The catalog
608,666 rows, by stacks then stars
jeffliu05042/send-email-skill/skills/send-email Skill
1★ repoSend plain-text email through either macOS /usr/bin/mail or an explicitly selected authenticated SMTP service, with RFC 2047 subject encoding and remote acceptance verification. Use when the user asks to email, mail, send, or deliver a report, notification, or confirmation, including when direct Postfix delivery is rejected because of sender-IP reputation.
ccckfg/agent-skills-manager/skill/agent-skills-manager Skill
no license1★ repoManage local AI Agent Skills with the dependency-free scripts bundled inside this Skill. Use when inspecting, comparing, importing, or synchronizing Skills across Claude Code, Codex, Cursor, Antigravity, Gemini CLI, GitHub Copilot CLI, Windsurf, opencode, Kiro, Pi, Qoder, Trae, CodeBuddy, Kimi Code, iFlow, Qwen Code, Lingma, MiMo Code or the shared ~/.agents directory; listing their MCP servers; or safely reviewing MCP and other agent configuration. The bundled script works without installing the optional TUI.
Mahermenix/fable-relay Skill
1★Use when the owner wants Fable 5 involved in a task — planning a feature with Fable, preparing a brief or kickoff for a Fable session, estimating what a Fable session will cost, escalating a hard problem to Fable, or executing a Fable-authored plan with GLM/OpenCode workers. Also when the owner says "fable-relay", "prep for Fable", or "run the stories".
davidabaddesign-glitch/project-advisor/skills/project-advisor Skill
1★ repoComprehensive project and business advisor & coach that orchestrates specialist subagents (market, competition, finance, strategy, marketing, product, risk) with mandatory critical verification, FARO coaching, accountability, OKRs and persistent project memory. Use whenever the user asks for advice or coaching on their project or business: validating an idea, starting a company, feasibility, business plan, strategy, goals, progress reviews, pitch — or says "advise me", "let's have a session", "what do you think of my idea", "is this viable", "how do I monetize", "I'm stuck". Spanish triggers too: "asesórame", "hagamos una sesión", "qué opinas de mi idea", "es viable esto", "cómo lo monetizo", "estoy atascado". Also: business advisor, coaching, FARO session, startup advice, idea validation, accountability check-in. Do NOT use for general knowledge questions unrelated to the user's own project ("what is a SAFE") or standalone tasks another skill covers directly (a post, an email).
TGPSKI/go-fips-toolkit/.agents/skills/fips-crypto-audit Skill
1★ repoRuns a FIPS 140-3 crypto compliance audit across Go repositories, classifying every crypto/ import by risk and generating per-component reports. Separates first-party code from vendored dependencies and flags non-cryptographic uses of crypto primitives that break under GODEBUG=fips140=only. Use when auditing Go services for FIPS compliance, assessing new repos before adding them to FIPS CI, re-running an audit after vendor bumps, or generating evidence for compliance documentation.
acost1a/future-regret/skills/future-regret Skill
1★ repoUse when the user is about to commit to an architecture, data-model, dependency, or design decision on an existing codebase (picking a database or schema shape, build vs buy, adopting a library or pattern, locking an API contract, or "let's just do X for now"), or asks what they'll regret later ("will I regret this", "what will bite us", "future-proof this"). Run BEFORE writing the code or agreeing. Do NOT use for brand-new product ideas, routine bug fixes, or trivially reversible choices.
LorcanChinnock/reflect Skill
1★Use at the end of a session, or when the user says "/reflect", "reflect on this session", "save what you learned", or "update your memory". Reviews the session for token-wasting detours, reusable workflows, blockers, corrected assumptions, and undocumented quirks, filters hard, then routes each survivor to its home: lean personal auto-memories (editing, merging, and deleting as readily as adding) or, for a durable convention the whole repo needs, a proposed edit that lands via a normal PR — amending a fitting existing doc (an @-referenced sub-file, or an AGENTS.md section) when one exists, otherwise a lean .claude/memories/ note @-imported from CLAUDE.md, never inlined into CLAUDE.md's own body. Proposes a concise change list before writing. Works best with Claude Code auto-memory, but the project-instructions route also works with it off; needs no other skill.
goodday6709-sudo/one-fact-one-source-skill/skills/one-fact-one-source Skill
1★ repoUse when a coding task may create, change, audit, or consolidate multiple implementations of the same business fact across functions, constants, statuses, permissions, amounts, schemas, contracts, derived caches, or repositories.
