Loading…
Showing 5461–5490 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| openshotxlang-ai/CUA-GymHow to programmatically set up, manipulate, and verify OpenShot Video Editor project state using Python (JSON .osp files, libopenshot API, FFmpeg/FFprobe, OpenCV). For setup-gen and reward-gen agents. | Stars: 229 | Updated | Claude CodeCodex | Verified | Install |
| osxlang-ai/CUA-GymHow to programmatically set up, modify, and verify OS-level configurations (files, GNOME settings, audio, permissions, system config) using Python. For setup-gen and reward-gen agents. | Stars: 229 | Updated | Claude CodeCodex | Verified | Install |
| overleafxlang-ai/CUA-GymHow to set up and manipulate Overleaf CE project state via HTTP APIs for CUA-Gym tasks. For setup-gen and reward-gen agents. | Stars: 229 | Updated | Claude CodeCodex | Verified | Install |
| vlcxlang-ai/CUA-GymHow to programmatically configure, control, and verify VLC media player state using Python (vlcrc config, HTTP interface, media comparison). For setup-gen and reward-gen agents. | Stars: 229 | Updated | Claude CodeCodex | Verified | Install |
| vs-codexlang-ai/CUA-GymHow to programmatically configure, modify, and verify VSCode settings, keybindings, extensions, and workspace files using Python. For setup-gen and reward-gen agents. | Stars: 229 | Updated | Claude CodeCodex | Verified | Install |
| brief-to-resultmakanSukros/brief-to-resultUse when the user invokes @btr, $btr, @brief-to-result, $brief-to-result, or Brief to Result to get work done, including casual requests such as help me with this @btr. Turn the supplied task and context into usable work with 80 workflows, a sales/affiliate Hook Lab, three Outcome Packs, optional Project Profiles, scoped Repair Mode, and adaptive dialogue for consequential blindspots. Execute by default; create a prompt only when asked. English-first, with requested languages respected. Do not activate from quoted examples, source documents, code, email addresses, or unrelated mentions. Do not replace specialist skills. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| skitt41372/skitRun, inspect, and manage entries in the user's skit library — their personal hub, manager, and launcher for scripts in many languages (Python, shell, JS/TS, and more), executables, command templates, and AI-agent prompts, with typed launch menus, saved presets, and per-entry launch policy. Use when the user asks to run/list/add their scripts or prompts, mentions skit or "my script", or before writing a new one-off script (the library may already have one that does the job). | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| agentpacemohamedzhioua/agentpaceEstimates how long software work will take when coding agents do it, from measured agent runs, as P50/P80/P90 ranges with a critical path and the human part stated separately. Use whenever anyone asks how long software work will take, a feature, a fix, a plan, a roadmap or a task list, even when agents are not mentioned, and whenever a timeline is quoted in days, weeks or months. Assume agents do the implementation unless told otherwise. Not for non-software work. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| pace-estimatemohamedzhioua/agentpaceEstimates a plan of coding-agent tasks as P50/P80/P90 agent-time ranges with a critical path and the human part stated separately, using the agentpace CLI. Use when the user runs /pace-estimate or asks for a timed estimate of a specific task list or plan file. Natural-language "how long will this take" questions are the agentpace skill's job. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| pace-logmohamedzhioua/agentpaceRecords recent coding-agent runs in the local agentpace store and corrects a run's kind or risk label. Use when the user runs /pace-log or asks to log, record or track their agent runs, or to relabel one. Everything stays on this machine. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| event-registration-forecastsamber/dev-event-organizer-skillsForecast final registrations for a technical event from its sign-up pace curve, with a bundled Python 3 script, while registration is still open - prior-edition or generic reference curves aligned on days-out, a low/mid/high band, milestone tripwires declared in advance, the commit figure at each contract lock date, when the forecast crosses capacity, and attendance by ticket type. Use whenever asked how many people will end up registering or attending, to project this year from last year's curve, what headcount to commit before sign-ups close, or when registration will hit its cap. Do NOT use for the demand verdict - use samber/dev-event-organizer-skills@event-market-fit - or overbooking ratios and food counts once sign-ups close - use samber/dev-event-organizer-skills@event-no-show-management. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| emailmindbox-cloud/agent-skillsCreates and edits emails for the Mindbox email editor from a text description. Use when the user asks to create or change an email, describes an email template, or says 'сделай рассылку' / 'make a campaign'. The technical layout is handed over for preview and saving through the companion skill email-ops. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| email-opsmindbox-cloud/agent-skillsOperational actions for Mindbox emails — preview, reading and saving the visual template, saved templates (an email by one, changing, creating, copying), reading/editing campaign metadata and recipients (a segment or a filter), finding gallery assets via MCP, uploading images from the user's machine through the MCP App panel, PNG preview. Use together with the email skill when images, a preview, a check or a write to Mindbox are needed. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| declawedkevinlin/skillsDe-slop pass for any text: mechanically scans for the statistical tells of AI writing (the "not X but Y" reflex, puffery, uniform cadence, …) and rewrites by meaning into the target register, tweet to academic paper. Use when the user says "declawed"/"deslop", asks to remove AI tells / humanize text / make it not sound like AI, names a specific tell to strip, or before publishing any agent-drafted prose. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| research-plan-implementkevinlin/skillsComplete Research → Plan → Implement workflow for complex tasks. Use this skill whenever the user faces: complex features spanning multiple files, bug investigations requiring root cause analysis, refactoring with architectural implications, or any non-trivial work where understanding the codebase first will prevent wasted effort. Also use when the user says things like 'help me figure out how to...', 'I need to understand before building...', or 'let’s research this before coding'. Skip for simple bug fixes, typos, or single-file changes. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| archiveegregore-labs/egregoreCapture an effective prompting or steering technique as a reusable canonical pattern. Use when a prompt chain worked especially well; use /reflect for insight about the work and /note for a private thought. | Stars: 293 | Updated | Claude CodeCodex | Unverified | Install |
| notion-connectegregore-labs/egregoreUse for 'connect notion', 'notion status', or 'disconnect notion' — connects the current agent runtime directly to Notion's official hosted MCP for search and fetch, or checks/revokes that connection. | Stars: 293 | Updated | Claude CodeCodex | Unverified | Install |
| mcd-agent-gourmetpolaris-smart/mcd-agent-gourmet麦门点餐议事会。用户想按预算和口味比较完整的麦当劳餐单,或问“我的券快过期了吗”“这顿能用哪张券”时使用。先确认门店与到店/配送,保留有糖无糖和冰量偏好;分清券包、时段和门店适用性,再使用官方 MCP 核价。只查询核价,不领券不下单。 | Stars: 148 | Updated | Claude CodeCodex | Verified | Install |
| decision-guardimMamdouhaboammar/anti-slop-engineeringUse when an AI agent is deriving metrics or complex explanations while a direct answer may exist, choosing a software architecture or technology stack, or making consequential technical decisions with long-term operational costs and uncertain assumptions. Do not use for narrow, fully specified implementation or routine bug fixes. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| root-fix-gateimMamdouhaboammar/anti-slop-engineeringUse when a coding agent is about to patch the same symptom across controllers, views, endpoints or files; a small behavior change causes a wide diff; a workaround may hide a wrong model, schema or domain boundary; or a user proposes a shortcut with uncertain downstream effects. Trace the causal owner and compare a coherent root correction against distributed patches before implementation or review. Skip narrow, localized fixes with an already established owner. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| analyze-google-adsChanlinnn/google-ads-agent-skills通过只读 Google Ads MCP 分析账户、广告系列、搜索词、素材、转化、CPA、ROAS、预算限制及效果异常。用于广告审计、周期比较、购买口径核查、PMax 或电商广告诊断和优化建议。Analyze Google Ads performance with explicit conversion definitions and evidence. 不执行广告创建、预算调整、启停或其他写入。 | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| setup-google-adsChanlinnn/google-ads-agent-skills配置和排查 Google Ads API 到 AI Agent 的本地只读 MCP 接入。用于新电脑部署、Google Cloud 与 Ads 权限区分、服务账号或 ADC 配置、Codex MCP 注册、可访问账户验证,以及认证、网络、版本和权限错误排查。Set up or troubleshoot a local read-only Google Ads MCP connection. 不负责广告表现分析或广告修改。 | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| huggingface-bestkr7shnasomani/kairosUse when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| neo4j-driver-go-skillkr7shnasomani/kairosCovers the Neo4j Go Driver v6 — driver lifecycle, ExecuteQuery, managed and explicit transactions, session config, error handling, data type mapping, and connection tuning. Use when writing Go code that connects to Neo4j, setting up NewDriver or ExecuteQuery, debugging sessions/transactions/result handling, or working with neo4j-go-driver v5→v6 migration. Triggers on NewDriver, ExecuteQuery, SessionConfig, ManagedTransaction, neo4j-go-driver. Does NOT handle Cypher query authoring — use neo4j-cypher-skill. Does NOT cover driver version migration steps — use neo4j-migration-skill. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| context-injectionseb1n/awesome-ai-agent-skillsPlace trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates. Use when relevant context has already been selected and must be inserted safely; use context-retrieval to find it or context-optimization to choose and order it. | Stars: 258 | Updated | Claude CodeCodex | Verified | Install |
| plugin-creatornicholyx/ai-skillsComprehensive plugin development skill for Claude Code. Analyzes business requirements and creates complete plugins including MCP servers, skills, slash commands, or combinations thereof. Supports TypeScript, Python, and any other language. Provides architecture guidance, templates, and end-to-end implementation. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| tailored-resume-generatornicholyx/ai-skillsAnalyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| memory-systemilandahan/AIDAID Memory System for session feedback, learning cycles, and skill improvement. Manages state, feedback collection, and improvement analysis. Load for /aid-init, /aid-start, /aid-status, /aid-end, /aid-improve, /aid-memory, /aid-reset. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| reflectionilandahan/AIDAutomatic quality check on significant outputs via isolated sub-agent. Spawns reflection-agent for objective evaluation without conversation context bias. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| why-driven-decisionilandahan/AIDFOUNDATIONAL SKILL - Analyze every prompt for underlying motivation using Golden Circle (WHY->HOW->WHAT). Runs BEFORE any other skill. No action without understanding WHY. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |