DevOps & Infra

davie521 Skill

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration. Use when writing Dockerfiles or compose files, hardening images, or debugging container networking and volume issues.

creatorland Skill

A terse recurring standup digest of what MOVED in your creator outreach since last run — new replies (interested/question/declined), new yeses, stalls approaching Day-7, new opt-outs, and the single most important "do this next." Use when the user says "outreach standup", "what moved in my outreach since yesterday", "daily outreach digest", or "any new replies/yeses today". Read-only, free, schedulable. For the full board, use connection-pipeline-tracker.

creatorland Skill

Live pipeline board of every creator outreach this brand has running — grouped by lifecycle stage (queued → delivered → replied → accepted → opted-out/expired), with action-needed buckets surfaced and touches-sent + next-touch per outreach. Use when the user says "show my outreach pipeline", "status of my connections", "outreach board", "who replied / who's pending", or "track my creator outreaches". Read-only and free — reads the connection tools, never reaches anyone. Deliverable is a scannable markdown board.

imtangyujing Skill

量子位快讯写作skill。当需要基于官方信源（OpenAI、Google、AWS、Anthropic 等厂商的官方博客、发布公告、技术报告）快速产出一篇时效性强的中文资讯稿时使用。触发词包括但不限于：写快讯、出快讯、资讯稿、新模型发布稿、官方博客转述、把这个blog写成稿子、帮我转述这篇公告、XX发了新模型写一下。也适用于用户丢过来一个官方博客链接、公告PDF、发布会文字稿说「出个快讯」的场景。核心特征是100%忠于信源的纯转述、严格跟随用户提纲的小标题结构、1000-2000字。不要用于：有人格化表达的评论长文（用 khazix-writer 或 Jay Writer）、商稿（用 qbit-commercial-article）、深度解读和论文解读（用 tech-blog-writer）。

ulpi-io Skill

Local dev proxy that gives projects named HTTPS domains on .test with valid TLS. Use when setting up local development environments, running dev servers, sharing localhost publicly via tunnels, or managing Docker Compose services with HTTPS. Handles framework detection (30+ frameworks), port management, DNS, certificates, and public tunnels. Trigger on: "run my dev server", "set up HTTPS locally", "share localhost", "expose my app", "local dev proxy", "tunnel", ".test domain", or when helping users start/configure web projects.

nemori-ai Bundle

通过协作对话挖出用户真实业务痛点、在动手实现前先把需求搞对的心智——本仓 dev 流的需求发现闸（取代 superpowers:brainstorming，让 cc-master 的 dev meta-skill 自洽不外依赖）。Use when: 开始本仓任何 feature / skill / 行为改动之前（动第一下实现之前，无论请求看起来多简单）；请求以一个猜出来的方案形态到来而底层问题没说出口（"加个按钮" / "给我做个 X"）；要建模或动手却说不清真实需求、指不出一个它真在疼的具体实例；为一个新问题空间和用户共创词汇；一个请求捆了多个独立子系统、动手前要先拆；作为 master orchestrator 跑前台需求发现对话（挖需求是指挥自己的活，绝不外包）。Do NOT use: 已确认需求后写一个 skill 的 body → cc-master-skillsmith；判要不要建 skill / 放哪 / 会不会重叠 → curating-skill-portfolios；度量一个已写好的 skill → grounding-skill-evals；写 workflow 脚本怎么 parallel/pipeline → authoring-workflows；驱动一个已批准的 goal 到完成（编排执行 loop）→ master-orchestrator-guide。

nexadevapp Skill

Writes a dated software engineering report for the current repository and adds it as a new entry to docs/software-engineering-report.md. The report covers requirements traceability, quality assurance (the testing pyramid), architecture (existing documentation plus generated C4, 4+1, sequence, and ER diagrams in Mermaid), infrastructure, and CI/CD. Works on any repository and any tech stack. This skill must only be invoked explicitly via /software-engineering-report — never inferred from user messages.