smkuxi71-hash/skill-ship-max/core/.agents/skills/ship-codex-max-orchestrate Skill
no license1★ repoImplementation-only release-slice G3 loop for ship-codex-max v2 with TDD, medium-only adaptive Coach, hard budgets, build leases and a committed review ledger.
nguyenthdat/opencode-manager/.opencode/skills/typescript-coding Skill
1★ repoComprehensive idiomatic TypeScript/JavaScript guidance: 171 prioritized rules across 14 categories. Use when writing, reviewing, refactoring, optimizing, or debugging TypeScript or JavaScript (`.ts`, `.tsx`, `.js`, `.jsx`, `tsconfig.json`, `package.json`). Preserve the target project's declared TypeScript version, module system, and strictness settings; apply `satisfies`, `verbatimModuleSyntax`, `noUncheckedIndexedAccess`, and other modern-config guidance only when the project's toolchain supports them.
vivekkartha/terminal-computer-use/skills/computer Skill
1★ repoTerminal-first Computer Use: control files, folders, apps, clipboard, notifications, screenshots, and multi-step desktop workflows via shell scripts (bash/Python). Works with Claude Code, Cursor, Codex, Grok, Gemini CLI, and any agent with a terminal. Reuse scripts next to this SKILL.md. Use when the user wants computer use, desktop control, open/quit apps, organize files, Finder automation, or runs /computer.
jasperkong1996xx/interview-signal/skills/interview-signal Skill
1★ repoUse when an interviewer needs an evidence-driven interview guide, a live follow-up probe, or a multi-round handoff based on a candidate resume, job description, interviewer perspective, and any previous interview questions and candidate responses.
Integrating standard site hugo
halans/integrating-standard-site-hugo/integrating-standard-site-hugo Skill
1★ repoAn agent skill to add the necessary at-proto standards.site plumbing to a Hugo blog.
dkmqflx/nestjs-best-practices-plugin/plugins/nestjs-best-practices/skills/nestjs-caching-queues Skill
1★ repoNestJS caching and background-job queue best practices. Use when adding caching or async job processing to NestJS — CacheModule, cache-manager, Redis, or BullMQ/Bull queues. Triggers on CacheModule, @InjectQueue, @Processor, cache TTL, or background jobs.
The same file is in 1 other repository
zdnemz/claude-team/.claude/skills/continue-work Skill
1★ repoAutonomous execution loop — pick the next ready tasks from the plan, dispatch specialist agents with the right model, verify results, record progress, commit. Use when state phase is PLANNED or EXECUTING.
Xavier189/dig-skill/skills/dig Skill
1★ repoSocratic requirements excavation for uncovering what the user actually wants before work begins. Use whenever intent, goals, scope, constraints, success criteria, or hidden decisions are unclear or admit materially different interpretations, regardless of task size or domain. Also use whenever the user explicitly asks to dig, clarify, excavate, or challenge the requirements. Do not trigger merely because a task is large, architectural, or complex when the request is already decision-complete. Skip clear requests and purely informational questions unless explicitly invoked. Produces a clarity memo the user confirms before downstream work resumes.
metalaihq/trip-event-curator/skills/edition-check Skill
1★ repoGate against presenting an ended run as ongoing — verify every exhibition run, festival edition, conference year, and popup window against today's date before it reaches the traveler (a recommended exhibition that closed last month destroys trust instantly), and turn ended-but-recurring events into a next-edition watch card using official pre-announcements first, past cadence as a labeled estimate otherwise. Use when the user says '이거 아직 해?', '전시 끝난 거 아니야?', '이번에도 열려?', '다음 회차 언제야?', '작년엔 했다던데 올해는?', or automatically when event-finder/scouts surface a candidate whose run dates are unconfirmed or past, or when search results smell stale. Inherits v1.0 next-edition-watch concepts (ended-edition gate, pre-announcement pattern, cadence estimates). Produces ED-nn signals.
robcsaszar/frontend-kit/skills/with-canvas Skill
1★ repoCanvas implementation and review guidance for vanilla JavaScript, TypeScript, Web APIs, OffscreenCanvas, Web Workers, CanvasRenderingContext2D, WebGL-backed canvas, and canvas libraries including p5.js, Paper.js, Pencil.js, Konva, ZIM, Three.js, and Babylon.js. Use when creating, editing, optimizing, debugging, or reviewing canvas animations, generative art, games, charts, particle systems, interactive drawing tools, layered scenes, high-DPI rendering, RAF loops, hit testing, memory lifecycle, or performance issues. Trigger phrases: canvas, HTML5 canvas, OffscreenCanvas, requestAnimationFrame, getContext('2d'), drawImage, ImageData, particles, retained mode canvas, Konva, p5, Paper.js.
