AI 与智能体 Skill

「AI 与智能体」分类共 1599 个 Skill，按仓库 star 排序。分类自动生成，仅供参考。

全部 AI 与智能体1599 文档与办公608 前端开发524 测试486 项目与协作329 数据库与数据295 DevOps 与云268 科研253 代码质量与审查217 安全215 浏览器自动化205

bootstrap

agentscope-ai/OpenJudge868

bootstrap

Use when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I need to start evaluating my app but don't know where to begin," "I want to set up eval for a new product," or has just identified failure modes and needs to turn them into principles. Outputs a v0 grader in 30 minutes using OpenJudge SimpleRubricsGenerator, plus a roadmap to reach calibrated evaluation.

eval-report

agentscope-ai/OpenJudge868

eval-report

Use when the user has run multiple evaluation skills and wants a comprehensive analysis — maturity assessment, cross-skill signals, trends, prioritized actions, and an executive summary. Also use when the user mentions eval health check, evaluation audit, ship readiness, evaluation maturity, or "how good is my evaluation system itself." This is a read-only analysis skill.

find-skills-combo

agentscope-ai/OpenJudge868

find-skills-combo

Discover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two recommendation strategies — **Maximum Quality** (best skill per subtask) and **Minimum Dependencies** (fewest installs). Use this skill whenever the user wants to find skills, asks "how do I do X", "find a skill for X", or describes a task that likely requires multiple capabilities working together. Also use when the user mentions composing workflows, building pipelines, or needs help across several domains at once — even if they only say "find me a skill". This skill supersedes simple single-skill search by decomposing the task into subtasks and assembling an optimal skill portfolio.

mmx-cli

agentscope-ai/OpenJudge868

mmx-cli

Generate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation (MiniMax-M3 model), image generation (image-01), video generation (Hailuo-2.3), speech synthesis (speech-2.8-hd, 300+ voices), music generation (music-2.6 with lyrics, cover, and instrumental), and web search. Use when the user needs to create AI-generated multimedia content, produce narrated audio from text, compose music, or search the web through MiniMax AI services.

video-scrub

eternityspring/reelbench-skills868

video-scrub

把一条视频重建成「只有画面和声音」的干净文件——**源片的元数据一概不搬**： GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨，全部留在原地。走的是白名单而不是黑名单：不列要删什么，只说带什么过去（画面一条流、声音一条流），隐私保证来自结构，不来自枚举。难点不在容器 tag，在**看不见的那几层**：x264 把完整编码参数写成 SEI 塞在码流里、 AAC 把版本号写进 DSE、avc1 的 compressorname 里还有一份——`ffprobe` 一个都看不见。五个藏身处逐一堵死，每一处都有实测。默认 `--mode copy`：**画面逐字节照搬**（cmp 验证过），只重编音频，53 秒的片子 1.3 秒跑完； `--mode encode` 完整重编码，多杀掉码流域的东西。验收不靠声称：把源片所有元数据字符串当「针」，在输出文件里做**字节级扫描**，扎到一根就红。12 道门全部由脚本确定性检查。零依赖、零 API key，只要 node 和 ffmpeg。 Use when asked to 清元数据、去元数据、抹掉视频信息、视频隐私、去水印信息、 strip video metadata、remove exif from video、scrub video。

aeo-audit

indranilbanerjee/digital-marketing-pro856

aeo-audit

Audit how a brand appears across the 6 canonical AI answer surfaces — ChatGPT, Perplexity, Google AI Mode, AI Overviews, Gemini, Copilot — probing 10-25 queries into a numbered output bundle with per-platform visibility scorecards, citation-accuracy checks, a competitor matrix, content gaps, and an optimization playbook behind a four-gate quality scorecard. Triggers on "/digital-marketing-pro:aeo-audit", "does ChatGPT know about our brand", "check our AI search visibility", "how does Perplexity describe us", "are we showing up in AI Overviews". Reads the brand profile; reconciles probes against GSC actuals via /digital-marketing-pro:gsc-ai-performance and defines the AI-visibility scoring standard reused by geo-monitor and share-of-voice.

