Loading…
Showing 4711–4740 of 10180 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| salesforce-adminPranavNagrecha/AwesomeSalesforceSkillsRouter for the 261 SfSkills `admin` skill packages. Declarative Salesforce configuration: objects, fields, record types, page layouts, permission sets, reports, the record-access model (OWD, role hierarchy, sharing rules), and the requirements work that precedes them. Use when the request mentions custom object, custom field, picklist, record type, page layout, permission set, profile, validation rule, report, dashboard, queue, approval process, user setup, sharing rule, org-wide default, OWD, role hierarchy, record access, record visibility, who can see this record, duplicate rule, matching rule, duplicate prevention, clean up duplicates, merge governance, Spring release, seasonal release, Release Updates, Sandbox Preview. Finds and opens the exact skill package to read; it does not contain the guidance itself. | Stars: 26 | Updated | Claude CodeCodex | Verified | Install |
| salesforce-agentforcePranavNagrecha/AwesomeSalesforceSkillsRouter for the 53 SfSkills `agentforce` skill packages. Agentforce and Einstein: agents, topics, actions, prompt templates, grounding, guardrails, evaluation and production readiness. Use when the request mentions Agentforce, agent topic, agent action, prompt builder, Einstein, Trust Layer, grounding, RAG, guardrails, agent evaluation, prompt injection. Finds and opens the exact skill package to read; it does not contain the guidance itself. | Stars: 26 | Updated | Claude CodeCodex | Verified | Install |
| salesforce-dataPranavNagrecha/AwesomeSalesforceSkillsRouter for the 101 SfSkills `data` skill packages. Data model, data movement and data quality: migrations, bulk loads, query optimisation, deduplicating at volume, archival. Ordinary-volume duplicate cleanup and prevention use salesforce-admin; come here for hundreds-of-thousands+ dedup or third-party tools. LDV architecture uses salesforce-architect. Use when the request mentions data model, data migration, data load, Data Loader, Bulk API, external id, deduplication at volume, archival, SOSL, cross-object search, sandbox seed data, SandboxPostCopy, native Data Seeding. Finds and opens the exact skill package to read; it does not contain the guidance itself. | Stars: 26 | Updated | Claude CodeCodex | Verified | Install |
| salesforce-integrationPranavNagrecha/AwesomeSalesforceSkillsRouter for the 61 SfSkills `integration` skill packages. INBOUND integration and the API surface itself: the Salesforce REST and SOAP APIs, Bulk API 2.0 jobs, Platform Events, CDC, Pub/Sub, Named Credentials and middleware. For calling OUT to someone else's API from Apex, use salesforce-apex instead. Use when the request mentions integration, Salesforce REST API, composite API, SOAP API, Bulk API 2.0 job, Platform Event, Change Data Capture, Pub/Sub, inbound webhook, Named Credential, OAuth, connected app, MuleSoft, Salesforce Connect, external system calling Salesforce. Finds and opens the exact skill package to read; it does not contain the guidance itself. | Stars: 26 | Updated | Claude CodeCodex | Verified | Install |
| how-to-writewebkubor/writing-standard-skills「怎么写文字」的总纲——先用原话搭骨架并给足推理上下文,再按读者定语气(人还是 agent、上级还是同侧),最后把最终答案重写成脱离中途更新也能读懂的自包含文本。管一切要给别人看的文字:文档、单据、报告、评审意见、讲稿、群消息、PR 描述。触发:"写文档 / 写报告 / 提单 / 写评审意见 / 文案不合理 / 逻辑不清 / 这样礼貌吗 / 结论说不清 / 讲稿检查 / 最终答案不自包含 / AI 味 / 沿用用户术语 / 说人话 / 主动语态"。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| chanmeng-svg-verifyChanMeng666/chanmeng-svg-animation-studioVisually verify a rendered SVG animation by opening it in chrome-devtools MCP, capturing keyframes, and scoring against the 5-point quality rubric. Invoke this immediately after `/chanmeng-svg-animate` writes an output, or whenever the user asks "is this animation good?", "how does it look?", "verify the motion", or "check the SVG visually". Always run before declaring an animation complete. Returns a ≤100-word verdict and never leaks screenshots into the calling thread. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| account-custodywebkubor/writing-standard-skills「账户托管运营前置检查」——Agent 替人接管社交账户(发帖/回复/互动)之前,必须先完成四件事:核对当前平台与入口、加载平台规则红线、读出该账户已有人设与口吻、确认出口 IP 与属地一致。人设是「读出来」的不是「选出来」的:先翻该账户近 20 条历史内容、简介与固定推,再决定怎么说话。任何一步缺失就停下问户主,不猜。触发:"托管账户 / 代运营 / 帮我发帖 / 接管账号 / 账号运营 / 替我发 / 管理社交账号 / 人设对齐 / IP 属地 / 账户安全"。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| xhs-account-profilewenziai/wenzi-xiaohongshu-workflowUse when the user wants an agent to remember an account's positioning, voice, boundaries, data, trust assets, personal IP story, and content rules across sessions. Trigger phrases: "账号档案", "记住我的账号", "写入记忆", "人设垂直", "信任名片", "brand profile", "account memory", "style guide". Do not use for one-off post drafting unless profile data is missing. | Stars: 212 | Updated | Claude CodeCodex | Verified | Install |
