes, when a tool needs permission, or when an interactive question (AskUserQuestion/ExitPlanMode) is waiting. Covers macOS, Linux, and Windows. Not for the Claude Code desktop app (which has its own in-app notifications). Triggers on phrases like "notify me when claude finishes", "desktop notification for permission prompts", "set up sounds for claude code", "I miss claude's responses when in another window".
moonpiesheldon1337/grounded-research Skill
0★Enforces source-grounded, citation-first research discipline. Use this skill whenever the user asks to research a topic, fact-check a claim, summarize recent findings, look up current information, explain what the evidence says about something, or produce any factual output where accuracy and verifiability matter. Trigger even on conversational phrasing like "what's the deal with X", "is it true that Y", "what do experts say about Z", or "can you check if..." — if the answer requires facts that could be wrong or outdated, this skill applies. When in doubt, use it.
Proboi-ai/proboi-skills/article-writing Skill
no license0★ repoНаписание статей и лонгридов, которые звучат как от человека, а не от нейросети. Сбор контекста, выбор структуры, AI-детокс на всех уровнях (лексика, грамматика, структура, ритм), паттерны живого письма, сторителлинг, чеклист. Поддерживает detect-only режим.
markbain/bain-skills/bootstrap-claude Skill
no license0★ repoBootstrap a new Claude project — links an Asana project and writes default permissions to .claude/settings.json. Use when starting a new project, setting up Claude in a repo, or saying "bootstrap this project".
Spikeon-Studio/caveman-plan/skills/caveman-plan Skill
0★ repoLarge-project planning and execution in caveman voice. Creates epic checklists in .plans/epic_*.md, breaks each Epic step into its own plan_*.md hunt file (never one plan for whole epic), superpowers-plan detail per file, runs one hunt per Boss approval (hard stop between plans — never chain hunts in one turn), Follow Ups for uncertainty, then inventory-kills against the epic Goal. Depends on caveman (communication) and superpowers-plan (plan steps). Use for epics, multi-phase projects, /caveman-plan, "epic plan", "go hunting", "NEXT HUNT!", or when work spans many files/sessions and needs Boss checkpoints.
aigovbrasil/aigovbrasil/skills/major-os/praxis-os Skill
0★ repoProfessional services operating system for consultants and knowledge-worker operators. Activate ONLY when the user types "/praxis" or any "/praxis-*" command, when a new conversation starts in a project that already contains praxis-os state files (consultant_config.yaml, session_state.yaml, or manifest.yaml), or when the user expresses consulting intent that no single specialist agent clearly covers (ex: "new client just signed", "where am I in the case", "what's the next step in my workflow"). Do NOT activate for questions a single specialist already handles cleanly — let the specialist fire directly. The router is a dispatcher, not a wrapper. Routes to 23 specialist agents across 5 phases: SIGNAL, INTELLIGENCE, ARTIFACT, DELIVERY, FEEDBACK. Never invents commands. Never promotes hypotheses to facts. Always confirms before destructive action.
didiowen/pubmed-daily-digest Skill
0★Daily medical-literature digest agent — searches the past 24 hours on PubMed across configurable thematic queries, fills in missing abstracts via CrossRef, writes a TL;DR and a one-line Hot Take for each article (English by default; language is configurable in Step 2/3), picks 3–5 notable highlights, and renders a Markdown digest to a local output directory. Trigger when the user says "run daily digest", "daily lit", "daily journal", "medical literature digest", or "跑每日文獻". For yearly maintenance the skill also handles "update SJR scores" / "refresh journal rankings" — see the Maintenance section near the bottom.
cabbagecachekid/red-pen/skills/ai-written-check Skill
0★ repoDetects the mechanical tells that make professional prose read as AI-generated — em dashes, triple-list anaphora, "not X but Y" antithetical pairs, spatial and economic metaphors for abstract ideas, "architect" as a verb, engineered sentence cadence, mid-paragraph register swerves, builder/startup slang, and unfalsifiable universal claims ("everyone", "across the board"). Use when reviewing or editing a resume, cover letter, portfolio page, case study, proposal, bio, or any human-facing copy, or when the user asks for an "AI-written check", "AI tells", says copy "sounds like AI", or asks to make writing sound less generated.
