Agent Tooling
Skills that build, configure or extend agents and other skills.
Search and filter within Agent Tooling
13733 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| trace-to-practicewssfk12138/trace-to-practiceDistill task histories into evidence-backed improvements and help apply the findings. Use for 对话蒸馏/工作流复盘, recurring agent-error analysis, or applying prior retrospective findings. Not for a simple chat summary, unrelated memory setup, or ML model distillation. | Stars: 48 | Updated | Claude CodeCodex | Verified | Install |
| skills-vote-localMemTensor/skills-voteUse when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery. | Stars: 309 | Updated | Claude CodeCodex | Verified | Install |
| start-taskmaotoumao/CebianResume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md. | Stars: 185 | Updated | Claude CodeCodex | Verified | Install |
| get-startedcoupler-io/skillsUse this skill when the user's Coupler.io workspace is NEW or EMPTY — no datasets, no credentials — and they want their data flowing, or when any data request arrives from an account with nothing set up yet. Triggers include: "get started", "set up Coupler", "connect my data", "I just signed up", "pull my QuickBooks/Shopify/HubSpot/ads data", an empty list-datasets result, or a missing credential. Goal: take the user from an empty workspace to their own data rendered in this chat, in one guided pass — including the one-time browser step to authorize their source. Do NOT use for accounts that already have datasets or dataflows (work with their data directly), for platform questions ("what sources do you support?"), or for adding a source to an existing setup (use the create-dataflow skill instead). | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| amazon-ads-keyword-and-product-targetingcoupler-io/skillsUse for "which Amazon keywords make money", "what should my Amazon bids be", "is exact or broad match better on Amazon", "how are my Amazon auto campaigns doing", "which Amazon product targets work", "should I target competitor ASINs on Amazon", or "why is my Amazon cost per click so high" — even when the user never says "targeting". This is the earning view: which Amazon keywords and targets deserve more and what each should bid. For search terms to cut, use the waste skill. Amazon Ads only. | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| facebook-ads-creative-fatiguecoupler-io/skillsUse for "is my Meta creative burning out", "my CTR is dropping", "my CPMs keep rising", "how long before I need new ads", "which ads should I refresh", "how much new creative do I need a month", or "this ad used to work" — even when the user never says "fatigue". This is the how-long-has-it-left read; for which creative wins in the first place, use the creative analysis skill instead. Meta / Facebook Ads only. | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| facebook-ads-creative-performance-analysiscoupler-io/skillsUse for "which creative is working on Meta", "which ads should I put money behind", "what should the next round of creative look like", "why is my quality ranking below average", "is my hook working", "which video is holding attention", or "what do my winners have in common" — even when the user never says "creative". This is the which-ads-win read; for which winning ads are dying, use the fatigue skill instead. Meta / Facebook Ads only. | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| linkedin-ads-creative-fatiguecoupler-io/skillsUse for "are my LinkedIn ads burning out", "my LinkedIn click-through rate is dropping", "my LinkedIn frequency is too high", "how long before I need new LinkedIn ads", "which LinkedIn creatives should I refresh", "how much new creative do I need for LinkedIn a month", or "this LinkedIn ad used to work" — even when the user never says "fatigue". This is the how-long-has-it-left read; for which LinkedIn creative wins in the first place, use the creative analysis skill. LinkedIn Ads only. | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| linkedin-ads-creative-performance-analysiscoupler-io/skillsUse for "which LinkedIn ads are working", "which LinkedIn creative should I put money behind", "what should my next LinkedIn ads look like", "is my LinkedIn video hook working", "which LinkedIn carousel card gets the clicks", "are document ads worth it on LinkedIn", or "what do my best LinkedIn ads have in common" — even when the user never says "creative". This is the which-ads-win read; for which winning LinkedIn ads are wearing out, use the fatigue skill instead. LinkedIn Ads only. | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| tiktok-ads-creative-fatigue-and-refresh-cadencecoupler-io/skillsUse for "is my TikTok creative burning out", "my hook rate is dropping", "my CPMs keep rising", "how long before I need new videos", "which ads should I refresh", "how much new creative do I need a month", "how many videos should we shoot", or "this video used to work" — even when the user never says "fatigue". This is the how-long-has-it-left read and the production-cadence number; for which videos win in the first place, use the creative analysis skill. TikTok Ads only. | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| tiktok-ads-creative-performance-analysiscoupler-io/skillsUse for "which creative is working on TikTok", "which videos should I put money behind", "what should the next round of creative look like", "is my hook working", "which video is holding attention", "why do people scroll past my ad", or "what do my winners have in common" — even when the user never says "creative". This is the which-videos-win read; for which winning videos are dying, use the fatigue skill instead. TikTok Ads only. | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| content-decay-analysiscoupler-io/skillsFinds pages that are quietly losing organic traffic over time, from live Google Search Console data in your Coupler.io workspace — which pages are down on clicks, whether it's a ranking slip or fewer people searching, and which are worth updating first. Use for "which of my pages are losing search traffic", "what content is decaying", "which blog posts should I refresh", "why is my organic search traffic sliding", "which pages dropped in Google since last quarter", "find pages that need updating for SEO" — even when the user never says "decay". This is the losing-ground view: pages that used to do better and why. For pages that never ranked well in the first place use google-search-console-keyword-opportunities. A sudden site-wide drop isn't decay — this skill flags it rather than diagnosing it. Google Search Console only. | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| <slug>gooseworks-ai/goose-skills<What it does and when to use it, in one or two sentences. This is what an agent matches on. At most 1,024 characters.> | Stars: 1.3k | Updated | Claude CodeCodex | Verified | Install |
| plugin-fast-adapttaxueseek/plugin-fast-adaptDSH 插件升级适配与代码审查主入口。查 DeepSeek 官方最新版本与升级指南,扫描插件破坏性变更;支持四条车道(适配升级/造插件/启动排障/代码审查与防御性架构审核)及 DSH 原生插件与子 Agent 隔离委派协议,输出 P0/P1 紧凑报告。触发词:适配 DSH 插件、升级插件、插件不兼容、dsh 升级后报错、代码审查、代码审核、code review、生命周期检查、单例泄漏、Peer污染、紧凑报告、批量巡检。 | Stars: 15 | Updated | Claude CodeCodex | Verified | Install |
| go-to-market-launchJPeetz/agent-skillsUse this skill when planning a launch, beta, or GTM push. | Stars: 17 | Updated | Claude CodeCodex | Verified | Install |
| anti-over-engineeringJPeetz/agent-skillsUse when AI agents over-engineer code beyond user requests. | Stars: 17 | Updated | Claude CodeCodex | Verified | Install |
| deprecation-and-migrationJPeetz/agent-skillsUse this skill when deprecating APIs or migrating users. | Stars: 17 | Updated | Claude CodeCodex | Verified | Install |
| skill-portability-and-packagingJPeetz/agent-skillsUse this skill when packaging or porting agent skills. | Stars: 17 | Updated | Claude CodeCodex | Verified | Install |
| consulting-analysisxinetzone/SpecWeaveUse this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This skill operates in two phases — (1) generating a structured analysis framework with chapter skeleton, data query requirements, and analysis logic, and (2) after data collection by other skills, producing the final consulting-grade report with structured narratives, embedded charts, and strategic insights. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| link-check-cmdxinetzone/SpecWeave当用户提到'链接检查'、'检查链接'、'断链'、'链接修复'、'fix links'、'check links'、'验证链接'、'死链'、'链接有效性'、'提交前检查'时,必须使用此技能。提供Markdown链接有效性检查与自动修复能力:本地文件引用验证、外部URL可达性检测、file:///绝对路径转相对路径、相对路径层级自动校正。不要手动查找断链——本Skill封装了缓存机制、并发检测、自动修复和dry-run预览,是提交前质量门禁的核心工具。 | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| ask-mattJesusFilm/coreAsk which skill or flow fits your situation. A router over the skills in this repo. | Stars: 24 | Updated | Claude CodeCodex | Verified | Install |
| code-reviewJesusFilm/coreReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". | Stars: 24 | Updated | Claude CodeCodex | Verified | Install |
| teachJesusFilm/coreTeach the user a new skill or concept, within this workspace. | Stars: 24 | Updated | Claude CodeCodex | Verified | Install |
| writing-great-skillsJesusFilm/coreReference for writing and editing skills well — the vocabulary and principles that make a skill predictable. | Stars: 24 | Updated | Claude CodeCodex | Verified | Install |
| agentic-architectureOvid/paadUse when assessing the architectural health of a codebase — before a major refactor, when onboarding to an unfamiliar repo, after rapid growth, when planning a redesign, or to surface structural strengths and risks before they become expensive. Not for fixing what it finds, and not for reviewing a branch diff. | Stars: 154 | Updated | Claude CodeCodex | Verified | Install |
| agentic-dedupOvid/paadEXPERIMENTAL. Use when looking for meaningfully duplicated logic in a codebase, especially duplicate behavior hidden behind different names, different syntax, different control flow, or independently evolved implementations. Not for style issues, not for syntactic clone detection, and not for fixing what it finds. | Stars: 154 | Updated | Claude CodeCodex | Verified | Install |
| agentic-reviewOvid/paadUse when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review. Not for codebase structure, not for code style, and not for fixing what it finds. | Stars: 154 | Updated | Claude CodeCodex | Verified | Install |
| fix-architectureOvid/paadUse when working through architectural flaws documented in a .reviews/architecture/ report — selecting which flaws to fix, resuming a partial fix session across multiple sittings, or applying structural changes that need to be tracked back to a report. Not for producing that report — run the agentic-architecture skill first if there isn't one. | Stars: 154 | Updated | Claude CodeCodex | Verified | Install |
| abbey-system-promptdonaldfilimon/abiMaintain the Abbey / Aviva / Abi Discord system prompts in the Rust abbey-bot (`src/ask.rs`) and keep the hosted Grok bots (Grok Bot Abbey, Aviva Grok) in step with them. Use when the user says "improve grok bots", "abbey prompt", "persona prompt", "ask.rs", "system prompt", "tip floor", asks to change how Abbey/Aviva/Abi speak on Discord, or after an abbey-bot PR merges and the hosted bot's tip floor needs bumping. Runs as /abbey-system-prompt. | Stars: 18 | Updated | Claude CodeCodex | Verified | Install |
| ai-plandonaldfilimon/abiPlan abi AI work — model routing, completion, SEA self-learning, and training. Use when the user asks to plan AI orchestration, choose a model, run a completion, drive the SEA learn loop, or schedule training. Routes to complete-base, sea-learn-loop, agent-plan-train, and the abi-superpower-ai/sea/constitution superpowers. | Stars: 18 | Updated | Claude CodeCodex | Verified | Install |