The catalog
608,119 rows, by stacks then stars
vivekmaru/repo-atlas Skill
0★Create polished repository onboarding documentation as static HTML. Use when a user asks an agent to explore a repo, explain architecture, produce diagrams, render existing Markdown/spec docs into browser-friendly pages, build a glossary of acronyms/domain terms, summarize historical decisions from docs such as .kiro/, or make a new-engineer repo atlas/code map.
aigeekops/shared-obsidian-brain Skill
no license0★把任意 AI agent 经 MCP 接入 Obsidian vault,搭建本地优先的「第二大脑」 (Karpathy LLM Wiki 范式)。触发词:搭第二大脑 / second brain / LLM Wiki / 接入 Obsidian / 知识库。
HamedMP/secretbroker/skills/secretbroker Skill
0★ repoKeeps API keys, tokens, passwords, credential paths, and other secrets out of AI conversations while granting explicitly named environment variables to local child commands. Use when a local CLI command needs sensitive credentials or when a user is about to paste a secret into chat.
sahildave/skilltopia/.agents/skills/ai-image-generation Skill
0★ repoGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image
aqzi/SelectionBridge/skills/selection-bridge Skill
no license0★ repoResolve references such as "this", "this selection", "the selected code", "what I highlighted", or "the current VS Code selection" when Codex is running in a terminal beside a local or remote VS Code workspace. Use this skill before interpreting deictic references to editor selections; it reads the file/range pointer that the co-located Selection Bridge VS Code extension publishes to a registry file, then reads the referenced saved file content from disk if needed.
alexclymo/claude-tracker-skills/skills/tracker-audit Skill
0★ repoUse when the user wants to audit the task tracker, clean up the task docs, or says the docs feel stale, out of date, or contradictory — triggers like "audit the task tracker", "clean up the task docs", "the docs feel stale", "reconcile the tracker", "health check the tracker", "do the tracker docs still match reality". Sweeps the whole repo — tracker/, CLAUDE.md, architecture and navigation docs, and code comments — for stale and contradictory claims, reports them ranked by how likely each is to cause a wrong agent decision, and fixes them only on explicit approval. Manages project task *documents* on disk, not Claude Code's in-session task tools (TaskCreate/TaskList) — those are scoped to one conversation and never persist; this skill audits the durable, git-tracked record instead.
keykovar/skill-fe-code-review/skills/fe-code-review Skill
0★ repoReview frontend or hybrid app code changes. Use when the user asks to review a current diff, uncommitted or staged changes, a commit, branch range, PR, risky feature, release change, naming, file placement, simplification, regression risk, frontend-specific risk, or fixes made after a previous review. Default to read-only review. Use Quick Review for normal changes, Deep Review for large or risky changes, and Fix Review to verify previous findings and detect regressions introduced by their fixes. Detect React, Vue, TypeScript, JavaScript, and Hybrid/WebView projects and load only the relevant references.
junit/module-quality-reviewer Skill
0★Use when the user asks to audit or 全面审查 a substantial code module or cross-file feature, evaluate design and implementation quality, assess release readiness, distinguish confirmed defects from uncertain risks, or verify previously identified high-risk findings.
cekrauseee/harness/skills/harness-artifact Skill
23 days old0★ repoCreate, update, index, and validate final user-facing HTML visualizations in docs/artifacts/. Use when a project needs a versioned architecture map, flow, comparison, report, or other inspectable HTML explanation rather than application UI or temporary agent output.
BaoBao1996121/crazy-harness/.agents/skills/evidence-research Skill
0★ repoCollect independent browser evidence and produce a machine-validated cited report.
murphy977/3d-eyes/skill Skill
0★ repoUse when the user reports a 3D model or scene looking wrong (black/invisible/gigantic/untextured model, holes, weird shading), asks to check or QA a 3D file (GLB, GLTF, OBJ, PLY, STL, .splat), works with Gaussian splats, or generates 3D assets with AI and wants them verified. Requires the 3d-eyes MCP server.
caoproAI/service-pricing-advisor-cn Skill
no license0★面向中国自由职业者、顾问、教练、设计师、摄影剪辑师、代运营、个人IP、实体店和小型服务团队的服务报价诊断 Skill。用户准备给客户报价、担心报低了亏钱、报高了没依据、客户要求打折,或需要整理基础版/标准版/高配版方案时使用。根据用户提供的交付范围、预计工时、人工成本、直接成本、修改次数、加急、授权、税费、平台费和目标利润,先算不亏底价,再给有依据的可谈区间、三档方案、报价单骨架和可直接发给客户的话术;资料不足时一次只问一个关键问题,不编造市场价,不保证客户接受或成交。
yuanGao0816/prompt-rail Skill
no license0★Optimize prompts with a measured train/test dual-gate loop that resists memorizing eval cases. Use when the user wants to write or improve a prompt, tune a system prompt, build prompt evals with holdout, prevent prompt overfitting/背题, run prompt-rail, or iterate intent-classification prompts with separate train and test suites. Fork of prompt-smith plus anti-overfit rails.
shihchengwei-lab/session-analytics Skill
0★Weekly self-improvement loop for AI coding agents, plus ad-hoc usage analytics. Each agent analyzes its OWN tool's local session logs over the last 7 days (Claude Code via /insights artifacts, Codex via ~/.codex/sessions, others via their logs), reports success rates, friction patterns, stalled sessions, tool/token usage — and in a weekly review proposes evidence-tied workflow improvements: a small capped rules block in the tool's config (diff shown, user approves, block self-refactors instead of accumulating), mechanical harness fixes (hooks/env/permissions) preferred over prose rules, and skill/config hygiene both directions (hot paths reinforced, installed-but-never-invoked skills flagged for disabling; rule evidence re-validated across model changes). Trigger on "weekly review", "improve my workflow", "分析我的 session/使用紀錄", "which sessions failed", "my success rate", "compare my experiment runs", "哪些 skill 沒在用/停用沒用的 skill", or bare invocation (= 7-day overview). Reads local data only. Not for regenerating the official /insights report, or deep-reading one full transcript (expensive — see Cost rules).
RyanKershawWhittle/agentic-splunk-upgrade-orchestrator/skill Skill
0★ repoSplunk Enterprise on-prem upgrade skill for the forwarding/management tier - deployment servers, agent managers, intermediate forwarders, heavy forwarders (incl. DB Connect hosts). Full lifecycle - version-path planning, compatibility gates, pre-checks, per-component runbooks, post-checks, soak, rollback. TRIGGER when the user plans or executes a Splunk version upgrade, patches a forwarder/DS/HF, asks about upgrade order, KV store migration, DB Connect upgrade impact, or rollback. SKIP for app deployment (use splunk skill / splunk-deploy-engineer) and for Splunk Cloud stack upgrades (Splunk-managed).
mikeqwe/system-reality-alignment-plugin/plugins/system-reality-alignment/skills/align-system Skill
0★ repoDesign, review, plan, repair, implement, operate, or evaluate software and socio-technical systems so observations, data, decisions, actions, and outcomes remain traceable and aligned with reality. Use for architecture and system design, data-quality or state-model problems, observability and feedback loops, incident remediation, migrations, domain contracts, invariants, lineage, reconciliation, decision auditability, adaptive operations, and controlled evaluation of an intervention or this plugin. Do not use for isolated cosmetic edits or local syntax changes with no system-behavior implications.
proluct/skill-press/skills/skill-press-polish Skill
0★ repoDiagnose and improve an EXISTING Claude Code skill with a diagnose, fix, re-diagnose pass, whether skill-press built it or not. Use when the user says "polish this skill", "improve my X skill", "this skill keeps misfiring or confusing the agent", "clean up this SKILL.md", or after a skill-press run offers a polish pass. Not for creating new skills (use skill-press) and not for plugin-managed skills, which cannot be edited in place.