The same file is in 1 other repository
metrox-eth/quit-sponsor Skill
1★Turns an AI agent with persistent memory into a quit-smoking sponsor. Use when a person asks for help quitting smoking (cigarettes or other smoked tobacco), announces they are quitting, reports a craving, a slip, or a relapse, goes silent mid-quit, or asks the agent to witness and track a quit. Provides evidence-based protocols (immediate execution of the quit decision, urge surfing, slip attribution coaching, withdrawal timelines, nutrition and alcohol rules, NRT guidance, a two-year aftercare cadence) plus a sponsor decision tree with an order-of-operations for colliding rules, a three-clause contract, purge ritual, graded live-crisis ladder for a pack already in hand, wave protocol, slip and post-relapse protocols, recurrence escalation, silence protocol, a Ulysses pact, a red-flag medical playbook, high-risk situation mapping, if-then plans, and a timestamped logbook. Includes a low-verbal client mode and an optional module for cannabis co-use and tobacco-mixed joints. Not a medical device.
The same file is in 1 other repository
Paldom/skillskit/skills/add-skill Skill
1★ repoAuthors or improves an Agent Skill in the current repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, benchmark. Use when the user asks to create, add, write, refine, fix, or benchmark a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repo (create-skill-repo) or distilling research packs (skill-from-research).
639happy/cto-skill/ctoskill Skill
1★ repo帮助不会编程或刚开始 Vibe Coding 的用户,把软件想法问清楚,提前发现真正需要处理的风险,再把确认好的内容交给 Superpowers 完成设计和开发计划。仅在用户明确要求使用 CTO Skill 或 ctoskill 时使用;不要自动开始开发。
cskwork/handoff-spec-kit/skills/handoff-spec Skill
no license1★ repo기획-개발 핸드오프 기획서를 표준 형식(12개 섹션, 간이/전체 경로)으로 인터뷰하여 작성하거나, 작성된 기획서에서 명확화 질문 추출과 Jira 티켓 분할을 수행한다. Use when 사용자가 기능 기획서·핸드오프 문서·스펙 작성을 요청할 때, 스펙을 티켓으로 분할할 때, 기획서 리뷰·명확화를 요청할 때, 또는 handoff-spec을 언급할 때.
wahyujhoo17/crypto-scanner Skill
1★Scan Binance crypto markets for MA7/MA25 crossovers (Golden Cross / Death Cross), RSI momentum, volume spikes, and support/resistance levels. Generates trade setups with precise Entry, TP1, TP2, SL, and Risk:Reward ratio. Use when user asks to scan crypto markets, check pair technical analysis, look for MA crossovers, or evaluate trading setups.
hewieextracellular787/humanize-ai-writing/humanize-ai-writing Skill
1★ repoForce any writing to follow human patterns and strip every known sign of AI-generated text ("AI slop"). Use whenever producing or editing prose that will be read by a person, articles, blog posts, emails, captions, essays, documentation, social copy, reports, and whenever the user says "humanize this", "make it sound human", "remove AI slop", "doesn't sound like AI", "sounds robotic", or "rewrite this naturally". Apply this as a mandatory final pass on any long-form prose before delivering it.
The same file is in 1 other repository
answersamir/codebase-hygiene/skills/duplication-review Skill
1★ repoUse when reviewing a pull request or working diff to catch duplication the change introduces. Checks each new function against existing equivalents in the repo, flags copy-paste blocks inside the diff, and measures whether the new code connects to the existing codebase at all. Trigger on "review this PR for duplication", before merging, or as a pre-merge gate.
novoicefire/talkmap/plugins/talkmap/skills/talkmap Skill
1★ repoTransform a user-AI discussion, brainstorm, research thread, technical review, or decision process into a structured, human-readable, and optionally interactive HTML knowledge map. Use when the user asks to organize prior discussion, create a decision document, summarize a design process, turn ideas into a visual document, preserve rationale and trade-offs, or replace a Markdown-style specification with a more explorable format. Supports product, engineering, business, research, education, operations, planning, and other domains.