aeo-geo

indranilbanerjee/digital-marketing-pro856

aeo-geo

Strategy module for Answer Engine / Generative Engine Optimization — audits AI visibility, restructures content for citation, runs entity-consistency checks across Knowledge Graph, Wikidata, Wikipedia, Crunchbase, and LinkedIn, and produces JSON-LD schema specs, monitoring frameworks, and a 90-day LLM content strategy. Triggers on "/digital-marketing-pro:aeo-geo", "how do we get cited by AI", "optimize for AI Overviews", "fix our entity consistency", "do we need llms.txt". Reads the brand profile, compliance rules, and industry benchmarks; its measurement counterpart is /digital-marketing-pro:aeo-audit, with GSC actuals via /digital-marketing-pro:gsc-ai-performance.

agency-dashboard

indranilbanerjee/digital-marketing-pro856

agency-dashboard

Generate a portfolio-level dashboard across ALL client brands — per-client RAG health scores, campaign activity, budget pacing, aggregate KPIs, team utilization, pending approvals, upcoming deadlines, and an alerts panel — built for agency standups and weekly reviews. Triggers on "/digital-marketing-pro:agency-dashboard", "how are all our clients doing", "portfolio health check", "budget pacing across accounts", "which accounts are at risk". Enumerates every brand under ~/.claude-marketing/brands/ and pulls data via campaign-tracker.py, execution-tracker.py, and team-manager.py; drill into a single client with /digital-marketing-pro:performance-report or /digital-marketing-pro:client-report.

anidoodle

alexgreensh/anidoodle856

anidoodle

Code-drawn stills, drawing timelapses, films, explainers and interactive web animations in 31 styles, with composed scores. Matches a reference style, keeps characters consistent, teaches drawing. Deterministic, no generated assets.

anidoodle

alexgreensh/anidoodle856

anidoodle

attribution-model

indranilbanerjee/digital-marketing-pro856

attribution-model

Design a multi-touch attribution strategy — recommends the best-fit model for the business's sales cycle and data maturity, defines credit-distribution rules and lookback windows, maps platform-specific setup (GA4, HubSpot, Salesforce, warehouse), and documents tracking gaps and known blind spots. Triggers on "/digital-marketing-pro:attribution-model", "set up multi-touch attribution", "which attribution model should we use", "configure GA4 attribution", "how should we credit channels for conversions". Reads the brand profile and consumes the canonical model taxonomy in skills/funnel-architect/attribution-models.md; to run the models against real conversion data, pair with /digital-marketing-pro:attribution-report.

autopilot-status

indranilbanerjee/digital-marketing-pro856

autopilot-status

Campaign autopilot operations dashboard — 0-100 health scores for all active campaigns, a chronological log of auto-corrections taken (bid, budget, audience, creative, pause) with before/after metrics, the current guardrail rule table, campaigns escalated for human attention ranked by urgency, and estimated savings from automated interventions. Triggers on "/digital-marketing-pro:autopilot-status", "how is autopilot doing", "what did the autopilot change", "which campaigns need my attention", "show guardrail settings". Runs campaign-health-monitor.py for health scores, corrections history, and the savings report; reads the brand profile for KPI targets, naming conventions, and budget constraints.

backlink-gap

indranilbanerjee/digital-marketing-pro856

backlink-gap

Find referring domains that link to your competitors but not to you, ranked by an outreach-priority score (0.40 DR + 0.25 link-overlap + 0.20 traffic + 0.15 topical relevance) — outputs a four-gate quality scorecard, a 30-prospect outreach shortlist, broken-link candidates, and pre-filled outreach templates. Triggers on "/digital-marketing-pro:backlink-gap", "where are competitors getting links we aren't", "plan a link-building campaign", "quarterly backlink audit", "first 50 link targets for a new client". Consumes backlink CSV exports from the brand's connected backlink MCP, runs scripts/backlink_gap.py, reads the brand profile for DR thresholds and voice, and hands off to /digital-marketing-pro:digital-pr and /digital-marketing-pro:pr-pitch.