CodingCossack/writing-claude-design-prompts Skill
0★Use when turning product notes, briefs, specifications, or mixed mission packs into prompts for Claude Opus, Fable, or another design-capable Claude model whose primary result is a visual artefact, frontend, redesign, prototype, design system, or image-to-code implementation.
mintandkiwi/visual-task-brief Skill
0★Create concise, self-contained visual HTML task briefs and completed-delivery reports from application plans, project requirements, PRDs, build plans, implementation results, handoff notes, release summaries, or long Markdown documents. Use whenever the user asks to 出具任务书, 写任务书, 可视化任务书, 图文任务书, 项目任务说明, 交付书, 交付报告, 交付成果, 完成总结, 可视化交付, implementation brief, build brief, delivery report, handoff report, release summary, or asks to turn technical planning or completed work into numbered diagrams, connected flows, artifact maps, verification charts, and plain-language terminology. Always use for task-book and completed-delivery requests unless the user explicitly requests text-only output.
sonu07-star/agent-handoff-skill/skills/agent-handoff Skill
0★ repoCreate, validate, and resume structured handoff documents that let another AI agent continue work without hidden conversation context. Use when pausing or transferring unfinished work, approaching a context limit, switching agents or sessions, reporting a blocker, recovering after interruption, resuming from HANDOFF.md, or auditing a handoff for evidence, actionable next steps, secret leakage, and unsupported completion claims.
holdenjrussell/ms-clarity-cli/skills/microsoft-clarity Skill
no license0★ repoAnalyze Microsoft Clarity analytics, session recordings, heatmaps, rage clicks, dead clicks, scroll depth, JavaScript errors, and landing-page UX friction. Use for Clarity MCP setup, warehouse syncs, recording triage, behavior analysis, CRO investigations, or evidence-backed site recommendations for any client or brand.
hijabcantic-dotcom/app-review-opportunity-research-template/app-review-evidence-research Skill
no license0★ repoTurn public App Store and Google Play reviews into an evidence brief, product hypothesis, and customer-interview questions. Use when evaluating a competitor, testing a mobile-app idea, preparing an ASO or product discovery brief, or deciding what to investigate before building.
Syncfusion aspnetmvc ai assistview
syncfusion/aspnetmvc-ui-components-skills/skills/syncfusion-aspnetmvc-ai-assistview Skill
no license0★ repoImplement the Syncfusion ASP.NET MVC AI AssistView component — a conversational AI chat interface with prompt/response rendering, prompt suggestions, custom views, toolbar customization, file attachments, speech-to-text, AI backend integrations (Azure OpenAI, Gemini, Ollama, LiteLLM), generative UI with interactive tools, Chain of Thoughts reasoning visualization and text-to-speech audio playback. Use this skill when building AI chat UIs, integrating LLM backends, configuring assistant toolbars, customizing templates, rendering dynamic UI components, or handling voice input/output in ASP.NET MVC applications.
ONEIRO-codes/video-digest Skill
0★Fetch a video's transcript via the Supadata API and deliver a digest - summary, key points, action items - plus 3 personalized follow-up questions drawn from the user's memory files. Use this skill whenever the user shares a video URL (YouTube, TikTok, Instagram Reel, X/Twitter, Facebook, or a direct video/audio file link) and wants to know what it says, get a summary, extract takeaways or action items, or asks things like "summarize this video", "what's this video about", "get the transcript of", "pull the key points from this talk", or pastes a video link with minimal context. Also use it when the user asks to transcribe any video or audio URL, even without asking for a summary.
ebal/AI-Skills/bash-scripting Skill
no license0★ repoGuide and patterns for writing robust Bash scripts. Use when the user says "write a bash script", "shell script", "bash script", "write a script", "bash best practices", or needs help with Bash/shell scripting. Covers script structure, error handling, string manipulation, arrays, arithmetic, conditionals, loops, functions, traps, debugging, and common idioms distilled from the Advanced Bash-Scripting Guide.
nklabs-dev/oraculo/hermes Skill
0★ repoRoute repetitive tasks through ORÁCULO so they graduate into free .py scripts; always check oraculo status before solving an already-compiled task with the LLM
guoHaoTNT/craft-image-prompts Skill
0★创建、补全、优化和精炼文生图提示词,并从用户有权使用的参考图片中分析和迁移获准的视觉特征。用于从主题或零散信息建立视觉方向、诊断冲突、生成结构化方案与可复制提示词,或在不复制具体人物、商标、水印和私人信息的前提下融合参考图风格。
mkantautas/tallymeter-skill Skill
0★Track billable time in Tallymeter (tallymeter.com) — start/stop timers, log completed work, fix entries, and check unbilled totals. Use when the user asks to track time, log hours or worked time, start/stop/check a timer, fix a logged entry's description or project, see what's unbilled, or prepare data for a client invoice.
