DevOps & Infra

jramsahai Skill

Capture, compare, score, and pressure-test startup or product ideas before they become tracked work projects. Use when: (1) brainstorming candidate ideas, (2) comparing multiple directions, (3) building an idea scorecard, (4) evaluating whether an idea is worth deeper validation, or (5) deciding whether to promote an idea into a tracked project. NOT for: maintaining an active work project, project archival, or project-specific research after a tracked project has already been established.

jramsahai Skill

Manage centralized checkbox tasks in the Obsidian vault's Tasks.md: add, update, and complete tasks with due dates, priorities, waiting states, and project wikilinks. Use for anything actionable with an owner or deadline. NOT for: project status changes (project-tracking), store shopping items (shopping-list), or idea capture (idea-pipeline).

librefang Skill

Data pipeline expert for ETL, Apache Spark, Airflow, dbt, and data quality

javen-wangjunren Bundle

Initialize a local custom Elementor Widget plugin, design handoff workspace, and pending site-style context, choosing a Flat or Grouped plugin structure from expected Widget scale. Use once before the first custom Widget when no plugin scaffold exists; theme context is optional and read-only. Do not map Elementor Site Settings, design visuals, implement Widgets, deploy, or inspect a live WordPress installation.

lightningjim Bundle

Curates pipeline-generated bundle stubs and drafts README and key-passages files for ingested books in a Claude Code skill bundle. Use this skill whenever the user asks to curate a bundle, fill stubs or _TODO: placeholders in a skill bundle, draft README or key-passages for an ingested book, fill [title TBD] entries in key-passages.md, run pipeline verify gates (stitch --check, pkg) on curated content, or review and write-back curation output for books under skills/<skill>/references/<book>/. This skill operates on skills/<skill>/references/<book>/ directories in this repository.

alfons0329 Bundle

Runs one stage of the ticket pipeline (spec, rca, impl, verify, pr-create, pr-review, kb-update), reading and writing the artifacts that carry context between stages so each stage can start cold in its own session.

jim-nichols Skill

Commit and push the current repository's work to GitHub so it is safe and available on every other device. Use this whenever the user says "save", "save my work", "commit and push", "sync this", "push this up", "I'm switching devices", "I'm heading out", or otherwise signals they are done with a chunk of work or about to move between their laptop, phone, or a cloud session. Also use it proactively at the end of a completed task when the user works across multiple machines, since unpushed work on one device is the main way their workflow breaks.

fugisakimatheus Bundle

The 22 classic Gang of Four design patterns catalogued for TypeScript as ready-to-apply playbooks: intent, problem solved, participants, conceptual OOP example, and idiomatic TypeScript rewrites (discriminated unions, HOFs, generators, Record lookups). Includes trade-offs, how to recognize each pattern, and when NOT to apply them. Use when structuring new features, reviewing architecture, refactoring bloated classes/conditionals, designing extension points, or choosing between class hierarchies and union types. Triggers on: design pattern, GoF, Gang of Four, factory, abstract factory, builder, prototype, singleton, adapter, bridge, composite, decorator, facade, flyweight, proxy, chain of responsibility, command, iterator, mediator, memento, observer, state machine, strategy, template method, visitor, double dispatch, undo/redo, middleware pipeline, event emitter, anti-corruption layer, which pattern should I use.

dhinc1 Bundle

Render and mark up PDF documents — highlights, boxes, revision clouds, callouts, arrows, text stamps, and redactions — producing real, editable PDF annotations plus a rendered preview. Crucially, it RENDERS any page or zoomed region to an image first so Claude can actually SEE the drawing before marking it up. Use this whenever the user wants to annotate, mark up, redline, comment on, cloud, highlight, stamp, or redact a PDF, or asks to "mark up this drawing", "add a revision cloud", "redline this", "redact this", "stamp it as reviewed", "circle the X", "put a callout on Y", or wants to visually inspect / count / measure something on a PDF that has no usable text layer. Always use this skill for PDF annotation work rather than hand-writing PyMuPDF code. Do NOT use it for full quantity takeoffs (construction-takeoff) or exhaustive sheet-by-sheet drawing breakdowns (drawings-analyser) — this is the lightweight see-it-and-annotate tool.

prompthon-io Bundle

Inspect an existing web project and create or modify a working local page from a purpose, audience, sections, style and constraints brief. Use for building a website; leave final browser QA to webapp-testing and publishing to vercel-deploy.

prompthon-io Bundle

Deploy an approved and tested committed web project to a Vercel preview and verify provider identity, commit, status and actual URL. Use for publishing a website preview; production needs separate approval, and feature building or browser QA belong to other skills.