| xhs-monetization-backsolvewenziai/wenzi-xiaohongshu-workflowUse when the user wants to start or reposition a Xiaohongshu account but is asking "what should I post" before clarifying monetization, timing, personal IP direction, or trust path. Trigger phrases: "小红书定位", "不知道做什么赛道", "怎么变现", "个人IP", "账号方向", "XHS positioning", "monetization first". Do not use for drafting a specific post; use topic or copy skills after positioning is clear. | Stars: 212 | Updated | Claude CodeCodex | Verified | Install |
| aeonrootcastleco/rei-skillsThis skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly su | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| agent-evalrootcastleco/rei-skillsHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| agent-introspection-debuggingrootcastleco/rei-skillsStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| agent-platform-eval-flywheelrootcastleco/rei-skillsMeasures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when generating synthetic user scenarios, evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed o | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| agent-platform-skill-registryrootcastleco/rei-skillsInteract with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| agent-self-evaluationrootcastleco/rei-skillsUse after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| agentic-engineeringrootcastleco/rei-skillsOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| domino-api-introdominodatalab/domino-ai-pluginIntroduction to calling Domino platform APIs. Covers authentication (API proxy, access token, PAT, service account), which base URL to use, pagination, and common errors. Use before any other Domino API, SDK, app, extension, or governance automation skill, and whenever a request needs a Domino base URL or credential. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| domino-llm-gatewaydominodatalab/domino-ai-pluginCall Large Language Models through Domino LLM Gateway 2.0, the centrally governed gateway extension an administrator installs in front of external providers and Domino-hosted models. Covers finding and detecting the gateway, authentication with the in-run access token (fresh per call) or a Personal Access Token outside Domino, model aliases and model discovery, the OpenAI-compatible and Anthropic-compatible paths from the OpenAI and Anthropic SDKs, Pydantic AI, LangChain and plain HTTP, streaming, attribution headers, refused calls (login redirect, grants, budgets, guardrails), pointing a coding assistant such as Claude Code or Codex at the gateway, and what the administrator configures. Use when a user mentions LLM Gateway, Gateway 2.0, a gateway alias or URL, asks how to call a model through the Domino gateway, how to run a coding assistant through it, why a gateway call was refused, or what the gateway administrator must set up. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| domino-trace-setupdominodatalab/domino-ai-pluginSet up GenAI tracing for an LLM or agent application in Domino by checking the Domino SDK and MLflow requirements (the DSE needs nothing installed), then adding a tracing_setup.py helper, span evaluators, a config.yaml, and @add_tracing / DominoAgentContext wiring. Use when the user asks to add tracing, observability, or evaluation to an agent or LLM app running on Domino. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| lugasrezaprama/LugasFree local skill for academic and technical paraphrase, editing, and translation in Indonesian and English that keeps meaning, evidence, citations, and the author's voice. Use for parafrase, sunting, koreksi EYD V, ID↔EN academic translation, skripsi/tesis/jurnal sections, literature review, research gap, methods/results/discussion, reviewer responses, hedging and claim control. Not for fabricating data or references, ghostwriting whole theses, or evading plagiarism/AI detectors. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| matlab-orchestratorwzyn20051216/matlab-agent-skillsMATLAB agentic workflow router. Use this whenever the user asks for MATLAB, Simulink, .m/.mlx/.slx work, toolbox-driven engineering, paper reproduction, simulation, code generation, data analysis, control, robotics, signal/image/AI workflows, or wants an end-to-end automated MATLAB task with validation. For Simulink tasks on this machine, default to a visible workflow: open MATLAB/Simulink windows first so the user can watch modeling, simulation, tuning, and plotting progress. | Stars: 34 | Updated | Claude CodeCodex | Verified | Install |