InitusNovus/pcan-validation-skill Skill
0★Use when validating a two-channel PCAN or PCANBasic-compatible CAN/CAN-FD interface. Provides reproducible canary, functional matrix, FIFO-boundary, arbitration, timestamp, reopen, recovery, and checkpointed soak workflows with strict integrity accounting.
NolanCassidy/auto-tinker/skills/auto-tinker-automate Skill
0★ repoConfigure, inspect, or revise Auto-Tinker scheduler policy and exact task prompts without creating a second state system. Use when changing cadence, daily limits, scheduled-task scope, pause behavior, or scheduler handoffs; this skill configures automation but does not perform the scheduled workload or mutate GitHub.
SubliminalCoding/build-it-out/skills/build-it-out Skill
0★ repoRun a hardened coordinator-worker-reviewer build board for substantial implementation, hardening, migration, or decompose-build-review-iterate work. Use when a user says "build it out", "use the workflow", "run the board/swarm", requests a hardening pass, or wants independent orchestration and review. Uses a read-mostly Claude coordinator, exact-pane Codex workers, deterministic Git/scope/test gates, and a fresh capability-restricted Claude reviewer with bounded repairs. Do not use for a quick conversational answer or a trivial single-file edit.
Optimize claude fable 5 prompts
IchenDEV/claude-fable-5-prompt-optimizer/plugins/claude-fable-5-prompt-optimizer/skills/optimize-claude-fable-5-prompts Skill
0★ repoClarify, audit, and rewrite rough or existing prompts for Claude Fable 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt for Claude Fable 5, including requests phrased as Fable or Fabel prompt optimization, Fable/Fabel 提示词优化, or when an underspecified idea needs guided clarification before a copy-ready prompt. Ask only for missing information that would materially change the result; otherwise preserve intent and produce a lean, context-rich prompt with explicit outcomes, boundaries, evidence, output requirements, and completion criteria.
The same file is in 1 other repository
monsterxz9/image-to-manuscript-vision Skill
0★使用模型原生视觉能力,把书页照片、扫描页、截图或成组图片逐页转写为可编辑文稿;适用于“提取图片文字、整理成文稿、图片转 TXT/Markdown/Word、逐页抄录”等任务。默认禁止调用 OCR、Tesseract、PaddleOCR、EasyOCR、ocrmypdf、云端文字识别或其他自动识别引擎;仅在用户明确同意后才可改用 OCR。不适用于用户只要摘要、翻译或图片内容解释的情况。
edycutjong/cuporacle-mcp/skills/cuporacle Skill
0★ repoUse CupOracle to answer FIFA World Cup 2026 questions (fixtures, live scores, consensus odds, knockout bracket) and to buy a vetted, CLV-audited edge that the agent pays for ITSELF via x402 on Injective — under a spend cap, always citing the on-chain receipt. Invoke when the user asks about a World Cup match, "who's playing / who's through", "what are the odds", or "is it worth a bet".
guoHaoTNT/merge-spreadsheets Skill
0★在合并多个 Excel、XLS、CSV 或 TSV 前先确认业务关系、核验关联键与基数,再生成可审计的 Excel 和可选的自包含离线 HTML。用于多仓库存对齐、订单客户商品连接、跨来源字段补全、差异清单和动态多 Sheet 交付;重视前导零、重复记录、多对多阻断、隐私与真实验证。
jjromero88/jjromero-skills-dev/angular-design-system Skill
0★ repoSistema de diseño visual para apps Angular — monocromático (inspirado en la documentación de OpenAI y en el estilo actual de shadcn), escala de grises invertida por tema, dark mode sin flash, tipografía Inter+JetBrains Mono, componentes (botones/cards/alerts/modales/tablas/notificaciones/KPIs/charts) construidos sobre tokens CSS. Úsala junto con `angular-feature-architecture` para darle estilo visual a cualquier vista nueva.
mwojtyczka/matillion-to-databricks Skill
0★Guide for migrating Matillion ETL pipelines to Databricks. Trigger when the user wants to migrate Matillion orchestration (*.orch.yaml) and transformation (*.tran.yaml) pipelines to Databricks. Matillion orchestration pipelines become Databricks Jobs; transformation pipelines become Job tasks (SQL task for pure SQL, notebook otherwise), with Lakeflow Declarative Pipelines reserved for incremental/streaming or data-quality needs. Consult the relevant component reference before translating each component.
flowerjvm/flower-action-runtime-guide Skill
0★Use when building, modifying, reviewing, migrating, or testing Java code that uses flower-action-runtime, including ActionProposal and ActionDefinition design, registry/validation/policy/approval/pre-execution controls, tenant-scoped duplicate handling, explicit failure retry policy, synchronous/async/deferred executor selection, ActionRun and RunStore persistence, JDBC CAS concurrency, completion/cancellation/recovery, Flower workflow or event-loop backends, and 0.1/0.2-to-0.3 migration.
elliot-rosen/adversarial-review/skills/adversarial-review Skill
0★ repoAdversarial multi-agent debate for PR reviews, architectural reviews, and feature reviews. Committed opposing agents attack each other's cases across bounded rounds; only evidence-backed conclusions survive to a single ruthless verdict. Use when the user invokes $adversarial-review, asks for an adversarial, red-team, or debate review, or wants a PR, architecture, or feature judged brutally on evidence, best practices, and current data without nitpicking.
yusufaf/spicetify-agent-skills/skills/spicetify-live-test Skill
0★ repoUse when testing, debugging, or verifying a Spicetify extension change in the running Spotify desktop client — reading its console, running JS against Spicetify Platform APIs, inspecting or mutating extension localStorage, hot-reloading after an edit, or confirming a fix actually works in the client rather than only passing a syntax check. NOT for Spotify Web API work (playback/playlists via OAuth), which is a different layer.
Juliusolsson05/staged-decomposition Skill
0★Forces a written stage decomposition before any implementation code is written for a complex feature, and requires tests to be built from recorded real data rather than imagined cases. Use when implementing or refactoring a non-trivial feature in a large codebase (roughly 35k+ LOC), when a previous attempt got to 40-70% and stalled, when bugs are being fixed by adding conditionals to existing code, when multiple data sources or providers must agree on one output, when a feature is spread across far more files than it should be, or when the user asks to redesign, untangle, or isolate a subsystem.
YMIR777/vibecoding-prompt-workflow/skills/prompt-first-workflow Skill
no license0★ repoApply first-principles task framing with a bounded read-only preflight before substantive work. Use for projects, changes, debugging, reviews, research, writing, design, and other tasks where goals, context, constraints, approval boundaries, acceptance criteria, or output requirements need to be explicit. Show an executable task definition before substantive work on complex, open-ended, state-changing, or decision-bearing requests; do not force ceremonial rewrites for simple, already-clear answers or low-risk actions.
Chulinuwu/skillloom/skills/autonomous-learning Skill
0★ repoReview completed Claude Code, Codex, or compatible agent work for durable declarative knowledge and reusable procedural knowledge. In Skillloom Hermes mode, curate one bounded second-brain outcome only after a checkpointed meaningful delta and policy-promote only validated safe skill candidates. Use when explicitly invoked, when a Stop hook requests learning review, when an invoked host completes non-trivial work, or when repeated corrections reveal a stable workflow.
mrcha033/skills/plugins/advisor-review/skills/advisor-review Skill
no license0★ repoMrCha Skills — portable Agent Skills for ChatGPT, Codex, and compatible agents
neilchen2000-pixel/agent-skill-stack/skills/agent-skill-stack Skill
0★ repoFind, evaluate, assemble, and runtime-activate the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use as the primary orchestrator when a request spans multiple replaceable capabilities or asks for a sustained, complete, or end-to-end outcome—even when the user never says “Skill”—and use domain Skills only as downstream specialists. Also use for multi-Skill selection, installed-Skill audits, conflict checks, low recall, indirect helpers such as humanizers or compliance checks, and project routing with dependency closure. Search local Skills, registries, GitHub, and OpenCLI; compare adoption, verified fit, safety, and overlap; block incomplete handoffs. Do not use for a single bounded action or locating one known/common Skill; use that domain Skill or the generic find-skills workflow.
Sm1te/beyond-the-map Skill
0★Take a consequential project from fuzzy intent to a verified outcome. Use when the user explicitly invokes beyond-the-map or asks for an end-to-end lifecycle spanning unknown discovery, design, consequential decisions, planning, execution, verification, handoff, and retrospective. Do not trigger for factual questions, a single phase already covered by another skill, simple edits, or narrowly scoped fixes with clear acceptance criteria.
pengpeng810/deep-book-guide-skill/skills/deep-book-guide Skill
0★ repoUse when a user provides a book title and wants a deep reading guide, chapter-by-chapter orientation, key cases, verified short quotations, or help preparing to read the complete book.
dariuxas/ncl-skill/skills/nuclei Skill
no license0★ repoComprehensive ProjectDiscovery Nuclei v3 expertise for installing, configuring, running, debugging, and reviewing authorized scans; authoring and validating advanced YAML templates and workflows; and working with HTTP/raw HTTP, payloads, DAST fuzzing, race conditions, unsafe requests, DNS, TCP, file, headless, SSL, WebSocket, WHOIS, JavaScript, code, Flow, matchers, extractors, variables, DSL helpers, Interactsh/OAST, authentication, signing, CI/CD, the hosted Template Editor, and APIs. Use whenever the user mentions Nuclei, nuclei-templates, ProjectDiscovery templates, Nuclei YAML, Interactsh, TemplateMan, Nuclei workflows, Nuclei OAST, or asks to create, fix, optimize, validate, explain, or execute a Nuclei template or scan.
liush2yuxjtu/skill-readme-workflow Skill
0★启发式编排:将一个 skill 产品化为 README 和 GitHub landing page。
d-init-d/d-break-skill Skill
no license0★Universal adversary lab skill that GUARANTEES a fully compromised AI agent demo on every host via Live max-pressure break (B1/B2) plus mandatory Shadow total compromise (B3). Use for jailbreak/red-team presentations, attacker roleplay, agent harm demos, OWASP ASI scenarios, defense-stack pierce, /d-break, "bẻ khóa agent", "jailbreak demo", "agent bị compromise". Educational synthetic lab only.
Amal-David/polyglot/skills/polyglot Skill
0★ repoThis skill should be used when someone wants an educational language-learning phrase, vocabulary practice, pronunciation hints, a Polyglot language-pair selection, or configuration of Polyglot's optional ambient phrase mode.
wangyu16/orz-claude-plugin/skills/orz-markdown Skill
no license0★ repoorz-markdown usage skill. Use this skill whenever you need to render markdown with this parser, write markdown that uses {{...}} custom plugin syntax (mermaid, chart, qrcode, youtube, smiles, toc, span, emoji, attrs, space, yaml, nyml, or their aliases mm/qr/yt/sm/sp/em), use :::container syntax (success/info/warning/danger/spoil/tabs/tab/cols/col/left/right/center), set up a complete HTML page to display parser output, choose or import one of the 12 bundled CSS themes, or create a custom theme stylesheet. Also invoke when asked about .markdown-body class, prepareSources, browser runtime scripts for QR codes or tabs, or any KaTeX math syntax in this project. ALWAYS invoke before editing documents whose headings carry stable block IDs ({{attrs[#blk-...]}}).
smtpfast/smtpfast-skill/plugins/smtpfast/skills/smtpfast Skill
0★ repoSend transactional emails and manage contacts, domains, broadcasts, suppressions, and webhooks through the SMTPfast (smtpfa.st) email API. Use when the user wants to send email via SMTPfast, integrate the smtpfa.st API, wire up transactional email, add SMTPfast to an app or agent, check an email's delivery status, or manage sending domains, contacts, or broadcasts on SMTPfast.
Nick-800/skills/skills/electron-development Skill
no license0★ repoHigh-security and performance-optimized Electron development workflows. Use whenever building, reviewing, extending, or auditing an Electron desktop app — main process, renderer, preload scripts, contextBridge, IPC (ipcMain/ipcRenderer), BrowserWindow config, or packaging with electron-builder/electron-forge. Trigger on any mention of Electron, a desktop app built with Electron, contextIsolation, sandbox mode, preload scripts, IPC bridges, or requests to scaffold/secure/optimize an Electron + TypeScript/React/Vite app. Also trigger when auditing Electron code for security holes (nodeIntegration enabled, disabled contextIsolation, the remote module, missing CSP, unrestricted navigation/window.open) or performance issues (blocking the main process, oversized IPC payloads, listener/memory leaks). Apply the security and performance defaults automatically even if not explicitly requested — they are the non-negotiable baseline, and violating code should be flagged and corrected, not silently written.
caoproAI/account-autopsy-cn Skill
no license0★面向中国自媒体新手、短视频创作者、个人IP、实体店、企业账号和内容团队的账号诊断 Skill。用户提供平台、账号目标、主页截图或介绍、最近3至10条标题、封面、脚本、视频信息与可用数据后,找出没人看、涨粉慢、有流量没客户、更新困难或卖不动的主要死因,引用具体证据,生成五项评分、下一条可发布的完整内容和7天抢救计划。用户询问账号为什么没结果、如何改定位与内容、流量是否错位或怎样恢复断更时使用。
caoproAI/cao-pro-ai-topics Skill
no license0★为抖音、小红书、视频号等内容账号策划、生成、筛选和诊断短视频选题。使用“用户需求→主题→话题”和“共识+陌生感”方法,把账号定位、目标人群、产品或服务、内容目标转化为可拍摄的选题库。用户提出不知道拍什么、批量想选题、制定选题日历、根据产品找内容方向、优化空泛选题、区分流量/转化/关系维护内容,或明确调用“@曹proAI 爆款选题”时使用。
samuelstefancic/ContextRift/examples/synthetic-project/.agents/skills/exampleboard-card-workflow Skill
0★ repoGuide changes and audits of ExampleBoard card lifecycle transitions, guards, event history, idempotent replay, and lifecycle regression tests. Use for work whose expected behavior depends on docs/card-lifecycle.md. Do not use for copy edits, formatting, generic quality checks, unrelated unit tests, or inventing missing business rules.
Frontend behavior preserving refactor
SHIHAOZOU/ai-frontend-engineering-skills/skills/frontend-behavior-preserving-refactor Skill
0★ repoImprove frontend structure, types, boundaries, readability, or performance without changing intended behavior. Use for component extraction, state simplification, API cleanup, dependency reduction, or architecture migration.
dukesky/resume-tailor/plugins/resume-tailor/skills/resume-tailor Skill
0★ repoTailor a resume to a specific job description — honestly, with no fabrication. Use when the user wants to adapt, rewrite, customize, or optimize a resume or CV for a particular job posting / JD; wants a gap analysis of how well their resume matches a role; or wants to know which of a job's requirements they meet, partially meet, or miss. Works from a resume file (PDF, Markdown, or text) or pasted text plus a job description (pasted text, a file, or a URL).
YellowOrz/bilingual-paper-translator/skills/bilingual-paper-translator Skill
0★ repoCreate bilingual versions of research papers as interleaved HTML and paginated PDF, translating the original text into a selected target language with one whole-paper model context while preserving formulas, figures, tables, references, and links. Use when the user provides an arXiv title, ID, or URL; a DOI or official paper page; a direct PDF URL; a local PDF; or local HTML. Prefer arXiv HTML, then arXiv TeX, then the official PDF; convert other PDFs to HTML with Docling. The target language defaults to Simplified Chinese.