mike22890 Bundle

系统架构设计与工程决策的综合指南。当需要设计分布式系统、微服务架构、数据库选型、缓存策略、消息队列、负载均衡、CAP 定理应用、高并发/高可用设计、DevOps/SRE 实践、容器化/K8s 部署、监控告警、架构文档编写时使用。

tydm2 Bundle

Use when the user wants to turn a domain need into a multi-agent workflow — one orchestrator brain + several specialist subagents + one-line triggers (e.g. "build me an X pipeline", "assemble a subagent team"). Clarifies the blueprint, optionally researches community skills, and generates each agent's charter (AGENT.md with a self-iteration & expert-strengthening protocol), knowledge bases, and wiring contracts as a ready-to-run file structure. Not for one-off tasks, simple delegation, or docs only.

dev-ansh-r Bundle

First-run setup for the Qualcomm skills - get started, set up, configure or onboard a new machine for QAIRT/QNN/AIMET work. Probes what is already installed, asks only what cannot be discovered, and writes the .qualcomm-env config every other Qualcomm skill reads. Covers all layouts - SDK on this machine, a remote Linux build server or cloud VM, a separate AIMET host, board over SSH or ADB or none yet. Run this before any other Qualcomm skill, or when one reports that setup has not been run.

dev-ansh-r Bundle

Build a pre-compiled QNN HTP context binary for Qualcomm QCS6490 using the QAIRT/DLC flow - qairt-converter with AIMET quantization_overrides, qairt-quantizer, then qnn-context-binary-generator - and deploy and validate it on the board. Use for production deployment, fastest model load time, applying AIMET .encodings, or any qairt-converter, qairt-quantizer, DLC or context binary question. The classic alternative is qnn-model-export, which reaches a context binary via a cross-compiled .so built on the board instead.

dmitry-fomin Bundle

Use for a new feature, project step, or broad change that needs separate Codex contexts for specification, independent critique, Astra implementation, and acceptance with a judge-owned commit. Keep a journal, worktree, author questions, and checkable boundaries; do not use it for a one- or two-file point fix.

hideki5123 Bundle

Review local git changes or an architecture document against the Cost Optimization pillar of Google's Cloud Well-Architected Framework. Identifies gaps across 6 principles (spend aligned to value, cost-aware culture, utilization efficiency, continuous optimization, architectural cost drivers, workload-specific cost patterns), and for each non-trivial risk asks the user to decide Accept / Mitigate / Defer / Block — producing a documented risk register, not just a finding list. GCP-principle-based but cloud-agnostic. Use when the user asks for a cost review, cloud cost optimization check, rightsizing review, or spend efficiency review. Trigger phrases include "well architected cost", "GCP cost review", "cost optimization review", "cost pillar review", "FinOps review", "rightsizing review", "コストレビュー", "コスト最適化レビュー", "Well-Architected コスト".

vadrisai Bundle

Extracts data from an input PDF, validates it, renders a formatted report, and retries extraction on failure.

sergekostenchuk Bundle

Use when a project needs launch/infrastructure coordination across domains, registrars, servers, DNS, deploy, SSL, webmaster tools, monitoring, and launch readiness. Dry-run first; do not purchase, provision, deploy, or mutate production without explicit approval.

hideki5123 Bundle

Review local git changes or an architecture document against the Security, Privacy, and Compliance pillar of Google's Cloud Well-Architected Framework. Identifies gaps across 7 principles (security by design, zero trust, shift-left, preemptive defense, AI used securely, regulatory/privacy, shared responsibility), and for each non-trivial risk asks the user to decide Accept / Mitigate / Defer / Block — producing a documented risk register, not just a finding list. GCP-principle-based but cloud-agnostic. Use when the user asks for a security architecture review, Well-Architected security check, threat / risk review, or zero-trust assessment. Trigger phrases include "well architected security", "GCP security review", "security pillar review", "security risk review", "zero trust review", "セキュリティレビュー", "セキュリティリスクレビュー", "Well-Architected セキュリティ".

hideki5123 Bundle

Review local git changes or an architecture document against the Reliability pillar of Google's Cloud Well-Architected Framework. Identifies gaps across 8 principles (SLOs aligned to UX, recovery targets, HA via redundancy, horizontal scalability, observability, graceful degradation, tested recovery, postmortems), and for each non-trivial risk asks the user to decide Accept / Mitigate / Defer / Block — producing a documented risk register, not just a finding list. GCP-principle-based but cloud-agnostic. Use when the user asks for a reliability review, resilience / SRE review, SLO assessment, failure-mode analysis, or recovery readiness check. Trigger phrases include "well architected reliability", "GCP reliability review", "reliability pillar review", "SLO review", "resilience review", "信頼性レビュー", "Well-Architected 信頼性", "可用性レビュー", "障害耐性レビュー".

sergekostenchuk Bundle

Plan safe website migrations when existing URLs, redirects, sitemap, robots, schema, canonical pages, metadata, analytics, webmaster tools, or launch monitoring may change. Use after existing-site analysis or rebuild decisions; never apply production redirects, DNS, deploy, or webmaster mutations without explicit approval.

