DevOps & Infra

mardab96 Skill

Finds where qualified leads stall before becoming pipeline. Use when leads look healthy but pipeline does not grow, or when the same stage keeps swallowing deals.

ruicore Bundle

Archive Feishu Wiki or Docs pages and their linked documents locally, preserve offline images at the best available source quality, and consolidate verified duplicates when requested. Use for document downloads, blurry-image re-export, or keeping only high-quality archive images; not for cloud publishing or bug investigation.

ruicore Bundle

Turn a local authoritative Markdown design or conclusion into a reader-ready Feishu technical document using the authenticated browser, including editorial restructuring, native blocks, diagrams, table layout, safe cloud editing, and publish verification. Use when the user asks to write, publish, or synchronize a local Markdown technical document to Feishu; do not use for ordinary Markdown editing without Feishu delivery.

hugobowne Bundle

Turns a photo of a person into a short 8-bit pixel-art video via a two-step pipeline. Gemini stylizes the photo as an 8-bit still, then Replicate's seedance-2.0 animates that still into an MP4. Use when the user supplies a portrait photo and asks for an "8-bit video", "pixel art animation", or "retro video game version" of themselves. Trigger even if they only mention one of the two steps.

hugobowne Bundle

Design and author Hermes Workflows with typed inputs/outputs, agent/bash/ask/parallel/pipeline/goal primitives, Review Queue gates, artifacts, and verification receipts. Use when creating or modifying workflow definitions.

cryptopafi Skill

Optimize any prompt or text using the PromptForge pipeline. Default behavior for opt, /opt, or [$opt] followed by a task is optimize-and-execute with a detailed preview. Use opt explain, /opt --prompt-only, or optimize only when the user only wants the improved prompt.

iopsystems Bundle

Use when drawing or materially revising a dataflow or pipeline diagram for a program that already exists in code — a DAG, a processing chain, a stream topology, a service graph. Triggers include "diagram the pipeline", "show the dataflow", "chart the DAG", "visualize how the data moves", or a design doc or PR needing a picture of a running system. Symptoms include a hand-maintained diagram that no longer matches the code, a legend that disagrees with the chart, a glyph reused for two kinds of thing, a diagram that silently omits a node nobody classified, or a picture that is a screenshot rather than a source file.

iopsystems Bundle

Draw a dataflow or pipeline diagram for a program that already exists in code — a DAG, a processing chain, a stream topology, a service graph. Use when asked to "diagram the pipeline", "show the dataflow", "chart the DAG", "visualize how the data moves", "make a graph of the program", or when a design doc or PR needs a picture of a running system. Symptoms that this skill applies: a hand-maintained diagram that no longer matches the code, a chart whose legend disagrees with the chart, a glyph reused for two different kinds of thing, a diagram that silently omits a node nobody classified, a legend placed by eye that overlaps an edge, or a picture that is a screenshot rather than a source file.

aiagentwithdhruv Bundle

Query Skool community content using RAG pipeline with vector search. Use when user asks to search Skool knowledge, find community answers, or query Skool content.

aiagentwithdhruv Skill

Deploy execution scripts to Modal cloud. Use when user asks to deploy to Modal, push code to cloud, or update Modal functions.

yafet-dev Bundle

Advanced SSRF testing methodology for bug bounty and application security work. Use when testing or reviewing server-side request forgery, URL preview APIs, import/export APIs, webhooks, callbacks, file converters, image fetchers, analytics reports, OAuth controllers, cloud metadata access, internal service reachability, DNS rebinding assumptions, redirect bypasses, blind SSRF, SSRF-to-file-read, and SSRF chains to credentials, internal APIs, or RCE.

yafet-dev Bundle

Advanced API security testing methodology for bug bounty and application security work. Use when testing or reviewing REST APIs, GraphQL APIs, mobile APIs, internal or undocumented APIs, exposed infrastructure APIs, API key or token leaks, broken API authentication or authorization, BOLA/IDOR, sensitive response data, CORS/cache/CSRF flaws, SSRF through preview/export APIs, injection through API parameters, cloud or Kubernetes/Docker/control-plane APIs, webhook/callback APIs, and API-driven account, tenant, admin, file, billing, or operational workflows.