| megapowers-doctorlawzava/megapowersUse when Megapowers seems inactive or broken: a skill did not fire, the output style is missing, or the user asks to check the Megapowers setup. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| seo-firecrawlrisukisu/marketing-skillsFull-site crawling, scraping, and site mapping via Firecrawl MCP. Use when user says "crawl site", "map site", "full crawl", "find all pages", "broken links", "site structure", "discover pages", "JS rendering", or needs site-wide analysis. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| seo-flowrisukisu/marketing-skillsFLOW framework integration: evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO prompts. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| seo-image-genrisukisu/marketing-skillsAI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics. Powered by Gemini via nanobanana-mcp. Requires banana extension installed. Use when user says "generate image", "OG image", "social preview", "hero image", "blog image", "product photo", "infographic", "seo image", "create visual", "image-gen", "favicon", "schema image", "pinterest pin", "generate visual", "banner", or "thumbnail". | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| mira-image-promptingGlobal-AI-Group-Inc/content-generation-skillsHow to write stills for Mira AI's image models: GPT Image 2, 2.5 and 2.6, Nano Banana Pro and 2.1, Seedream 4, 4K and 5 Pro, Muse Image, Ideogram 4.5, Flux. Which model holds text, which keeps a product identical across a series, how the craft banks for light, optics, composition, grade and materials are used, and the words that make an image worse. Use it before any generate_image call on Mira, or when the user says "image prompt", "промпт для картинки", "нарисуй", "сгенерируй картинку", poster, packshot, banner, cover. NOT for video (mira-video-prompting). | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| agents-context-router-releaserunkids/agents-context-routerPrepare, review or publish an agents-context-router release through its Release Please PR and GitHub draft release. Use when preparing a release, choosing the next version, reviewing a Release PR or publishing a new version. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| approval-boundariesreply-team/jason-aiWhere an agent must stop and ask the user before acting, how an operation's approval class is derived from its reversibility and its reach, what a valid confirmation looks like, and the one case where acting first is correct. Covers previews, retries and idempotency keys, unattended runs, standing approvals and anomaly stop-rules. Use before any operation that reaches a real person, when deciding whether an approval still applies, or when configuring an agent to run without a human present. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| managed-campaign-workreply-team/jason-aiUse when a person wants Jason to start outbound work for them, such as getting meetings or running a campaign, and asks what to do first, and when an interactive agent session should turn an outbound objective into durable campaign work that Jason performs - creating a campaign, adding the people it is about, submitting managed provider operations and AI role work, and following what the runtime does with them; and when a person wants Jason to answer somebody who wrote back - answering a conversation in its own thread, filing, closing or reopening it - or says stop it or not yet about work Jason holds - stopping or holding work, from cancelling one work item to pausing the provider's campaign. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |
| quick-startreply-team/jason-aiUse when a person has just had Jason installed and wants to be taken to their first campaign, when an install prompt says to start the quick-start skill, or when somebody with no campaign yet asks where to begin. It asks one question, reads which channels are routed instead of asking, and says the plan in one message. | Stars: 10 | Updated | Claude CodeCodex | Verified | Install |