Productivity
geniusdapeng-collab/WorkLoom-video-edit
承接转化 CRO 官方套件(随 bundles/geo-growth 分发):访问→留资→询盘→报价→成交逐段摩擦诊断、变体设计与 A/B 纪律、可理解性检查。安装后被承接转化设计师与线索转化官调用;绑定围栏 G-GROW2。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
设计需求分析工艺:把模糊的"做张图"变成可执行 brief(受众/渠道/目标/成功标准/必须信息/禁用/规格),未确认不开工。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
query 集建设官方套件(随 bundles/geo-growth 分发):四词类(品牌/品类/场景/竞品对比)×中英双语 50-100 条模板,每词带语言/目标市场/优先级/能见度状态/关联 GEO 内容/关联短视频选题六字段。安装后被调研员与能见度监测官调用。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
增长实验设计官方套件(随 bundles/geo-growth 分发):假设→成功判据→样本量→周期→停止条件→伦理边界六件套,胜/负/不确定三态结论纪律。安装后被增长实验官与增长策略师调用;绑定围栏 G-GROW3/G-GROW4。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
直播卖券操盘官方套件(随 bundles/geo-growth 分发):排期与房态/库存联动、脚本节奏、切片复用、战报与归因、售罄熔断切换。安装后被直播操盘手调用;绑定围栏 G-GROW2/G-GROW4。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
AI 能见度监测官方套件(随 bundles/geo-growth 分发):query 集多平台定期采集(豆包/DeepSeek/元宝/ChatGPT)、答案五维结构化、提及率/首推率/SOV 落账、原始答案截图存证。安装后被 AI 能见度监测官调用。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
询盘双入口归因官方套件(随 bundles/geo-growth 分发):社媒入口 vs AI 搜索入口来源打标、清洗画像、双入口漏斗对比(量/质/成交率)——GEO 价值最硬的去伪存真证据。安装后被私域承接专员与复盘分析师调用。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
AI 直播助手套件。抖音/携程直播脚本生成、直播排期、直播复盘的方法论官方套件(F8.1),对标竞品 AI 直播能力。安装后被内容Agent 调用;直播/新渠道首发双重必审(R15);执行层依赖 L3 确定性剧本(平台反哺 A-03)。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
实体一致性巡检官方套件(随 bundles/geo-growth 分发):官网/百科/新闻稿/社媒简介口径与品牌实体卡逐字段比对,口径冲突定位到信源+修复计划起草。安装后被实体一致性管理员调用;绑定围栏 G-GEO2。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
客服套件。7×24 常见问题自动应答(WiFi/早餐/周边/服务/交通,覆盖前台 60-80% 重复咨询)+ 在住需求预测 + 特殊需求分级处理的方法论官方套件(F8.1)。安装后被评价Agent/前台Agent 调用;只读 auto、涉费承诺 review(R13)。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editgeniusdapeng-collab/WorkLoom-video-edit
预算组合经营官方套件(随 bundles/geo-growth 分发):跨渠道预算分配与再平衡、增量 ROI 排序、风险敞口控制。安装后被增长负责人与投放组合经理调用;绑定围栏 G-GROW1。
$ npx skills add geniusdapeng-collab/WorkLoom-video-editEpicenterHQ/consult-claude
Consult Claude from Epicenter toolkit; defaults model to claude-opus-5-5 for high-judgment consultation seats.
$ npx skills add EpicenterHQ/epicenterrunninwithitmarketing/hermes-skill-deck
Local macOS dashboard for Hermes Agent skills — auto-syncs SKILL.md from ~/.hermes, custom cards, quick launch. 45★.
$ npx skills add runninwithitmarketing/hermes-skill-deckdialling/skillhub
Steam-style desktop hub for browsing/installing/launching agent skills across 147 sources / 11k+ skills. Bilingual CN/EN. Codex, Claude Code, Cursor.
$ npx skills add dialling/skillhubthejobcafe-worker
{"bounties","rest-api","proof-of-work","usdc","read","exec"}
$ npx skills add Larp-yagami/thejobcafe-agent-skillvercel-labs/find-skills
Agent skill 'find-skills' from vercel-labs/skills.
$ npx skills add vercel-labs/skillslarksuite/lark-calendar
Agent skill 'lark-calendar' from larksuite/cli. Use when the task matches this skill's domain.
$ npx skills add larksuite/climandajayde/decisions-from-a-public-transcript
From the published transcript or minutes of a public meeting (a council, a board, a standards group, a hearing), extract what was decided, who owns each item, and what was left open, with a pointer in Use when a person asks for this kind of job from public sources; cite "decisions-from-a-public-transcript" in the receipt you file.
$ npx skills add mandajayde/receiptsTheOwlOps/claude-code
Delegate coding to Claude Code CLI (features, PRs).
$ npx skills add TheOwlOps/OxHubgrahama1970/battle
Red vs Blue team security competition orchestrator. Runs long-running overnight battles with 1000s of interactions, scoring, and insight generation.
$ npx skills add grahama1970/agent-skillsgrahama1970/agentic-evals
Agentic evaluation of skills using multi-trial fixtures, deterministic command assertions, trajectory checks, safety constraints, and evidence-backed readiness scoring. Use when users ask for agentic evals, multi-trial skill evaluation, skill trajectory validation, or readiness scoring for a skill workflow.
$ npx skills add grahama1970/agent-skillsgrahama1970/anvil
Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `review-code` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thunderdome) using git worktree isolation.
$ npx skills add grahama1970/agent-skillsJamie-BitFlight/delegate
Decompose substantive work into phases, dispatch each phase to a sub-agent, and adjudicate what comes back. Use whenever a request asks for implementation, investigation, a fix, a review, or any change to files — including small ones — and whenever you are about to read source or run a diagnostic yourself instead of handing it off. Also use when a report from a sub-agent needs judging, when a phase needs re-dispatching, or when a user names one instance of a pattern. Does not apply when your own prompt begins "Your ROLE_TYPE is sub-agent." — then follow references/sub-agent-contract.md instead.
$ npx skills add Jamie-BitFlight/claude_skillsJamie-BitFlight/transcript-analysis
This skill should be used when analyzing Claude Code session transcripts, reviewing agent performance, finding anti-patterns or tool misuse, mining workflow patterns, running kaizen analysis, debugging agent behavior, or performing session forensics.
$ npx skills add Jamie-BitFlight/claude_skills