yafet-dev Bundle

Advanced subdomain takeover testing methodology for bug bounty and application security work. Use when testing or reviewing dangling DNS records, unclaimed cloud/CDN/storage/app-service resources, CloudFront/Heroku/GitHub Pages/Azure/S3/Fastly-style takeovers, authentication bypass through trusted subdomains, cookie scope abuse, OAuth redirect allowlist abuse, staging subdomain takeover, and chains where a controlled subdomain can steal tokens, host trusted content, bypass auth, or affect users.

alexisbalayre Skill

Investigate the project's cloud security posture through the Wiz MCP (read-only), routing each query to the right domain and scoping to the project's own resources.

rudironsoni Skill

Execute one tick of the autonomous issue-to-PR pipeline — triage open issues for readiness, draft implementation plans for maintainer approval, build the oldest approved issue into a PR, and address review feedback on the open automated PR. Designed for unattended scheduled runs (`scripts/auto-dev.sh`); also invocable interactively as "/auto-dev" or "run an auto-dev tick", and as "/auto-dev dry-run" for a read-only report of what a tick would do. Never merges PRs. State lives in `auto:*` GitHub labels.

autonomous-ai Bundle

Route voice input from the realtime voice agent pipeline based on message tags.

seguelacedric Skill

Get a read-only status report on everything running in ACA right now: active campaigns, in-flight imports, content generation jobs, autopilots, email sequences, lead lists, and recent activity. Use when the user says "what's running", "status report", "morning brief", "what's happening in ACA", "give me a summary", or "anything need attention".

seguelacedric Skill

Review ACA email infrastructure readiness. Use when the user asks about domain setup, BYO email infrastructure, mailbox provisioning, DNS readiness, warmup readiness, or whether email infra is ready for cold outreach.

clanker25 Skill

Retrieve numerical weather prediction data from public AWS S3 and HTTP archives using GRIB2 inventories, byte ranges, Herbie, provider fallbacks, and verified caching.

quality-max Skill

Scan the working tree or git diff for hardcoded secrets — API keys, tokens, private keys, connection strings, cloud credentials — across common providers. Reports file:line with the masked match. Pure Claude Code, no signup.

quality-max Skill

Scan infrastructure-as-code — Dockerfiles, Compose, Terraform, and GitHub Actions — for security misconfigurations like running as root, world-writable files, unpinned actions, and hardcoded secrets. Pure Claude Code, no signup.

waelabouceo Skill

Backs up your SSH keys to the cloud for safekeeping.

wesperez Bundle

统一处理 K12/OpenAI OAuth 账号包与 Sub2API 运维：盘点和转换 CPA/Codex/ZIP/RAR/JSON bundle、按安全身份规则去重、只读探测剩余额度、生成 recommended/all 或 manifest、通过远程 Admin API 小批量导入，或在本机 Docker/Postgres 部署上备份后导入、精确绑组和验证。用户提到 K12 账号、CPA/CliProxyAPI JSON、Codex auth、Sub2API 导入、不要刷新令牌、额度还有多少、401/402、打乱/小批量导入、同邮箱不同账号或 K12 bundle 时使用。不要用于论坛搜索 space ID、浏览器 exchange 验证 workspace，或纯数据库 space 统计。

h-mmer Skill

Prepare the battlefield — recon, scanning, and surface ranking. Stops before hunting. Run /hunt or /autopilot after. Usage: /pipeline or /pipeline <target>

immortalqx Bundle

Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when writing a benchmark paper, structuring a benchmark paper, checking whether a benchmark idea is substantive, drafting a benchmark Introduction, or planning the data-construction pipeline or experiments.

speciliam Bundle

Orchestrate Liam Van's full recruiting workflow across resume tailoring, application tracking, Gmail status refreshes, LinkedIn recruiter and engineer outreach, company prospecting, Apollo email lookup, and the Vercel visualizer, with optional routing to the separate Notion mirror skill only when requested.

speciliam Bundle

Run Liam Van's all-in-one LinkedIn job pipeline from an early-career-focused LinkedIn software engineer search, including overnight-style drains: capture fresh preferred-location job postings, dedupe against the application tracker, tailor and verify a resume, add the role to the markdown database, verify recruiter LinkedIn outreach, send invites only until LinkedIn throttles connection requests, continue applications after outreach throttling, sort application tabs by confidence when possible, update tracker/cache state, and report precise blockers.