hack23 Skill

CI/CD pipeline security, supply chain security, SLSA compliance, artifact signing, dependency scanning

hack23 Skill

AWS security best practices, VPC security, IAM, KMS, CloudTrail, GuardDuty for CIA platform deployment

hack23 Skill

Data pipeline design, ETL processes, Spring Integration patterns, batch processing for political data

chocholous Bundle

Validate, test, compare, and monitor your own Apify Actors across the full build-to-production lifecycle. Covers preflight input validation, multi-Actor pipeline validation, A/B comparison of two Actors for a production switch, post-run output validation (silent data failures), deploy-gate regression detection, fleet-wide quality scoring, PII/GDPR/ToS pre-publish risk triage, and fleet profit and next-action analytics. Most of these Actors return a stable decision enum (act_now / monitor / ignore, or switch_now / canary / no_call) that CI gates and AI agents can branch on without parsing prose; the fleet-wide Actors return a scorecard or prioritized action queue. Use when someone wants to test an Actor before publishing, validate an input or pipeline, decide between two Actors, catch broken output, gate a deploy, audit Actor quality, check compliance risk, or analyse fleet revenue.

chocholous Bundle

Turn Google Jobs into a job search API for your app, AI agent, or alerts pipeline with the Apify Google Jobs Scraper Actor (johnvc/Google-Jobs-Scraper). Query by role and location with country, language, and radius filters, and get fresh structured listings back, including title, company_name, source platform, posted_at, schedule_type, and direct apply_options links, ready to dedupe by job_id and serve as a feed. Use when the user wants a job search api, a job postings API or job listings feed for an application or AI agent, wants to refresh a job board or job alerts programmatically, or asks which job search sites have an API. Pay-per-page billing, MCP-ready for Claude and other AI agents.

chocholous Bundle

Build a local-business lead database from Google Maps in one Apify pipeline — search by target audience + geography, enrich each place with company contacts (from website), leads enrichment (people with names/emails/phones/LinkedIn), Instagram + Facebook profile data, and optionally reviews for lead scoring. For places that come back without named contacts, escalate to apify/ai-web-scraper to pull owner / decision-maker names from the business website. Backfill missing phones via scalelist/phone-finder and missing emails via scalelist/email-finder. Deliver a deduplicated CSV. Use whenever the user asks to build a lead list from Google Maps, scrape local businesses, generate B2B leads by city/industry, find owner/decision-maker contacts for restaurants / dentists / gyms / hotels / any local vertical, score leads by review volume or rating, or asks for a "Google Maps lead-gen pipeline".

chocholous Bundle

Get YouTube transcripts as structured JSON with a hosted YouTube transcript API (the Apify Actor johnvc/YoutubeTranscripts). Pass one video URL or a batch array and get back non_timestamped text, timestamped snippets, language metadata, and optional SRT, VTT, and plain text formats, plus video title, channel, and view count. Works with standard videos and Shorts, handles language preference and translation, and runs from cloud IPs without IpBlocked errors. Use when the user wants a youtube transcript api, needs to get or download a YouTube transcript or subtitles, asks to extract the transcript from a YouTube video, or wants captions as JSON, SRT, or VTT. Pay-per-video billing, MCP-ready for Claude and other AI agents.

chocholous Bundle

Set up a recurring buying-signal detection pipeline that finds companies showing buying intent across three signal types — job postings (hiring for the persona), fundraising events (recent raises), and LinkedIn content (pain-point posts, hiring announcements) — then aggregates results into a deduplicated leads.csv with the signal source, evidence URL, and detection timestamp per row. Split-schedule architecture — Apify Actor Tasks pull raw data on their own cadence, a Claude-side aggregation task normalizes, deduplicates against a blacklist, and appends new leads with a weekly-idempotent guard. Use when the user says "find companies with buying signals", "detect intent signals for outbound", "set up a weekly lead pipeline", "monitor hiring signals for lead gen", "track startup funding leads", "find LinkedIn buying signals", "schedule Apify Actors for prospecting", "build a signals-based lead list", or "set up buying-intent monitoring for my ICP".

chocholous Skill

Build job-market intelligence from public job boards using Apify Actors. Use when the user asks to analyze hiring demand, find companies hiring for a role, compare job-market trends, scrape LinkedIn Jobs, Google Jobs, Indeed, or Glassdoor, extract required skills from postings, rank target companies, benchmark salaries, or create a focused job-search pipeline.

ferroxlabs Skill

HR orchestrator for SMBs. Routes job descriptions, interview questions, onboarding, performance reviews, 1-on-1s, handbook sections, offer letters, offboarding, comp banding, PIPs, terminations, accommodations, leave, RIF, and pipeline reports to the right sub-skill. Templates only - not employment-law advice; outputs must be reviewed by HR counsel.

davie521 Skill

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

davie521 Skill

Restate requirements, assess risks, create a step-by-step implementation plan, and WAIT for explicit confirmation before touching any code. On approval the FIRST action MUST be creating an isolated git worktree (never edit the main worktree); implement inside it; after implementation hand off to /cpr (PR pipeline) or code review. Use when starting a feature, architectural change, complex refactor, multi-file change, or when requirements are unclear.

davie521 Skill

Deployment strategies (rolling, blue-green, canary), CI/CD pipeline patterns, health checks and Kubernetes probes, rollback playbooks, and production readiness checklists for web applications. Use when planning a release, setting up CI/CD, or preparing rollback. Dockerfile and Compose specifics live in docker-patterns.

iblai Skill

Platform application gate — turn membership into an apply/review process. Applicant apply/renew/submit flows (drafts, file uploads, fees, withdrawal), reviewer pipeline (list, stats, detail, per-student decisions, notes, waivers, admin override submit, blocks), post-acceptance placement tests and course assignments, student account provisioning (invite/link), and application form authoring (schema, decision templates, fees, renewal windows). Use when wiring up an admissions/enrollment application flow, working the review pipeline, deciding applications, or managing application forms.

iblai Skill

Programmatically generate, edit, and publish courses via the ibl.ai Course Creation API — create a task, generate an AI outline, run the full creation pipeline, then read the course outline, full structure, and draft unit content. Use to author courses from the API.

iblai Bundle

Deploy and self-host the ibl.ai platform infrastructure — AWS single/multi-server architecture, the golden-AMI staging launch pipeline, the iblai-infra-cli (Terraform + Ansible) provisioner, edX LMS SSO identity providers (Google/Microsoft/Apple/OpenID Connect), and standing up OpenClaw/NemoClaw agent-sandbox gateway servers. This is the ops/self-hosting reference (how the platform is deployed on infrastructure you control), not api.iblai.app REST calls. For the API side of claw instances, see /iblai-api-agent-sandbox.

yenhao-huang Bundle

Use when the user asks to create, set up, build, update, repair, validate, or run an agent sandbox Docker environment for Codex and Claude. Trigger on requests such as "建立 sandbox", "建立 codex sandbox", "create a sandbox", "create a codex sandbox", "幫我開 sandbox", "make a sandbox for Codex", "make a sandbox for Claude", sandbox mounts, sandbox SSH, Docker-in-Docker, custom skills/hooks bootstrap, or project-specific sandbox setup such as Pretrieval. Create or update a project-local `.runtime/build_codex_sandbox.sh` script from this skill's bundled `src/` files. Do not execute Docker commands unless the user explicitly asks.

yenhao-huang Bundle

Create, configure, validate, or repair Drone CI for a Git repository. Use when the user asks to add Drone CI, initialize `.ci`, start a Drone server or Docker runner, connect Drone to Gitea webhooks, create `.drone.yml`, define pipeline steps or triggers, or standardize CI docs, scripts, and tests.

yenhao-huang Bundle

Install, configure, validate, integrate, stop, reinstall, or uninstall a local self-hosted Langfuse deployment with Docker Compose, including Hermes observability setup. Use for Langfuse local deployment, first-run initialization, Docker Compose troubleshooting, Hermes Langfuse traces, Windows Hermes venv issues, and safe Langfuse cleanup.

yenhao-huang Bundle

Install, start, integrate, diagnose, validate, stop, or uninstall Tailscale inside an existing Docker or LXC container while keeping the host out of the tailnet. Use for container-to-cluster connectivity, userspace networking, /dev/net/tun capability checks, Tailscale Serve, proxy access, and safe removal or complete cleanup.

nemori-ai Bundle

当你要调用 Workflow 工具，或要写 / 调试 / 启动一个 Claude Code dynamic-workflow 脚本时用——author / debug / launch a Claude Code dynamic-workflow script，当你要写 workflow 脚本时——哪怕你自觉已经懂这套 API。当你发现自己在猜 workflow 引擎的 determinism 或 resume 规则、没查 shape 就伸手够 parallel() / pipeline()、想手写一个 validation linter、或刚被 harness 报错正要 relaunch 时用。先查再猜，别等跑挂了才来。

nemori-ai Skill

当你在 Codex 下想写 / 调试 / 启动 cc-master 的 workflow 脚本、或想套用 Claude Code dynamic-workflow API 时用——这是 Codex adapter 的 unsupported stub。Triggers: 在 Codex 里提到 Workflow 工具、`agent()` / `parallel()` / `pipeline()` / `phase()` / `workflow()`、后台 task id、workflow resume/cache/budget、"能不能把 Claude Code workflow 直接搬到 Codex"。Do NOT use when 只是做普通 Codex 任务规划、普通 shell 脚本、或使用已验证的 Codex 产品面并行能力；本 stub 只负责阻止把 Claude Code Workflow API 当作 Codex 可用机制。启用真正 Codex 版前必须验证 deterministic multi-agent workflow execution、后台执行与完成通知、resume/cache 语义、脚本 runtime/API 形状、资源上限与 budget 报告。

