Claude Skills by NeverSight

Publish to your Telegram channel/group via a bot using the official Telegram Bot API — send text or photo posts, edit and delete messages, and verify the bot's access to a chat. Use when the user wants to broadcast to a Telegram channel/group with a bot token (BotFather), cross-post an article, or manage the bot's posts. Distinct from the personal-account Telegram connector.

Full personal Telegram control over MTProto (Telethon) with the user's own account — list/search chats, read & summarize history, see unread, look up contacts & chat info, download media, and send / reply / forward / edit / delete / react / send files / mark read. Use when the user mentions Telegram, a Telegram chat/group/contact, "我的 Telegram", reading/replying/forwarding/summarizing Telegram messages, their unread Telegram, or sending a file/message on Telegram.

Create, read, list, search, and manage Tencent Docs (腾讯文档) — online documents, sheets, slides, mind maps, flowcharts, smart tables, and forms — via the Tencent Docs Open API. Use when the user mentions 腾讯文档 / Tencent Docs / docs.qq.com, a docs.qq.com link, or wants to create / read / organize a doc, sheet, slide, mind map, or flowchart in their Tencent Docs space.

Manage Tencent Cloud CLS alarm policies, notice groups, shields and alarm execution logs. Use when the user asks to: list / create / modify / delete CLS alarms, enable or disable alarms, manage notice recipients (SMS / email / webhook), mute alarms during deploys, or view which alarms fired and when. For searching the underlying log content, use the companion `tencentcloud-cls` skill.

Search and analyze Tencent Cloud CLS (Cloud Log Service) logs. Use whenever the user asks to: search logs, debug API errors, trace requests by trace ID, find 5xx errors, run CQL/SQL analytics over log topics, extract structured fields. Backed by the official tencentcloud-sdk-python CLS client.

Manage Tencent Cloud COS (Cloud Object Storage) buckets and objects. Use whenever the user asks about COS / 对象存储 / Tencent Cloud bucket operations: list buckets, list objects, upload, download, delete, pre-signed URLs, calculate bucket size (du), batch delete with prefix, copy objects between keys. Backed by the official cos-python-sdk-v5.

Manage DNS records on DNSPod (Tencent Cloud's DNS service). Use when the user asks to add / update / delete A / AAAA / CNAME / MX / TXT / NS / SRV / CAA records, list records for a domain, search records, add ACME challenge / SPF / DKIM / domain-verification TXT records. Backed by the official tencentcloud-sdk-python DNSPod client.

Manage Tencent Cloud EdgeOne (CDN + edge security). Use when the user asks to: list zones, purge CDN cache (URL / prefix / hostname / all), prefetch URLs to warm edges, check purge / prefetch task status, manage acceleration domains, list / create / delete EdgeOne DNS records, inspect WAF / security configuration. Backed by the official tencentcloud-sdk-python TEO client.

Manage Tencent Cloud TKE (Tencent Kubernetes Engine) clusters and workloads. Use when the user asks to: list clusters, check cluster / node health, list pods or services, scale a Deployment, do a rolling restart, fetch kubeconfig, view recent K8s events, manage node pools. Combines the official tencentcloud-sdk-python TKE client (cluster metadata) with kubectl for in-cluster operations.

Search Telegram channels/chats and pull audience + engagement stats (subscribers, reach, ER/ERR) from TGStat via its Stat API. Use when the user wants to find Telegram channels to advertise in (esp. Russian-language / RU market), research competitor channels, or check a channel's reach/engagement before buying an ad placement.

Publish text, image, video or carousel posts to your Threads (@threads) account via the official Threads API, and read your own recent posts. Use when the user wants to post to Threads, cross-post a short update / thread, attach an image or link, or review their own Threads posts. Auth uses a Threads access token (BYOC). 支持 Threads 文本 / 图片 / 视频 / 轮播发布与自有贴文读取。

Upload videos to the user's TikTok inbox/drafts and read their TikTok profile via the Content Posting API. Use when the user wants to publish or post a generated video to TikTok, send a video to their TikTok drafts, or check their TikTok account.