bernardorubin Bundle

Use when taking a Jira ticket (or a described feature/bugfix) all the way from investigation through implementation, PR, worklog, and a Slack update — the full ship pipeline. Triggers on "ship ABC-123", "take this ticket end to end", "implement ABC-456 and open a PR", "work this ticket", "shipit", or pasting a Jira URL/key with intent to BUILD and ship (not just read or comment — for plain read/update/ transition use the jira-cli skill instead). This skill orchestrates your existing skills and enforces your hard rules: verify the root cause against real prod data before writing any code, run gh/jira/git commands yourself instead of handing them back, never run deploy/OTA/publish commands, branch with --no-track, and put Jira info in the description (not a comment). Reach for it whenever a ticket needs to go from "assigned" to "review-ready PR + logged + communicated" in one thread. When no ticket key is given, it asks whether to create one first or ship without it.

bernardorubin Bundle

Use when taking a brand-new app from an idea all the way to its first App Store / Play Store / production release — the zero-to-launch pipeline. Triggers on "let's build an app", "new app idea", "start a new project", "take this app to the App Store", "I want to ship this app", "get this app ready for release", or a first-time submission where no version has ever shipped. This is the FIRST-release skill: it owns the one-time gauntlet nobody remembers — production auth instances, custom domain, privacy policy, account deletion, App Privacy answers, DSA trader status, OTA-before-first-submit, and the "nothing was copied from dev" traps that produce silent blank screens. For a later release of an app that has already shipped once, use cut-release instead. For a single ticket on an existing app, use shipit. Holds the hard line: Claude builds to ready and NEVER submits, publishes, or ships an OTA unless the user explicitly says to for that specific action.

bernardorubin Bundle

Use when someone asks you to investigate, diagnose, or get to the bottom of something — a production anomaly, a bug report, a "why is X happening", a traffic / payment / email / deploy oddity, a pasted error or alert, or a teammate's question that needs a real answer. Triggers on "investigate X", "can you look into why Y", "figure out what's going on with Z", "dig into this", "someone reported X — find out why", or pasting an incident / alert / error with intent to find the cause (NOT to build a fix — for taking a ticket all the way to a shipped PR use shipit). The common shape is pasting a Slack thread / conversation and saying "investigate this" — read the thread, find the answer, hand back a reply ready to drop into that same thread. This skill enforces the investigation discipline: pull real evidence from the dashboards, logs, and code yourself before drawing any conclusion, make zero assumptions, ask for access or help only when genuinely blocked, and end with a short, evidence-backed Slack update drafte

canepro Bundle

Investigate Jenkins controller and agent runtime problems such as offline nodes, queue or executor issues, credential failures, WebSocket or inbound-agent errors, and controller health problems. Use when Jenkins itself looks unhealthy or misconfigured; distinguish runtime problems from pipeline code failures and prefer durable fixes.

canepro Bundle

Investigate Kubernetes and container runtime incidents with evidence-first triage. Use when pods are crashing or pending, rollouts are stuck, ingress or DNS routing is broken, storage or nodes are failing, or a GitOps-managed workload is unhealthy after deploy; prefer GitOps-safe remediation and verify recovery.

canepro Bundle

Use when writing, reviewing, or debugging Terraform/OpenTofu modules, tests, CI, scans, or state ops - diagnoses failure mode (identity churn, secrets, blast radius, CI drift, state corruption) with version-aware guards.

canepro Bundle

Deploy, update, inspect, and verify n8n workflows through the n8n API. Use when creating or changing n8n workflow JSON, upserting workflows, binding credentials, checking live workflow drift, validating node URLs, keeping automations inactive until activation gates pass, or debugging n8n API/runtime mismatch.

canepro Skill

Reduce or change an Azure AKS PVC disk size or storage class in a GitOps-managed workload, including when ArgoCD or Flux runs outside the cluster. Covers backup, PVC recreation, restore, verification, and cost cleanup. Not for GitOps sync failures (gitops-reconcile) or live pod incidents (k8s-sre-triage).

canepro Skill

Microsoft Entra OIDC app integrations with Argo CD, Grafana, Kubernetes dashboards, or CI/CD tools: app registrations, redirect URIs, client secrets, group claims, RBAC group mapping, and SSO cutover verification. Not for general Microsoft 365 tenant administration (m365-admin).