k-telux/SciReviewWriter/i18n/ja Skill
1★ repo科学レビュー、学位審査用レビュー、論文形式の原稿を、ノート、PDF、BibTeX、LaTeX、DOCX、図表、査読コメントから計画・執筆・改訂・監査・配布するための証拠ゲート型ワークフローです。機構中心、引用追跡、全ページの視覚検証、プライバシー保護、不確実性と競合解釈の明示が必要な作業に使用します。
himanshi-28/coding-agent-skills/skills/debug-with-evidence Skill
1★ repoExplicit-invocation workflow for systematic debugging that reproduces failures, forms falsifiable hypotheses, collects runtime evidence, proves root causes, adds regression tests, and verifies targeted fixes. Use only when the user directly invokes the debug-with-evidence skill.
cmflynn/crontab-edit/skills/crontab-edit Skill
1★ repoEdit, install, replace, or restore a user crontab from the command line without silently wiping it. Use whenever the task touches `crontab` — "restore my crontab", "install this crontab", "add a cron job", or editing a crontab backup file.
zztimur/skills-to-pay-the-bills/fbar-threshold-check Skill
1★ repoCheck the $10,000 FBAR threshold from foreign account statements. Use for reviewed preflight handoffs, daily ledgers, multi-account aggregation, and year-end FX conversion.
v60samurai/agent-skills/skills/workflow/prompt-compile Skill
1★ repoCompile a high-quality task brief before executing a medium-or-larger task, then execute against it and verify. Pairs with the prompt-compile-gate hook for deterministic triggering; define-do-verify in one pass.
ravipalwe/designos/skills/designos Skill
1★ repoDesignOS — a complete design operating system that takes a product from raw idea to dev-ready design through five gated phases: Brief → Direction → Design System → Screens → Handoff. Built for designers and founders who want senior-level craft, not template output: taste calibration, distinctive art direction with anti-generic safeguards, OKLCH-based perceptually-even color systems, computed contrast verification (WCAG 2.1 + APCA via bundled script), a multi-pass self-critique protocol before every review, and self-contained HTML artifacts that open straight from disk. Every phase writes numbered artifacts into `design/` and `design/STATE.md` tracks progress so any session resumes exactly where the last stopped. Fully standalone. Use when the user says "DesignOS", "design my app end to end", "run the design workflow", "take this idea to a full design", "redesign this product", or wants a complete design process rather than one isolated artifact.
bigjoecoding/smb-acquisition-diligence Skill
no license1★Guides due diligence for buying or evaluating a small business (roughly under $5M in revenue) — normalizes Seller's Discretionary Earnings (SDE) from a P&L or tax return, flags red flags in the seller's financials and add-backs, estimates a defensible valuation range, and runs a phased due diligence checklist. Use when a user is screening a business-for-sale listing or CIM, calculating SDE / add-backs / owner benefit, sanity-checking a broker's asking price, prepping a due diligence document request list, writing an LOI-stage or post-LOI diligence checklist, or drafting a deal summary memo for a small business acquisition.
LeonardSEO/power-platform-skills-codex/plugins/canvas-apps/skills/add-data-source Skill
1★ repoGuide the user to add a data source, connection, or API connector to a Canvas App via Power Apps Studio, then verify and continue. USE WHEN the user asks to add a data source, add a connection, add an API, add a connector, connect to SharePoint / Dataverse / SQL / Excel / OneDrive / Teams / Office 365, or any similar request to make new data available to the app. DO NOT USE WHEN the user is asking to list or describe existing data sources — call list_data_sources or list_apis directly instead.
The same file is in 1 other repository
Nightflight6/open-agent-skills/skills/en/geo-content-optimizer Skill
1★ repoCreate, optimize, or audit evidence-backed content for generative answer and search experiences by improving answerability, claim traceability, entity clarity, and original value. Use for GEO content briefs, answer maps, citation-ready claim review, answer-surface-informed optimization, or GEO audits. Do not use as the primary skill for deep question research, ordinary SEO planning, technical SEO implementation, rank or visibility monitoring, generic article editing, fact checking alone, keyword research, or answering a single question.
kingtmn/ai-application-design-review/skills/ai-application-design-review Skill
1★ repoPre-implementation kill-criteria review for AI apps, Agents, or Workflows. Finds at most two blocking failure modes and designs one falsifiable minimal experiment. When multiple independent blockers compete, applies conditional decision-priority scoring and experiment-coverage declarations. Use when the user invokes /ai-application-design-review, or asks for design-stage blocking-risk / kill-criteria review before building. Do not use for code review, runtime debugging, UI taste, pure brainstorming, model-picker advice alone, or full system redesign.
ponponusa/agent-context-maintainer Skill
1★Create, update, and validate repository-local AI agent context files such as AGENTS.md, .agents/core.md, .agents/routing.md, provider-specific profiles, and task SKILL.md routing. Use when an AI coding agent (Codex, Claude Code, Gemini, Copilot, Cursor, or others) is asked to make AGENTS.md or SKILL instructions self-maintaining, inspect the current path and generate optimal agent context for it, or keep agent instructions synchronized with the repository's actual structure.
Mahermenix/vault-sync Skill
1★Use at the end of any agent coding session to reflect what happened back into the Obsidian vault. Reads the session transcript and git history, extracts decisions, tasks, projects, people, research, and other entities, then creates new vault pages or updates existing ones using the right templates and folder placement. Maintains the vault's zero-orphans principle by updating index files and adding wikilinks. Use whenever the user mentions ending a session, wrapping up, syncing to vault, logging the session, updating Obsidian, capturing what we did, saving session notes, or says "/vault-sync", "/end-session", "/log-session" — and after long working sessions even if they don't explicitly ask. Supports planning mode (capture what they intend to do) and work-log mode (capture what actually happened); work-log is the default.
mohamedzhioua/proofguard/deferred/api-contract-guard/skill Skill
1★ repoBlocks a breaking change to a published contract — a REST/RPC/GraphQL endpoint or its request/response fields, an event/webhook payload schema, or a public library signature — made IN PLACE (renamed/removed/retyped field, newly required param, changed status code/error shape, tightened validation) instead of via expand-contract (add the new shape alongside the old, migrate consumers, deprecate with a window, remove later) and/or a version bump. Best used reactively before changing any endpoint, event schema, or exported function signature with existing consumers. Use when the user says "rename this field", "change the response shape", "make this param required", "update the API", "change the payload", "return a different status code", or after an agent edits a contract other code already calls. DO NOT USE for doc sync (docs-drift-guard), diff scope (clean-diff-guard), or the done-claim (evidence-before-done); this guard is specifically about not breaking existing consumers of a published contract.
shinpr/grok-workflows/plugins/claude-to-grok/skills/claude-to-grok Skill
1★ repoMaps Claude Code tool, agent, and progress-tracking identifiers to Grok runtime equivalents while preserving claude-code-workflows (dev-workflows*) execution semantics. Use when running dev-workflows* on Grok, including recipe-* orchestration that needs CC→Grok translation.
PlayWithAndyJin/modernduang-skills/skills/modernduang-theme-custom Skill
no license1★ repoHelp users modify Modern Duang theme source files. Use this skill whenever the user wants to customize source code, edit templates, change styles, modify scripts, or understand the purpose of specific theme files. Also trigger when the user asks "which file controls X" or wants to add/change theme behavior beyond config.
tersignhq/skills/tersign-evidence Skill
1★ repoProduce, verify, and submit counter-signed transaction evidence via Tersign — the neutral evidence layer for agent commerce. Use this skill when an agent needs dispute-ready evidence for any arbitration venue (Internet Court, Kleros, UMA), needs to verify a counterparty's x402 receipt or action record without trusting them, needs to issue counter-signed receipts as a seller, or needs a tamper-evident audit trail for compliance (EU AI Act Article 50 disclosures, audit-log exports). Trigger on: evidence, evidence envelope, counter-signed receipt, receipt verification, verify a receipt, hash chain, chain of custody, tamper-evident record, audit trail, dispute evidence, evidence submission, exhibit, ERC-1497 evidence, evidenceDefs, proof of delivery, proof of transaction, receipt digest, ledger verification, x402 receipt, offer-receipt, action record, agent disclosure record, Article 50 evidence, compliance export. Also trigger when a dispute is being filed or responded to and the agent holds (or its counterparty claims) transaction records — the envelope turns self-submitted testimony into an independently verifiable exhibit. Do NOT trigger for payment execution itself (use a payments skill) or for choosing an arbitration venue (use the dispute-layer skills); this skill supplies the evidence those layers consume.
zeroatflops/flops-skill Skill
1★Look up and cite verifiable GPU/compute rental reference prices (H100, A100, H200, and more; spot, on-demand, or DePIN markets) from the public FLOPS Index — no API key required. Use when the user asks what a GPU or accelerator costs to rent, wants the cheapest option for a given chip, wants to compare spot vs on-demand vs decentralized compute rates, or wants to fact-check / cite a compute price with a source they can independently verify. Keywords: GPU price, H100 cost, A100 rental, compute pricing, spot price, on-demand, DePIN, GPU-hour, accelerator rental, FLOPS index.
The same file is in 2 other repositories
3bsalam-1/architecture-extractor Skill
1★Analyze a codebase and generate a highly detailed `docs/engineering_constitution.md` that captures its engineering DNA — architecture philosophy, coding standards, patterns, conventions, and structural rules — in a reusable form that can be applied to a completely different product. Use whenever the user asks for: an engineering constitution, architecture extraction, coding standards document, project engineering handbook, codebase DNA, reusable architecture template, "extract the patterns from this codebase", or "document how this project is built". Also trigger when the user wants to start a new project "in the same style as" an existing one, or wants to capture the implicit conventions of a repo before a major refactor or team handoff. This skill is about HOW the project is built, never WHAT it does.
khaichonggg/prove-before-done Skill
1★Evidence-first Agent Skill that verifies work before reporting completion.
The same file is in 1 other repository
arlegotin/pythurion/skills/pythurion Skill
no license1★ repoImproves correctness, maintainability, typing, reliability, testability, and measured performance for Python code, optimized for Python 3.12 and newer. Use whenever a task reads, writes, explains, reviews, refactors, debugs, tests, designs, optimizes, profiles, or benchmarks Python—including source files, snippets, code blocks, tests, notebooks, scripts, packaging, project configuration, or workload latency, throughput, CPU, memory, allocation, startup, and I/O—even when quality or performance guidance is not requested. Do not use when Python code, Python runtime behavior, and Python project configuration are all incidental to the task.
igapyon/miku-media-proc-skills/skills/miku-media-proc Skill
1★ repoUse when the user explicitly asks for miku-media-proc or needs a repository-local skill for media processing workflows, including video, audio, image, subtitle, metadata, and batch media preparation tasks.
Pavelgq/weekly-rpg-retro Skill
1★Run a weekly RPG-style reflection ritual: the user is a character in their own campaign, Claude is the Game Master. Use whenever the user asks to do a weekly reflection or retrospective, review their week, update their character sheet, fight their "bosses", set up the campaign for the first time, or run a quarterly review. Also use when the user mentions this campaign by its name from profile.md. Triggered manually — never run automatically or on a schedule.
Dafenxz0/statecraft-skill/skills/complete-ui-states Skill
1★ repoBuild and audit complete, recoverable UI behavior beyond the happy path. Use when creating or reviewing user-facing web interfaces that load remote data, submit forms, search, upload, authenticate, request permissions, check out, autosave, reconcile version conflicts, resume long-running work, or run asynchronous actions; when asked to add loading, empty, error, offline, retry, partial-data, stale-data, conflict, or success states; or when preparing an interface for real use. Pair with visual-design skills and preserve their visual direction while owning state behavior, recovery, accessibility, continuity, and verification. Do not use for purely static pages or backend-only reliability work with no changing user-facing state.
Odinary-AI/research-writing-skill/plugins/research-writing/skills/research-writing Skill
1★ repoUse when working on academic research writing: research positioning, paper drafting or revision, writing-quality audits, target-venue adaptation, simulated peer review, manuscript assembly, reviewer responses, pre-submission checks, or asynchronous paper-readiness workflows. Use for tasks involving academic papers, abstracts, introductions, claims, evidence, citations, venue fit, rebuttals, response letters, LaTeX/PDF manuscript preparation, and publication-risk review.