brand-setup

indranilbanerjee/digital-marketing-pro856

brand-setup

Create or update the brand profile every other skill reads — a quick 5-question or full 17-question interactive setup capturing identity, business model, industry and compliance markets, 4-dimension voice scales, channels, goals, and competitors, saved to ~/.claude-marketing/brands/{slug}/profile.json via scripts/setup.py. Triggers on "/digital-marketing-pro:brand-setup", "set up a new brand", "onboard a new client", "switch to another brand", "update our brand voice". Also handles brand switching (updates _active-brand.json) and field-level profile edits; run this first — all marketing skills auto-apply the resulting profile, voice samples, and compliance rules.

budget-tracker

indranilbanerjee/digital-marketing-pro856

budget-tracker

Track advertising spend pacing in real time across connected ad platforms (Google Ads, Meta, LinkedIn, TikTok) — produces a budget dashboard with daily burn rates, end-of-period projections, overspend/underspend alerts, and dollar-specific reallocation recommendations backed by CPA/ROAS context. Monitors and recommends only; it never edits platform budgets. Triggers on "/digital-marketing-pro:budget-tracker", "are we overspending this month", "how is our ad budget pacing", "track spend across platforms", "will we blow through the budget cap". Reads budget targets from the brand profile, runs scripts/ad-budget-pacer.py, and saves snapshots for trend history; pairs with /digital-marketing-pro:budget-optimizer.

campaign-orchestrator

indranilbanerjee/digital-marketing-pro856

campaign-orchestrator

Full campaign-lifecycle module — produces campaign briefs, budget allocations via three models (70/20/10, efficiency-ranked, funnel-weighted), channel-mix and media plans, UTM taxonomies with governance rules, launch checklists, ABM plans, and post-mortem reports. Plans and documents; it does not launch or edit live campaigns. Triggers on "/digital-marketing-pro:campaign-orchestrator", "build a media plan", "how should we split budget across channels", "set up UTM naming conventions", "run a post-mortem on the campaign". Reads the brand profile, guidelines, and campaign history via campaign-tracker.py; its reference docs are consumed by /digital-marketing-pro:campaign-plan rather than duplicated.

campaign-plan

indranilbanerjee/digital-marketing-pro856

campaign-plan

Generate a complete multi-channel campaign plan document — SMART objectives, audience segments with targeting criteria, channel mix with rationale, a budget allocation table with reach/cost estimates, a phased timeline from pre-launch to wrap-up, a KPI framework, and a risk register. Plans only; it does not launch or modify campaigns. Triggers on "/digital-marketing-pro:campaign-plan", "plan a campaign for our product launch", "build the Q3 campaign plan", "what channels and budget for lead gen", "draft a campaign timeline with KPIs". Reads the brand profile, guidelines, and agency SOPs, and reuses the /digital-marketing-pro:campaign-orchestrator reference docs for planning frameworks instead of re-deriving them.

churn-risk

indranilbanerjee/digital-marketing-pro856

churn-risk

Score customer segments for churn risk from behavioral signals — email engagement decline, purchase recency, usage drops, support sentiment — producing a 0-100 risk scorecard with four tiers, per-tier intervention playbooks (actions, timing windows, channels, messaging), LTV-at-risk totals, and retention-ROI prioritization. Assesses and recommends; it does not send outreach or launch campaigns. Triggers on "/digital-marketing-pro:churn-risk", "which customers are about to churn", "score our segments for churn risk", "email engagement is dropping, who is at risk", "build a retention intervention plan". Pulls behavioral data from a connected CRM MCP (Salesforce or HubSpot) or user-provided exports, runs scripts/churn-predictor.py, and reads the brand profile for lifecycle context.

client-onboarding

indranilbanerjee/digital-marketing-pro856

client-onboarding

Generate a complete onboarding package for a new marketing client — kickoff meeting agenda, 20-30 question discovery questionnaire, stakeholder map with RACI matrix, platform-by-platform access checklist, 30-60-90 day milestone plan, communication cadence, escalation protocol, welcome email template, internal team brief, risk register, and a day-by-day first-week action plan. Triggers on "/digital-marketing-pro:client-onboarding", "we just signed a new client", "build a kickoff agenda and discovery questionnaire", "30-60-90 day plan for the new account", "what access do we need from the client". Reads the brand profile, guidelines, custom templates, and agency SOPs so the package matches house process.