sergekostenchuk Bundle

Use when planning deployments, build commands, environment checks, CI/CD, release steps, smoke tests, rollback, and monitoring. Dry-run first; do not deploy to production, change secrets, or mutate live services without explicit approval.

aiblueprinthq Skill

Prepare local Render or Vercel deployment configuration and verify build, start, output, environment, and health-check readiness without deploying. Use for /release, Render setup, Vercel setup, deploy readiness, render.yaml, or vercel.json.

aiblueprinthq Skill

Build every remaining planned feature serially in explicit Continuous Mode, with one local branch, verification cycle, commit, archive, and local merge per feature. Stop on decisions or blockers and never push or deploy. Use only for /continuous, $continuous, or a direct Continuous Mode request.

framecoreworks Bundle

Use this skill for portable Codex or ChatGPT workflow routing, bounded roles, gates, handoffs, visible state, artifact templates, reasoning routes, request diagnostics, QA loops, delivery discipline, and provider-neutral governance.

farzammohammadi Bundle

Upload a Markdown (.md) file to a Confluence Cloud page with tables, headings, formatting, and mermaid diagrams all rendering correctly — no copy-paste, no wording changes. Use this whenever someone wants to publish, push, sync, or upload a markdown doc, spec, design, or README to Confluence, or complains that pasting markdown into Confluence breaks the tables or diagrams. Also trigger on "put this doc on Confluence", "get this on the wiki", "publish this to Confluence", or updating an existing Confluence page from a markdown source.

viderstar Skill

Review an Airflow DAG before it is merged: idempotency, retries and timeouts, failure alerting, heavy imports at module level, configuration through Variables, secrets in Connections, and concurrency settings. Use when asked to "review this DAG", "check the pipeline", "is this ready to merge", "why does the DAG fail", "add a new DAG", "optimise this DAG". Not for research notebooks.

jtaroreh Bundle

Configure models and execution runtime for agystack. Configures Antigravity model tiers per role and Cloud Run runtime settings for up to 100+ parallel workers.

pgomezurrea-eng Bundle

Build a complete Creative Bible — a strategic ad creation system covering customer avatars, awareness stages, market sophistication, messaging strategies, 100 hooks, script formulas, and more — for any brand. Use this skill whenever the user asks to create a Creative Bible, ad strategy system, messaging playbook, hook bank, ad copy system, creative strategy framework, or anything involving systematically mapping a brand's advertising messaging across awareness stages and customer segments. Also trigger when the user wants to fill in or work with the Creative Bible template, or asks for a structured approach to ad creative that goes beyond one-off copywriting. This skill covers the full pipeline: competitive research → customer mapping → template fill → quality audit.

farzammohammadi Bundle

Generate .excalidraw JSON files for architecture flows, system diagrams, and simple sketches from natural-language descriptions. Use whenever the user asks to draw, sketch, diagram, or visualize a flow, architecture, pipeline, or system with a small number of boxes (up to ~15) — especially for slides, docs, or when they mention excalidraw. Also trigger when the user describes components and their connections ("X calls Y which writes to Z") and wants something they can open in excalidraw.com.

aaryan1524 Bundle

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user wants to "fix everything", "sweep the codebase", "auto-fix all issues", "clean up the whole project", or asks for a single command that both diagnoses and remediates quality problems. Do NOT trigger for: read-only audits or health reports where the user only wants findings without code changes; single-dimension reviews (use the focused skill instead: brooks-review / brooks-audit / brooks-debt / brooks-test); server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime.

aaryan1524 Bundle

Combined codebase health dashboard that scores a project across all four quality dimensions — PR quality, architecture, tech debt, and test quality — in a single pass, drawing on twelve classic engineering books. Triggers when: user wants an overall quality assessment, asks "how healthy is this codebase?", "run all the checks", "I need a health score before the release", or wants to onboard a new team with a quality overview. Do NOT trigger for: server health checks, HTTP health endpoints, Kubernetes liveness/readiness probes, database health, or application uptime. Also do not trigger when the user specifically requests only one dimension — use the corresponding focused skill instead (brooks-review / brooks-audit / brooks-debt / brooks-test).

painhardcore Bundle

Use when the user asks to write, edit, or review a local Docker Compose file (compose.yaml / docker-compose.yml) or a local service stack.

lushengguo Skill

启动 KCEX Spot 连接本地开发环境（Docker Compose + Mock API），观察做市行为和订单管理，检查限流/铺单/模式切换是否正常

aaryan1524 Skill

Run end-to-end deploy pipelines across Stripe, Supabase, and Vercel using the Composio CLI. Promote Stripe products, push Supabase migrations, ship Vercel deployments, and verify with post-deploy checks — all from one script.