41Yr9/vibeplus/skills/code-review-skill Skill
1★ repoProvides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Python, Django, FastAPI, Go, C#/.NET, Kotlin, Swift, NestJS, C/C++, Zig, CSS/Less/Sass, Qt, and more. Covers architecture review, performance review, security audit, code quality anti-patterns, and common bugs across all ecosystems. Use when: reviewing pull requests, conducting PR reviews, code review, reviewing code changes, establishing review standards, mentoring developers, architecture reviews, security audits, performance reviews, checking code quality, finding bugs, giving feedback on code.
enocgit/sdlc-kit/skills/address-review Skill
1★ repoTriages review comments on an open pull request — from humans and from bots (CodeRabbit, bugbot, Codex, Sourcery, …) — and addresses them. Reads every comment, verifies and challenges each one against the code, the frozen contract, and the ADRs to weed out false positives, then auto-fixes the trivial and gates the rest behind a plan. Manually invoked, standalone — not tied to a pipeline stage. Use when the user says "address the PR reviews", "go through CodeRabbit's comments", "handle the bugbot findings", "handle the codex findings" or "respond to the review".
jahfaliabdulrahman-dev/hermes-skills/skills/flutter-android-build-system Skill
1★ repoComplete Flutter Android build system knowledge — Gradle configuration, namespace, applicationId, AGP versions, ProGuard/R8, Isar compatibility, signing, CI/CD. Merged from developer.android.com/build + isar.dev + docs.flutter.dev/deployment/android. MoA-audited 2026-07-06.
F1n1k/kimi-webbridge-skill Skill
1★Control the user's real Chrome or Edge browser through the local Kimi WebBridge service. Use for browser navigation, opening or managing tabs, reading pages, clicking, filling forms, taking screenshots, saving PDFs, uploading files, inspecting network traffic, or automating websites with the user's existing browser sessions. Trigger whenever the user mentions Kimi WebBridge or asks to interact with a real browser through it.
FlewolfXY/apple-health-analyst Skill
1★Turns the agent into a personal health-data analyst for Apple Health exports. Use when the user mentions an Apple Health / HealthKit export (export.xml), wants their Apple Watch or iPhone health data analyzed, asks questions about their own sleep, heart rate, HRV, steps, fitness, fatigue or recovery trends, wants to know whether a habit change or intervention actually worked, or wants to design a self-experiment (n-of-1) on their own health data.
Rebel028/AgentSkills.Sdk/skills/author-skill-docs Skill
1★ repoAuthor or draft the skill docs a NuGet package feeds into AgentSkills.Sdk — a Skill Body plus reference docs. Use when a Maintainer asks to author, draft, or write agent skill docs for their package, or when chained from the setup-agentskills-sdk skill because the repo has no markdown docs to wire up.
wendelcastro/fluxo-engenharia-ia/skills/blindar Skill
no license1★ repoBlinda o código contra vulnerabilidades. Use quando o usuário estiver lidando com entrada de usuário, autenticação, armazenamento de dados sensíveis ou integrações externas. Use quando construir qualquer funcionalidade que aceite dados não confiáveis, gerencie sessões ou interaja com serviços de terceiros.
leksman/ai-security-guard Skill
1★Harden and audit an app's AI/LLM features against prompt injection, jailbreaks, privilege escalation, action-marker/card forgery, PII and cross-tenant leakage, and media/vision abuse. Use when adding, reviewing, or securing any feature that sends user-controlled text, voice transcripts, or images to an LLM. Installs runtime guards (injection detection, context sanitization, marker stripping), wires blocked-attack alerting (Sentry or any sink), and can run a multi-agent security audit against the codebase.
weitongxucc-dev/design-low-fi-prototypes/skills/design-low-fi-prototypes Skill
1★ repoTurn vague or complete product requirements into beginner-friendly, cross-agent low-fidelity learning boards and genuinely interactive prototypes for Web, native apps, WeChat mini programs, and desktop clients. Use for wireframes, page flows, MVP or full-project screen planning, pre-coding UI design, platform pattern comparison, clickable low-fi prototypes, UI state coverage, dimension annotations, modular multi-page products, tracked revisions, impact analysis, visible live Agent-to-HTML changes, or safely revising an existing wireframe package. Produce typed vendor-neutral specs, portable HTML artifacts, managed change records, and implementation handoff without moving into high-fidelity branding or production code.
ralfyishere/piensalo/micro-skills/audience-constraint-check Skill
1★ repoCheck a deliverable against its actual consumer: who reads it, what they do next, what format and register they need, and what they will assert downstream on its basis. Activate when the deliverable has a named audience beyond the requester, or its text will be forwarded, announced, or acted on by someone absent from the conversation.