client-proposal

indranilbanerjee/digital-marketing-pro856

client-proposal

Draft a professional agency proposal or pitch document for a prospective client — executive summary, situation analysis, scope of services with a deliverables matrix, KPI targets with baselines and stretch goals, 2-3 pricing options, team bio structure, case-study placeholders, terms outline, and next steps, written from the agency's perspective. Triggers on "/digital-marketing-pro:client-proposal", "write a proposal for this prospect", "scope of work for a 6-month retainer", "respond to this RFP", "pitch deck outline with pricing tiers". Loads the agency's own brand profile (not the client's), plus custom templates and agency SOPs; industry benchmarks inform the KPI and pricing sections.

client-validation-document

indranilbanerjee/digital-marketing-pro856

client-validation-document

Produce the Part 5 Client Validation Document — the one true stop of the 12-Part engagement where unbiased v1 findings from Parts 2-4 are compiled into 12-25 evidence-cited finding blocks, each awaiting an ACCEPT / REJECT / EDIT / DEFER client decision, plus a paired JSON response template. Recorded responses feed the Part 6 Decision Matrix (engagement-state.py) to determine v2 re-runs. Triggers on "/digital-marketing-pro:client-validation-document", "prepare v1 findings for client review", "run part 5 client validation", "the one true stop", "record the client's validation responses". Requires Parts 3-4 marked completed in _engagement.json; reads the eight v1 core documents; pairs with /digital-marketing-pro:engagement-workflow and /digital-marketing-pro:four-core-documents.

company-cfo

coreyhaines31/makerskills849

company-cfo

Monthly CFO workflow for a company or agency — pull raw data from bank + payment processor + payroll + expense management, categorize and reconcile, compute end-of-month cash via transaction-sum method, update a scenario projector for forward forecasting, write the monthly snapshot report, surface decisions to leadership. Modes — monthly (default; the standing report), weekly (thin cash pulse), scenario (ad-hoc modeling in the projector), pickup (resume where the prior run left off). Anonymized team-scope sibling to personal-cfo (which handles personal household finances). Composes with company-brain (report gets stored + wiki-indexed there), toolify (wire company-specific data sources), loopify (schedule the monthly + weekly runs). Triggers on "/company-cfo," "/cfo," "monthly cash report," "do the CFO snapshot," "CFO monthly," "let's run CFO," "cash projection," "runway forecast," "monthly financials," "cash pulse."

decide

coreyhaines31/makerskills849

decide

When you have a decision to make and want a structured workflow that picks the load-bearing questions, walks through them, reaches a call (or "wait"), and archives the rationale for future reference. Based on the 37signals Guide to Making Decisions (38 questions) plus house additions like Q39 opportunity cost ("what does saying yes displace?"). Triages to 6–8 relevant questions per decision instead of forcing the full set. Archives every decision to ~/.config/makerskills/decide/archive/ with a revisit date so you can check later whether the call was right. Triggers on "/decide," "help me decide," "should I [X]," "I need to make a decision about," "stuck on a decision," "deciding between," "go/no-go on," "what should I do about." This is both the decision-making workflow AND the decision log — making the decision is the act of logging it.

jab-hook

coreyhaines31/makerskills849

jab-hook

Gary Vaynerchuk's jab-jab-jab-right-hook framework applied to a personal portfolio rotation on X and LinkedIn. Jabs = build-in-public + educational (value). Hooks = promo (the ask). Each property in the user's configured portfolio (see `~/.config/makerskills/jab-hook/properties.yaml`) gets a hook at least once every ~3 weeks; jabs fill the rest. Drafts go into the user's Typefully workspace via MCP. Modes — plan (7-day plan), pick-next (single post), audit (coverage report), draft (specific post). Triggers on "/jab-hook," "what should I post," "plan my socials," "next promo," "next jab," "next hook," "social rotation," "promote [property]," "BIP post," "audit my socials," "what haven't I posted about."