The same file is in 1 other repository
globalsolo-os/solo-founder-risk-diagnostic Skill
no license0★Free 7-question structural risk diagnostic for cross-border solo founders running US LLCs (or other entities) from outside the US. Scans Money, Entity, Tax, and Accountability axes using the META framework and returns deterministic per-axis risk scores plus flagged risk patterns. Use when a user asks any of "what's my structural risk", "scan my setup", "META check", "am I missing something about my LLC / banking / tax structure", "I run a US LLC from abroad — what's my exposure", or any variation framed around a solo founder's cross-border legal/financial structure. Do NOT use for tax filing help, formation help, or vendor recommendations — this skill diagnoses risk patterns, it does not prescribe solutions.
sdfkr22/session-bug-hunter Skill
no license0★Analyzes the current Claude Code session — conversation history AND changed code files — to detect potential bugs, technical debt, regressions, and performance issues, then creates structured GitHub issues for each one after user approval. Always use this skill when the user says "find bugs", "open issues", "create github issues", "bug report", "what bugs did we introduce", "session bugs", "hunt bugs", "report issues to github", or anything implying they want to capture problems from the current session as GitHub issues. Also trigger proactively when the user is wrapping up a session and there were visible errors, workarounds, or "fix later" comments during the session.
The same file is in 1 other repository
trademomentum-llc/parameterizing-plan-docs Skill
0★Use when authoring or maintaining a multi-step plan, runbook, or implementation document containing configurable values (ports, namespaces, repo names, version pins, paths, URLs, secret names) that future readers may need to substitute when applying the plan to a different environment.
18studio/avito-skill Skill
no license0★Manage Avito business workflows through the `avito-py` Python SDK from `p141592/avito_python_api`. Use when Codex needs to analyze Avito listings, paid promotion, chats, calls, CPA leads, orders, delivery, labels, stock, reviews, ratings, realty pricing/bookings, jobs/vacancies/applications/resumes, account balance, employees, phones, tariffs, or Autoload diagnostics.
irisfeng/kindle-pdf-skill/skills/kindle-pdf-skill Skill
0★ repoReflow/optimize PDFs for small e-readers (Kindle 6", Kobo, etc.) so technical books with code/tables/equations stay readable. Covers k2pdfopt, Calibre, and Kindle device settings.
leadupofficial/leadup-claude-skills/leadup-admin-panel-planner Skill
0★ repoPlan an admin panel for a LeadUp SaaS, client website, or CRM — super admin, org admin, tenant admin, and staff views. Outputs navigation, modules, tables, filters, actions, roles and permissions, reports, dashboard KPI cards, and empty/loading/error states. Tuned for multi-tenant SaaS and India SMB tools. Use when the user says "admin panel", "dashboard plan", "super admin", "tenant admin", "CRM dashboard", or "admin modules".
SousouGarden/vc-playbook-suite/board-dynamics-wargame Skill
no license0★ repoCEO 被罢免的 Boardroom 博弈推演引擎。不是讲「怎么开好 board meeting」,而是「VC + 独董如何联合 fire 你」「CEO coup 如何预防」「产品战略分歧如何不变成 personnel 分歧」。含 10 个经典 CEO 罢免 / board 政变案例 + 5 种 faction 动态 + 12 种 boardroom move。
jordanl17/claude-skill-targetable-feedback/targetable-feedback Skill
0★ repoRenders multi-section drafts as an interactive widget where each paragraph and bullet is tappable for inline per-unit guidance. Use when the user signals intent to iterate on a draft, either at generation time ("draft an RFC and let me give feedback on each section," "write X so I can iterate on each part") or retroactively on prior multi-section assistant output ("let me give feedback on each part," "make that targetable," "I want to mark up what you just wrote"). Do not trigger for one-shot drafting requests with no stated iteration intent, single-edit feedback like "fix bullet 3," content that is mostly code or tables, or output under roughly three paragraphs.
benskamps/finding-underserved-keywords Skill
0★Use when optimizing existing pages for SEO, hunting low-hanging keyword opportunities, analyzing pages that get impressions in Google Search Console but few clicks, or planning a content refresh. Covers the full content lifecycle (initial → growth → mature) and integrates with Generative Engine Optimization (GEO) for AI-search visibility. Applies to any site with GSC access.
glebmish/lifeops-skills/plugins/ebay-listing/skills/ebay-improve-listing Skill
0★ repoCritique and improve an existing eBay listing — dispatches a fresh subagent for unbiased review, then applies selected suggestions. Use when the user says "improve this listing", "can we do better", "review my listing", or wants a second opinion on pricing, title, or description.
tabgab/opp_repl-skill/opp-repl-ai-workflows Skill
no license0★ repoEnd-to-end recipes for an AI agent working with opp_repl via its MCP server or shell tools — investigate a regression, bisect across git commits, tune parameters, run a full release gate, set up a new project from scratch. Load this ALONG WITH opp-repl-mcp-server when acting as an autonomous agent managing OMNeT++ simulations.
duangduang55/notion-sync-skill Skill
no license0★将对话内容结构化地同步到 Notion 数据库。触发词:同步到 notion、更新到 notion、存到 notion、记录到 notion、保存到 notion、写入 notion。首次使用需交互式配置 API Token 和数据库 ID,自动读取属性结构并设置映射。
drsreekrishnan/constellation-map-skill/skills/constellation-map Skill
0★ repoTransforms a mind map image (PNG, JPG) into a fully interactive dark-space constellation map visualization — a single self-contained HTML file with physics-based floating nodes, color-coded branches, drag/focus interactions, and twinkling background stars. Use this skill whenever the user uploads or references a mind map, concept map, hierarchy diagram, or any tree-structured image and wants it turned into an interactive visual, constellation, star map, or node graph. Also trigger when the user asks to "visualize", "animate", or "make interactive" any hierarchical PNG or diagram. Even if the user just says "make this interactive" alongside an image with a tree structure — use this skill.
Teguhcanggu/vps-mcp-hub-skill Skill
0★Plan, deploy, verify, and connect self-hosted remote MCP servers on a VPS-backed hub for Claude Chat, ChatGPT, and API clients. Use this skill when a user wants an end-to-end VPS MCP hub workflow: classify an MCP server, prepare source code, containerize it, handle secrets safely, deploy it as an isolated sidecar or register an npm/STDIO server, expose it through a remote MCP hub, verify tools/list and smoke calls, connect clients, and document rollback/monitoring. Created by Jiwa Karya Bali as a public, reusable production deployment pattern.
BridgeLogicsProjects/okr-skill-coach/okr-ai-product-teams Skill
0★ repoUse this skill whenever someone is setting OKRs for an AI product team, an AI-enabled product, or any initiative where the output is non-deterministic — meaning the system learns, adapts, or produces results that cannot be fully predicted in advance. Triggers include any mention of AI product OKRs, machine learning metrics, model performance goals, trust metrics, responsible AI, AI feature adoption, or when someone is struggling to write Key Results for work where outcomes are probabilistic rather than guaranteed. Also use when a team is treating AI features like any other feature and missing the unique measurement challenges. This skill coaches AI-specific OKR writing and connects goal-setting to responsible AI practice.
CarlosJunioor/skillZs/skills/find-agent-skills Skill
no license0★ repoFind, compare, and safely evaluate Agent Skills for Claude Code, Codex, Cursor, Copilot, Gemini CLI, and other compatible agents. Use when someone asks for a skill, reusable workflow, SKILL.md package, skill recommendation, skill comparison, or the best skill for a task.
codeugar/ai-stem-splitter-skill Skill
0★Use when the user wants to split a song or audio file into vocals, drums, bass, guitar, piano, and other stems; remove vocals for karaoke; extract acapellas or instrumentals; process YouTube, SoundCloud, Bandcamp, direct audio URLs, MP3, WAV, or other audio through the AI Stem Splitter API, SDKs, or web app.
wachawo/claude-skills/skills/banner-design Skill
0★ repoDesign banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage. Uses ui-ux-pro-max, frontend-design, ai-artist, ai-multimodal skills.
The same file is in 7 other repositories
koenvdheide/codex-skill/skills/codex Skill
0★ repoInvoke the local Codex CLI as an independent analysis partner. Use when you need to brainstorm alternative approaches, red-team a plan or decision, get a fresh debugging perspective, or review a diff/report adversarially. Do NOT use for trivial tasks, simple lookups, or when no concrete artifact or question exists yet.
Thanane15M/telegram-agent-router Skill
0★Multi-agent Telegram bot architecture with PostgreSQL-native state management. 10+ specialized agents, intent-based routing, persistent cross-session memory, and production-grade conversation state machines. Activate when building or debugging Telegram bots with multiple agents, routing logic, conversation context, or persistent memory. Trigger phrases: "telegram bot agents", "multi-agent telegram", "route messages to agents", "telegram bot router", "conversation state telegram", "persistent memory bot", "telegram intent classification", "agent handoff telegram", "telegram session state", "specialize telegram bot", "telegram webhook architecture".
prakash888kp/AEM-SKILLS/skills/tier-1-administration/aem-component-development Skill
0★ repoA curated catalog of Adobe Experience Manager (AEM) skills organized into tiers, with dependency chains and contribution guidelines.
alexzhu0/agent-ready-skills/skills/agent-handoff-brief Skill
0★ repoUse when handing work from one AI agent, developer, or session to another by summarizing current state, files touched, decisions made, blockers, verification, and next safe actions.
Diegocortes15/playwright-ia-automation-framework-saucedemo/.claude/skills/from-issue Skill
no license0★ repoGenerate Playwright tests from a Jira ticket (read via the Atlassian MCP), composing /scaffold-page-object when a target Page Object doesn't yet exist, and open a GitHub PR with the generated tests for review.
blammectrappora/italian-brainrot-generator Skill
no license0★Italian Brainrot Generator — turn any character or selfie idea into the viral Italian-brainrot meme style with exaggerated mamma-mia hand gestures, dramatic facial expressions, and absurdist humor energy. Perfect for TikTok reaction images, Instagram Reels covers, meme posts, viral content, brainrot edits, Italian gesture memes, and absurdist humor formats. Generate brainrot-style portraits, character memes, reaction faces, and shareable viral content via the Neta AI image generation API (free trial at neta.art/open).
fengyiqicoder/hubspot-pipeline-cleanup Skill
0★Use when the user wants to clean up HubSpot (or any CRM — Salesforce, Pipedrive, Close) pipeline, identify stale deals, fix deal stages, or audit pipeline health. Triggers on "my pipeline is a mess", "find stale deals", "clean up HubSpot", "review my deals", "what should I close out", "pipeline review before forecast", "deals stuck in stage X", or running quarterly pipeline hygiene. Also triggers when the user mentions forecast accuracy problems or sales velocity metrics.
blammectrappora/muppet-portrait-generator Skill
no license0★Turn yourself, friends, or any character into a hilarious muppet-style felt puppet portrait with googly eyes, fuzzy fabric textures, and exaggerated colorful features. Perfect for viral TikTok memes, profile pics, birthday cards, social media posts, and Sesame Street-inspired fan art. Generate plush puppet avatars, felt character portraits, fuzzy creature designs, and silly puppet-fication transformations in cinematic studio lighting via the Neta AI image generation API (free trial at neta.art/open).
Audrent-hq/skills/saas-contract-review Skill
0★ repoReviews a SaaS contract (MSA, order form, DPA, EULA) against a configurable standard markup, surfaces clauses that deviate from market norms, and suggests specific redline language. Use when reviewing inbound vendor contracts before signing, evaluating customer-pushed redlines on your own paper, or doing a periodic contract-stack audit. Outputs structured findings with severity and specific drafting suggestions.
Loringtonian/usage2 Skill
0★For Claude Code SUBSCRIPTION users (Pro / Max 5x / Max 20x) — give the agent visibility into its own token consumption with API-equivalent dollar cost, % of session/week quota, and per-subagent attribution. Reads Claude Code's per-message `usage` blocks from the session transcript JSONL. Captures the built-in `/usage` panel via tmux for rolling 5h/7d/Sonnet-only quota percentages. Includes a passive calibration that learns your tier's tokens-per-percent from real samples. Use when the user says "/usage2", "how many tokens", "token cost", "compare token usage", "am I being efficient", "what's my quota", "how close to the limit", "subagent cost", "which subagent burned the most", or whenever the agent needs to reason about session/week budget, model efficiency, or A/B token comparisons.
mrsoundmind/product-audit-skill Skill
0★Comprehensive UX, product strategy, and experience audit skill. Use this whenever the user invokes /audit, /product-audit, /ux-audit, /site-audit, or asks for a design audit, UX audit, product audit, experience audit, or conversion audit for any app or website. Triggers on: 'audit this product', 'audit this app', 'audit this site', 'run a full audit', 'do a UX audit', 'review the experience of', 'audit for a client'. Produces a comprehensive .docx report authored by Shashank Rai, with depth scaled to product type. Always use this skill. Never attempt an audit without reading it first.
ezos26/claude-skills/skills/audit Skill
0★ repoComprehensive multi-domain codebase audit. Runs security, architecture, data, UI, integration, and performance audits in parallel with cross-examination. Usage /audit [scope]. Examples /audit full, /audit security, /audit tesla, /audit iterations 40-52