Generate AI videos with Google Veo via AceDataCloud API. Use when creating videos from text descriptions, animating still images into video, upscaling/extending videos, re-shooting with new camera motion, or inserting/removing objects. Supports Veo 2, Veo 3, and Veo 3.1 models including fast variants.

Inspect Vercel projects, deployments, build logs and domains via the Vercel REST API. Use when the user mentions Vercel, a deployment that failed / is building, build or runtime logs, a preview URL, project domains, or wants to check / redeploy a Vercel project.

Publish posts to your VK (ВКонтакте) profile or community wall and read your own recent posts, via the official VK API (wall.post / wall.get). Use when the user wants to post to VK, cross-post an article for a Russian-speaking audience, or list their own recent VK wall posts with engagement. Auth uses a VK access token (community access key recommended).

Generate AI videos with Wan (Alibaba) via AceDataCloud API. Use when creating videos from text prompts or animating images into video. Supports text-to-video, image-to-video, reference video transfer, multi-resolution (480P-1080P), and optional audio.

Render and extract web page content via AceDataCloud's WebExtrator API. Use when scraping a page's final rendered HTML, or extracting typed structured data (Article, Product, Recipe, Video, Discussion, Job) plus clean markdown/text from any URL. Real headless Chromium with schema.org + LLM extraction.

Generate articles, manage drafts, publish to «发表记录», send customer-service messages, manage menus and pull stats on a WeChat Official Account (微信公众号 / 服务号 / 订阅号) via the WeChat MP server-side API. Use when the user mentions 公众号, 服务号, 订阅号, mp.weixin.qq.com, AppID/AppSecret of a WeChat Official Account, or asks to draft / publish / send a customer message via WeChat.

Read your WeCom (企业微信 / WeCom / Work Weixin) contacts, send app & group messages, create and read WeDoc docs/smart sheets, and manage schedules (日程) and meetings (会议) via the WeCom server-side API as a self-built app. Use when the user mentions 企业微信, WeCom, 通讯录成员/部门, 应用消息, 群机器人/应用群聊, 企业微信文档/智能表格, 企业微信日程 or 会议, or a qyapi.weixin.qq.com call.

Read and post on 微博 / Weibo (weibo.com) with the user's own login cookies (BYOC) — list their recent posts with repost/comment/like counts and publish a new 微博. Use when the user mentions 微博 / Weibo, "我的微博", reading their post engagement, or 发微博 / posting to Weibo.

Publish and manage posts on a self-hosted WordPress site via the WordPress REST API. Use when the user mentions WordPress, wp-admin, publishing / updating a blog post, managing categories or tags, or uploading media to their own WordPress site.

Read & act on X (Twitter) with the user's own login cookies (BYOC) — post tweets (text / images / video / threads / replies / quotes), search tweets & users, read timelines and single tweets, like / retweet / follow / delete, and see trends. Use when the user mentions X / Twitter, 发推 / 发推特 / 推特, "我的 Twitter", posting to X, searching X, or reading their X timeline.

Search YouTube, read your own channel and uploaded videos (stats, comments), and upload new videos via the YouTube Data API v3. Use when the user mentions YouTube, "my channel", "my videos", searching YouTube, video views / likes / stats, uploading a video to YouTube, or checking how a published video is doing.

Read and publish on Zhihu (知乎) with the user's own login cookies (BYOC) — list their published articles with vote/comment stats, inspect one article, and publish a new article. Use when the user mentions 知乎 / Zhihu, "我的知乎文章", reading their article stats (点赞/评论), or publishing/发文 to Zhihu.

Audit API routes against shared types — scan routes, plugins, and types for mismatches. Read-only, no changes. Use before PRs, after adding routes, or for periodic API contract validation.

Use when architecting OCI solutions, migrating from AWS/Azure, designing multi-AD deployments, evaluating Always-Free tier, or avoiding OCI anti-patterns. Covers VCN CIDR immutability, AD-specific subnet deprecation, Security List vs NSG confusion, Cloud Guard auto-remediation danger, tenancy-specific AD name prefixes, compartment hierarchy, and Flex shape cost savings.

