Explore skills
Search every indexed skill by name, description, repository or instructions, then narrow the results.
Showing 54181–54210 of 63935 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| problem-framingafeezadebayo/thinking-decisions-skillsDefines the right problem before anyone solves it. Takes a problem someone has stated (a brief, a goal, a complaint, a 'why is X happening' question, a request to fix or improve something) and tests whether it is framed well, then produces two to four candidate frames, a chosen problem statement and success criteria. Surfaces the stated frame, gathers short written definitions from several people, asks what the description leaves out, checks the objective, analyses cases where the problem did not occur, and treats problems as multicausal rather than finding one root cause. Use whenever someone asks to frame or reframe a problem, write a problem statement, scope a project, run a root-cause or 5 Whys session, work out the real problem, or says a solution is not working and they do not know why. Do NOT use for choosing between options already defined (use decision-frameworks), stress-testing a chosen plan (use premortems), ranking a backlog (use prioritisation) or running desk research (use research-planning). | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| trade-off-analysisafeezadebayo/thinking-decisions-skillsHelps Claude, Codex or another AI agent compare several options against weighted criteria with a decision matrix, without the false precision that makes scorecards misleading. It gates options on must-haves first, caps and weights the criteria before scoring, scores on an anchored 1 to 5 scale, computes weighted totals, then runs a sensitivity check to see whether the ranking is real or noise. Use it when someone has three or more options and several competing criteria and asks to "compare these options", "score these", "build a decision matrix", "weighted scoring", "pros and cons is not enough", "which vendor/tool/candidate/supplier", or "help me choose between". Do NOT use it for a yes-or-no decision or the overall call (use decision-frameworks), to stress-test one chosen option (use premortem-analysis), or when one criterion clearly dominates and a matrix would add false rigour. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-agentic-registrationfavcrm/mcpUse when a new user wants to register for FavCRM from inside an MCP client, create a FavCRM workspace, request or verify signup OTP, receive a fav_mcp_* API key, or continue setup after agentic registration. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-billing-commercefavcrm/mcpUse for invoices, payments, products, orders, promotions, subscriptions, overdue follow-up, and commerce operations in FavCRM. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-booking-operatorfavcrm/mcpUse for service setup, availability, booking lifecycle, cancellations, no-shows, reminders, and daily booking operations in FavCRM. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-business-reportingfavcrm/mcpUse for FavCRM dashboards, weekly snapshots, KPI summaries, revenue, bookings, invoices, subscriptions, customer growth, and operational risk reports. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-channel-setupfavcrm/mcpUse when checking or connecting FavCRM communication channels, especially WhatsApp Business Embedded Signup from an MCP client or the favcrm CLI. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-comms-approvalfavcrm/mcpUse for FavCRM marketing campaigns, customer reactivation, broadcasts, WhatsApp, SMS, email, inbox replies, and approval-gated customer communications. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-content-publisherfavcrm/mcpUse for FavCRM blog posts, CMS content blocks, landing-page content, AI-generated images, post publishing, post updates, and content workflows. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-customer-lifecyclefavcrm/mcpUse for customer search, member profiles, tags, tiers, loyalty, segments, onboarding, retention, and customer 360 summaries in FavCRM. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-knowledge-trainingfavcrm/mcpUse for training the FavCRM AI agent with URLs or pasted text, listing knowledge documents, checking ingestion status, and pruning outdated knowledge. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-sales-opsfavcrm/mcpUse for FavCRM deals, pipeline stages, internal tasks, follow-ups, owners, workspace switching, and operational handoffs. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| favcrm-team-onboardingfavcrm/mcpUse when inviting a teammate to FavCRM, generating a one-time team invite token, accepting an invite, verifying an emailed invite OTP, or issuing an MCP API key for an invited team member. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| wscleand3v-null/wsclean-skillRadio interferometry imaging and deconvolution tool | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| skill-lib-iteratewanglin1111111/skill-lib-iterate开源 Skill 库(如 marketingskills)的「事实核对 + 三层迭代」方法论。核心判断:Skill 库的真正价值不在"装上 47 个 Skill",而在它给出的一套可复制 Skill 工程范式(触发条件→工作流→输出规范→交叉引用→护栏)。先核对再迭代:Star 数是曲线上的点不是快照("一夜爆火"是内容号话术,看 32.9k→36.3k→39.4k→42.5k→47.1k 的持续数月累积轨迹);图只挑最新最吸睛的 4 个,实际库是 47 个(v2.8.0)现 v2.9.0;人格模拟类 Skill(marketing-council)输出必须标注模拟、禁止编造引语、不暗示真人背书;第三方评测点名的真问题=Skill 定义固执不自适工具栈,生产落地前必做定制。三层迭代:L1 直接用——先写产品上下文底座(.agents/product-marketing.md:定位/受众/价值主张/竞品替代,不写则输出全是通用套话)再装(npx skills add),先跑产出真实改动的审计型(cro/seo-audit)别先跑战略讨论型(council,没数据输入=空转);L2 定制(性价比最高也是原项目最缺)——AI 搜索本土化(中文渠道:元宝/DeepSeek/豆包/百度AI/搜一搜)、换顾问团(两级标准:公众人物必须可溯源出处,私有顾问观点必须你提供绝不能编造)、接真实数据(从 43 个 loop 挑 1-2 个接 GA4/搜索/CRM,先跑通一个闭环比装 47 个有用)、加红线(行业合规约束写进 veto list 机器可读);L3 做它没做的(真正空位)——给每个 Skill 配前后指标+跑分+回归测试(库只能答"做什么"答不了"做得怎么样")、把"分歧地图+用证据裁决"机制抽出来用于定价/产品路线/技术选型等任何决策。Use whenever the user asks 开源 Skill 库怎么用/装了一堆 Skill 没效果/Skill 库怎么落地/Star 数是不是真的/council 模拟顾问团怎么用/要不要全装/怎么定制 Skill 库/Skill 效果怎么评估. Not for: 单个 Skill 的创作方法(走 leader 或直接写 SKILL.md)、AI 链路架构(走ai-chain-embed)、内容分发工具接入(走pipeline-onboard)、单点技术学习(走hands-on-loop). 触发词: Skill 工程范式、product-marketing.md、底座、先跑 cro、本土化 ai-seo、advisor-template、两级标准、veto list、loop 闭环、前后指标、跑分、回归测试、分歧地图、证据裁决、47 个不是 4 个。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| cn-ai-visibilitylm203688/china-compliance-skills-mirrorAnalyze brand/keyword visibility across 5 Chinese AI search engines (DeepSeek/Kimi/豆包/通义千问/文心一言). Get per-engine citation logic analysis, visibility scoring, and optimization strategies. Use when: checking if your brand appears in AI search results, optimizing content for AI citation, monitoring brand visibility in Chinese AI engines, planning GEO (Generative Engine Optimization) strategy for China market. RUN: ./check-visibility.sh 'brand' --api for instant 0-100 audit score. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| cn-aigc-detectorlm203688/china-compliance-skills-mirrorDetect AI-generated Chinese text using 5 statistical signals: sentence length variance (perplexity), vocabulary TTR (burstiness), structural pattern matching (首先...其次...最后), sentence starter uniformity, and punctuation density analysis. Highlights suspicious sections. Use when: verifying if Chinese text is AI-generated, checking content authenticity before publishing, auditing user-generated content for AI usage, detecting AI-written reviews/comments/articles, ensuring content originality compliance. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| cn-compliance-guardlm203688/china-compliance-skills-mirrorScan Chinese text for 200+ banned words across 6 legal categories (广告法/消费者权益保护法), check SEO compliance for 5 platforms (百度/小红书/抖音/淘宝/京东), and provide safe replacement suggestions. Detects 绝对化用语, 医疗效果承诺, 虚假宣传, 金融承诺, 诱导消费, 比较广告. Use when: checking Chinese marketing copy for legal compliance, reviewing product descriptions for advertising law violations, auditing content before publishing on Chinese platforms, replacing banned words with safe alternatives. RUN: ./check.sh '你的文案' --platform douyin for instant scan. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| cn-data-exportlm203688/china-compliance-skills-mirrorAssess cross-border data transfer compliance under PIPL/网络安全法/数据安全法. 