nemori-ai Skill

当你在 Cursor IDE Agent 下想写 / 调试 / 启动 cc-master 的 workflow 脚本、或想套用 Claude Code dynamic-workflow API 时用——这是 Cursor adapter 的 unsupported stub。Triggers: 在 Cursor 里提到 Workflow 工具、`agent()` / `parallel()` / `pipeline()` / `phase()` / `workflow()`、后台 task id、workflow resume/cache/budget、"能不能把 Claude Code workflow 直接搬到 Cursor"。Do NOT use when 只是做普通 Cursor 任务规划、普通 shell 脚本、或使用已验证的 Cursor 产品面并行能力（Task + background shell + `/loop`）；本 stub 只负责阻止把 Claude Code Workflow API 当作 Cursor 可用机制。启用真正 Cursor 版前必须验证 deterministic multi-agent workflow execution、后台执行与完成通知、resume/cache 语义、脚本 runtime/API 形状、资源上限与 budget 报告。

nemori-ai Skill

当你在 kimi-code 下想写 / 调试 / 启动 cc-master 的 workflow 脚本、或想套用 Claude Code dynamic-workflow API 时用——这是 kimi-code adapter 的 unsupported stub。Triggers: 在 kimi-code 里提到 Workflow 工具、`agent()` / `parallel()` / `pipeline()` / `phase()` / `workflow()`、后台 task id、workflow resume/cache/budget、"能不能把 Claude Code workflow 直接搬到 kimi"。Do NOT use when 只是做普通 kimi 任务规划、普通 Bash 脚本、或使用已验证的 kimi 后台并行能力（内置 subagent 角色 coder/explore/plan/general + Agent Swarm + 后台 Bash 任务）；本 stub 只负责阻止把 Claude Code Workflow API 当作 kimi 可用机制。启用真正 kimi 版前必须验证 deterministic multi-agent workflow execution、后台执行与完成通知、resume/cache 语义、脚本 runtime/API 形状、资源上限与 budget 报告。

cookiemonsterdev Bundle

Use when users ask how to build, configure, index, query, filter, scale, or troubleshoot Pinecone vector database applications, including serverless indexes, namespaces, upsert/query/update/delete operations, metadata filtering, hybrid search, reranking, Pinecone Assistant, or SDKs, especially when they need official Pinecone documentation, exact links, or docs-grounded guidance.

cookiemonsterdev Bundle

Use when users ask how to install, configure, model, query, secure, scale, repair, monitor, migrate to, or troubleshoot ScyllaDB clusters, ScyllaDB Cloud, Alternator, CQL applications, shard-aware drivers, CDC, nodetool, cqlsh, Manager, Monitoring Stack, Operator, or DynamoDB-compatible APIs, especially when they need official ScyllaDB documentation, exact links, or docs-grounded guidance.

cookiemonsterdev Bundle

Use when users ask how to build, configure, query, filter, index, scale, deploy, or troubleshoot Weaviate vector database applications, including collections, schema, CRUD operations, similarity/hybrid/generative search, multi-tenancy, replication, model provider integrations, client libraries, or self-hosted vs Weaviate Cloud deployment, especially when they need official Weaviate documentation, exact links, or docs-grounded guidance.

cookiemonsterdev Bundle

Use when users ask how to write, explain, configure, secure, optimize, or troubleshoot GitLab CI/CD pipelines, `.gitlab-ci.yml` syntax, stages, jobs, runners, variables, inputs, expressions, artifacts, caches, environments, deployments, CI/CD components, parent-child pipelines, merge request pipelines, or pipeline schedules, especially when they need official GitLab documentation, exact links, or docs-grounded YAML guidance.

cookiemonsterdev Bundle

Use when users ask how to install, configure, write, plan, apply, import, destroy, test, secure, or troubleshoot Terraform infrastructure as code, including HCL syntax, providers, modules, state, workspaces, backends, variables, outputs, data sources, provisioners, HCP Terraform, Terraform Enterprise, or the Terraform Registry, especially when they need official HashiCorp Terraform documentation, exact links, or docs-grounded guidance.