Use when given a bug report, failing test, stack trace, or CI failure that needs diagnosis and repair. Autonomously diagnoses root cause, implements minimal fix, verifies correctness, and commits. Keywords: fix bug, failing test, stack trace, CI failure, debug error, broken test.

Use when working with Cloudflare Tunnel or Access - tunnel setup, authentication configuration, 502 Bad Gateway errors, Docker/Kubernetes deployment, service token management, private network routing (SSH/RDP/databases), WebSocket/gRPC connection issues, replica scaling problems, WARP routing, Terraform/IaC automation, local development with quick tunnels, audit logging setup, compliance requirements (SOC2/HIPAA), or advanced network debugging. Keywords - cloudflared, 502 error, service token...

Use when launching OCI compute instances, troubleshooting out-of-capacity or boot failures, optimizing compute costs, or handling instance lifecycle. Covers shape selection, capacity planning, service limits, instance principal auth, and production gotchas. KEYWORDS: compute, instance, shape, capacity, OCPU, boot volume, launch, flex.

Use when creating Autonomous Databases, troubleshooting wallet connection failures, managing PDBs, optimizing ADB costs, or selecting clone types. Covers connection service cost impact, password complexity failures, stop/start cost trap, clone type consequences, Always-Free limits, and PDB lifecycle gotchas.

Audit project documentation against the codebase and fix drift. Run before PRs or after major changes. Compares documented architecture, test counts, and file paths against actual state.

Use when user asks to find, install, or search for agent skills. Also use when user asks 'can you do X' or 'is there a skill for X' where X is a specialized capability. Keywords: install skill, find skill, npx skills, skills.sh, extend agent, add capability.

Use when optimizing OCI costs, investigating unexpected bills, right-sizing resources, or planning Universal Credits commitments. Covers OCI-specific hidden cost traps (orphaned boot volumes, reserved IPs, stopped resources), Universal Credits non-transferability gotcha, shape migration savings, free tier maximization, and egress cost surprises. Keywords: cost, billing, budget, ECPU, boot volume, reserved IP, Universal Credits, free tier, egress, shape, FinOps.

Web scraping and search CLI returning clean Markdown from any URL (handles JS-rendered pages, SPAs). Use when user requests: (1) "search the web for X", (2) "scrape/fetch URL content", (3) "get content from website", (4) "find recent articles about X", (5) research tasks needing current web data, (6) extract structured data from pages. Outputs LLM-friendly Markdown, handles authentication via firecrawl login, supports parallel scraping for bulk operations. Automatically writes to .firecrawl/...

Run all quality gates across the entire codebase and report results. Headless — no analysis, just execute and print. Use for pre-PR validation, phase completion, or routine health monitoring.

Detect and fix AI writing patterns including overused phrases (testament to, pivotal, landscape, delve), structural tells (rule of three, em dash overuse, negative parallelisms, copula avoidance), promotional language, and vague attributions. Use when user asks to "make text sound human", "remove AI tells", "humanize writing", mentions patterns like "too many dashes" or "sounds like ChatGPT", or requests natural/conversational tone. Triggers: AI-generated, humanize, writing style, natural wr...

Use when writing IAM policies, troubleshooting 403/404 permission errors, setting up dynamic groups, or debugging IDCS federation. Covers OCI-specific policy syntax gotchas, principal type confusion, compartment hierarchy rules, verb hierarchy, and common authorization failures. KEYWORDS: IAM, policy, permission denied, dynamic group, compartment, IDCS, federation, 403, 404.

Full feature pipeline — pre-flight checks, TDD cycle, scope guard, quality commit. Combines pre-flight + tdd + scope-check + quality-commit into one flow. Use when implementing a feature, adding an endpoint, or building any non-trivial code change.

Use when writing Terraform for OCI, troubleshooting provider errors, managing state files, or implementing Resource Manager stacks. Covers terraform-provider-oci gotchas, resource lifecycle anti-patterns, state drift/corruption recovery, authentication precedence, and OCI Landing Zones. KEYWORDS: Terraform, OCI provider, state, Resource Manager, lifecycle, drift, import, 409, availability domain, boot volume, flex shape.

Use when designing multi-tenant OCI environments, standing up landing zone Terraform stacks, enforcing Security Zones, or planning hub-spoke network topology. Covers OCI-specific compartment hierarchies, multi-tenant IAM decision trees, Security Zone automation, CIS Foundations compliance, and DRG routing. Keywords: landing zone, compartments, Security Zone, hub-spoke, DRG, CIS, multi-tenant, tenancy, IAM policy.

Use when bulk-migrating import paths, renaming workspace packages, or reorganizing modules across many files in a monorepo. Uses scripted bulk operations with verification gates and atomic commits. Keywords: migrate imports, rename package, bulk import path change, module reorganization, monorepo refactor.

Use when setting up OCI metrics, alarms, or log collection, or troubleshooting missing data and silent alarms. Covers metric namespace naming, MQL dimension requirements, alarm missing-data handling, Service Connector IAM gaps, and Cloud Guard integration. KEYWORDS: monitoring, alarm, metric, MQL, namespace, log, Service Connector, Log Analytics, Cloud Guard, missing data, oci_computeagent.

Use when designing OCI VCN topology, troubleshooting connectivity failures, configuring Service Gateway to eliminate egress costs, choosing between Security Lists and NSGs, debugging transitive routing failures, or sizing Load Balancer subnets. Covers Service Gateway free egress, VCN CIDR immutability, peering non-transitivity, Security List hard limits, and stateful rule behavior.

Use when creating or editing Oracle-branded PowerPoint presentations, pitch decks, or technical slides. Applies Oracle design standards with cognitive science rules for audience retention. Triggers on: 'deck,' 'slides,' 'presentation,' .pptx filenames, 'Oracle presentation,' 'CloudWorld deck,' 'pitch deck.' Keywords: pptx, PowerPoint, Oracle brand, CloudWorld, slides, deck.

Use when the user asks to \"find OCI skills\", \"route Oracle Cloud work\", \"install the OCI skill pack\", \"review OCI skill ownership\", or \"separate Oracle skills\".

Use when managing Oracle Autonomous Database on OCI, troubleshooting performance, optimizing costs, or implementing HA/DR. ADB-specific gotchas, cost traps, SQL_ID debugging workflows, auto-scaling behavior, and version differences (19c/21c/23ai/26ai). Keywords: ADB, Autonomous Database, ECPU, auto-scaling, SQL_ID, wait events, ORA- errors, wallet, BYOL.

Use when setting up Better Auth with Oracle IDCS/OCI IAM, configuring OIDC callback URLs, trusted origins, provider bootstrap order, or sharing an auth model between Fastify and Next.js. Entry point for the full auth foundation — routes to bridge or provisioning skills when narrowed. Keywords: Oracle IDCS, OCI IAM, Better Auth, OIDC, Fastify auth, Next.js auth, callback URL, trusted origins, provider bootstrap.

Use when mapping IDCS claims to org membership after OAuth login succeeds. Covers mapProfileToUser, session.create.before, session.create.after hooks, MERGE INTO upserts, tenant-org mapping, and first-admin bootstrap. Keywords: IDCS groups, org_members, provisioning, session hooks, tenant map, MERGE INTO.

Coordinate parallel agent teams to execute multi-task implementation plans. Use when running phase tasks from the task plan, parallelizing independent implementation work, or executing custom plan files. Supports interactive (in-session TeamCreate agents) and headless (claude -p fire-and-forget processes) execution modes with task ledger tracking, heartbeat monitoring, budget control, and wave-based quality gates.

Scaffold a new development phase with branch, test shells, and roadmap entry. Use when starting a new feature phase or sprint to set up the development environment consistently.