7-question risk assessment determines compliance pathway (安全评估/标准合同/认证). Covers personal information thresholds, important data identification, CIIO obligations. Use when: transferring data from China overseas, assessing if data export needs CAC security assessment, determining which compliance pathway applies, checking PIPL compliance for international business, evaluating data localization requirements. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| eu-ai-act-complianceDirtyBeastAfterTheToad/EU-AI-Act-Compliance-Codebase-Audit-SkillUse this skill when answering questions about the European Union AI Act (Regulation (EU) 2024/1689) or conducting static and dynamic compliance audits on codebases to detect prohibited practices, missing transparency controls, or unfulfilled high-risk safeguards. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| bundle-localHuyTinh/git-release-bundlerConsolidate local Git branch commits into a 2-tier changelog and compile DB migration SQL scripts into a single release bundle (.antigravity/release_output/<version>/ or release_output/<version>/). Triggered when user asks to bundle branches, compile release scripts, generate release changelog, or types /bundle-local <version>, "gom nhánh", "tạo release local". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| git-markHuyTinh/git-release-bundlerMark the current or specified Git branch for local release bundling (.git/marked_branches.txt). Triggered when the user invokes /git-mark, /mark, /git-mark list, /mark list, /git-mark clear, /mark clear, /git-mark unmark <branch>, or says "mark nhánh này", "đánh dấu nhánh", "bỏ đánh dấu nhánh". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| module-audit-agentgirishlade111/ai-agent-skillsUse when asked to audit a module, check its health, or assess whether it should be refactored. Runs structural query, risk check, and test generation automatically. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| onboard-dev-agentgirishlade111/ai-agent-skillsUse when a dev is new to the project, asks for an overview, or wants to get oriented quickly. Fills graph gaps then runs a guided codebase interview. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| pr-review-agentgirishlade111/ai-agent-skillsFull PR review orchestrator. Use when asked to review a PR or check if it is ready to merge. Runs blast radius + drift check on changed files, then hands off to pr-review for comment triage and fixes. Do NOT use pr-review directly for full reviews — use this. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| brownfield-driftgirishlade111/ai-agent-skillsEnforces architecture boundaries defined in PLAN.md. Use when a PR crosses module/service boundaries, when the dev asks "are we following the architecture?", or as a scheduled architecture health check. Not for querying what a module does — use brownfield-chat for that. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| codebase-intelgirishlade111/ai-agent-skillsUnified codebase intelligence. Handles all questions about structure, logic, risk, and dependencies. Combines natural-language Q&A with deterministic lookups and pre-edit blast radius checks. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| deploy-checklistgirishlade111/ai-agent-skillsPre-deploy and post-deploy checklist skill. Ensures env vars, migrations, CI, rollback plan, smoke tests, and monitoring are verified before and after every deployment. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| greenfieldgirishlade111/ai-agent-skillsParallel persona planning for new projects. Research agent runs first to build domain context, then Architect, PM, and Security agents run in parallel. Synthesis agent combines all perspectives into a detailed GSD-style PLAN.md with Tensions section. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| pr-reviewgirishlade111/ai-agent-skillsFix engine for PR review comments. Fetches review comments (Gemini bot or human), categorizes by impact, posts a prioritized fix queue, and applies fixes on dev approval. Called directly for quick fixes, or internally by pr-review-agent as part of full PR review. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |