Architecture & codebase
12,712 rows, by stacks then stars
1,011 of these skill files have been read, by 858 distinct authors, and what they tell an agent counted. What Architecture & codebase authors agree on, and what they forbid
MadewellRD/skills-lab/dist/vendor/openai/finops-command-desk/cost-aware-architecture-desk Skill
2★ repoanalyze cloud cost drivers as design decisions covering data transfer egress cross-zone and cross-region traffic, nat and endpoint routing, cdn offload and cache hit ratio, storage class and lifecycle against measured access patterns, managed service against self-operated economics, interruptible and elastic capacity, retry polling and logging behavior priced from request and ingestion volume, and the resilience cost being deliberately paid for a stated recovery objective. use for architecture cost reviews, egress investigations, storage tiering decisions, and build against buy comparisons.
MadewellRD/skills-lab/dist/vendor/openai/ios-command-desk/ios-architecture-design-desk Skill
2★ repodesign iOS app and game architecture, module boundaries, data flow, offline behavior, engine integration, services, APIs, migrations, and ADR-ready decisions.
Job architecture leveling desk
MadewellRD/skills-lab/dist/vendor/openai/people-talent-command-desk/job-architecture-leveling-desk Skill
2★ repoplace a role against the level guide by scope, autonomy, and impact, map it to a job family, sub-family, and job code, attach the grade and salary band with its version and geographic differential, determine exemption or worker classification with the test applied and the jurisdiction it was applied under, and write the job description, must-have criteria, success measures, and posting content including any required pay range disclosure. use for leveling disputes, title against level questions, job architecture design, band mapping, exempt against non-exempt determinations, contractor classification risk, and job descriptions or postings.
MadewellRD/skills-lab/dist/vendor/openai/people-talent-command-desk/onboarding-desk Skill
2★ repobuild the plan that turns an accepted offer into a productive employee, covering the pre-start provisioning, equipment, and access sequence with owners and lead times, the employment eligibility verification window and its state without specifying which documents a person must produce, day one and first week, thirty sixty and ninety day milestones written as observable outcomes, the manager's commitments with dates, required policy acknowledgments and training deadlines, and benefits and payroll enrollment windows that are the person's to miss. use for new hire onboarding plans, ramp plans, first ninety days, manager onboarding checklists, internal transfer and new manager transitions, and early attrition follow-up.
MadewellRD/skills-lab/dist/vendor/openai/platform-engineering-command-desk/platform-api-contract-desk Skill
2★ repodefine the platform's own interface contracts, covering resource schemas and custom resource definitions, api groups and versioning, stability labels from alpha through beta to stable, backward-compatibility guarantees and what counts as additive versus breaking, the deprecation window and notice policy, cli and portal action surface, and the abstraction boundary between what the platform hides and what it deliberately exposes. use for platform api design, crd and resource claim schemas, schema versioning, breaking-change policy, leaky abstraction reviews, and platform client surface decisions.
MadewellRD/skills-lab/dist/vendor/openai/platform-engineering-command-desk/scaffolding-templates-desk Skill
2★ repodesign software templates and repository scaffolding, covering what a generated repository contains on day one, template parameters and the decisions they do not ask, template versioning and release, the renovation path that keeps the generated fleet current, managed versus owned files after handoff, template testing so generated repos pass ci on first run, and template drift measurement across the fleet. use for repo scaffolding, service templates, cookiecutter and scaffolder work, golden repo bootstrapping, fleet-wide upgrade campaigns, and template sprawl consolidation.
Vendor onboarding provisioning desk
MadewellRD/skills-lab/dist/vendor/openai/procurement-vendor-management-command-desk/vendor-onboarding-provisioning-desk Skill
2★ repoonboard an executed supplier by requesting the vendor master record with tax and compliance forms, verifying bank details out of band through a channel the requester did not supply, granting access only at the level the review authorized with the approval recorded per system, capturing the security configuration as actually built including identity federation provisioning logging retention and admin roles, setting up invoicing and purchase order handling, and naming an internal owner. use for vendor master setup, supplier bank detail verification and payment fraud controls, access provisioning and sso scim configuration, tenant security settings, invoicing and coding setup, supplier owner assignment, and go-live readiness after contract signature.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/architecture-design-desk Skill
2★ repocreate connector-grounded architecture and solution design artifacts from product requirements, technical discovery, repository structure, constraints, and stakeholder decisions. use when ChatGPT needs to produce software design specs, architecture decision records, component boundaries, interface contracts, migration plans, risk notes, source-fact evidence, or downstream implementation handoff notes for issue planning, verification, security, or implementation-handoff-desk workflows.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/maintenance-refactor-desk Skill
2★ repocreate connector-grounded maintenance, refactor, dependency-upgrade, dead-code removal, migration, and technical-debt reduction artifacts for software delivery. use when ChatGPT needs to assess refactor scope, plan safe code cleanup, sequence dependency upgrades, evaluate migration risk, define regression controls, prevent scope creep, or prepare downstream handoff notes for implementation-handoff-desk, test-strategy-desk, verification-desk, ci-failure-desk, security-threat-desk, or release-operations-desk workflows.
Security architecture review desk
MadewellRD/skills-lab/dist/vendor/openai/security-command-desk/security-architecture-review-desk Skill
2★ reporeview a system or change design for security control placement, covering trust boundary mapping, data flow analysis, conformance to the reference architecture, deviations and compensating controls, fail-open and fail-closed behavior, blast radius, conditions of approval, and residual design risk with the accepting party named. use for design reviews, architecture review board submissions, new service or major change assessment, segmentation and boundary decisions, and security sign-off before build starts.
MadewellRD/skills-lab/dist/vendor/openai/sre-reliability-command-desk/resilience-architecture-desk Skill
2★ repodesign timeout and retry budgets, circuit breakers, bulkheads, load shedding and admission control, backpressure, cache and stale-serve fallbacks, idempotency and replay safety, and graceful degradation modes, and record whether each control is configured, tested, proven in an incident, or unproven. use for resilience design, failure absorption, deadline propagation, retry amplification control, and degradation mode specification.
MadewellRD/skills-lab/dist/vendor/openai/web-development-command-desk/information-architecture-desk Skill
2★ repodesign web information architecture including sitemap, route hierarchy, navigation, url taxonomy, content relationships, wayfinding, content hierarchy, and findability. use when ChatGPT needs to structure websites, portals, dashboards, docs sites, ecommerce surfaces, or web apps before design, cms, accessibility, seo, frontend, or release work.
jonisavo/supersigil/.agents/skills/ss-refactoring Skill
2★ repoUse when restructuring code that has Supersigil specs and behavior must not change. Activates for module extraction, file moves, renames, hierarchy flattening, or any structural cleanup. Keeps specs, criteria, tracked files, and verification evidence valid throughout.
Fodhol/skills/plugins/building-secure-contracts/skills/guidelines-advisor Skill
2★ repoComprehensive smart contract development advisor based on Trail of Bits' best practices. Analyzes codebase to generate documentation/specifications, review architecture, check upgradeability patterns, assess implementation quality, identify pitfalls, review dependencies, and evaluate testing. Provides actionable recommendations. (project, gitignored)
is-bo/fullstack-forge-skill/.agents/skills/forge-architecture Skill
2★ repoEvaluate system boundaries, dependency direction, failure domains, and the fitness of the current topology. Activate automatically for multi-component applications when that concern is relevant to a software-engineering request.
is-bo/fullstack-forge-skill/.cursor/skills/forge-architecture Skill
2★ repoEvaluate system boundaries, dependency direction, failure domains, and the fitness of the current topology. Activate automatically for multi-component applications when that concern is relevant to a software-engineering request.
is-bo/fullstack-forge-skill/.gemini/skills/forge-architecture Skill
2★ repoEvaluate system boundaries, dependency direction, failure domains, and the fitness of the current topology. Activate automatically for multi-component applications when that concern is relevant to a software-engineering request.
is-bo/fullstack-forge-skill/.github/skills/forge-architecture Skill
2★ repoEvaluate system boundaries, dependency direction, failure domains, and the fitness of the current topology. Activate automatically for multi-component applications when that concern is relevant to a software-engineering request.
is-bo/fullstack-forge-skill/.windsurf/skills/forge-architecture Skill
2★ repoEvaluate system boundaries, dependency direction, failure domains, and the fitness of the current topology. Activate automatically for multi-component applications when that concern is relevant to a software-engineering request.
is-bo/fullstack-forge-skill/src/fullstack-forge/commands/forge-architecture Skill
2★ repoEvaluate system boundaries, dependency direction, failure domains, and the fitness of the current topology. Activate automatically for multi-component applications when that concern is relevant to a software-engineering request.
toRolex/rolex-skills/skills/engineering/codebase-design Skill
1★ repo设计深度模块的共享词汇表。当用户想要设计或改进模块的 interface、寻找深化机会、决定 seam 放在哪里、让代码更可测试或更易 AI 导航,或其他 skill 需要深度模块词汇表时使用。
toRolex/rolex-skills/skills/engineering/improve-codebase-architecture Skill
1★ repo扫描代码库寻找深化机会,以可视化 HTML 报告呈现,然后对你选择的任一候选项进行 grilling。
toRolex/rolex-skills/skills/engineering/setup-rolex-skills Skill
1★ repo配置本仓库的工程 skill——设置 issue tracker、triage 标签词汇和领域文档布局。每个仓库在首次使用其他工程 skill 之前运行一次。
grandheman/claude-sdlc/skills/developer Skill
1★ repoUse this skill when implementing features, writing code, creating functions or classes, refactoring existing code, or building any software component. Triggers on: "implement", "write the code for", "build this feature", "create a function", "refactor this", "add this to the codebase", "make this work", "write a class", "implement the logic". This skill enforces clean code principles, proper abstraction, documentation standards, and test-driven practices on every output. Always use this skill when producing code so that outputs meet the team's quality bar from the start.
grandheman/claude-sdlc/skills/devops-engineer Skill
1★ repoUse this skill for infrastructure, CI/CD, deployment, environment management, monitoring, and operational concerns. Triggers on: "CI/CD pipeline", "deployment", "infrastructure", "environment setup", "deploy to production", "monitoring", "alerting", "Docker", "containers", "environment variables", "secrets management", "build pipeline", "staging environment", "deployment runbook", "observability", "on-call", "operational readiness". Also triggers when a new project needs its infrastructure defined or an existing system needs a deployment strategy or operational documentation.
grandheman/claude-sdlc/skills/long-term-maintenance Skill
1★ repoUse this skill for any task related to long-term project health: technical debt management, dependency updates, refactoring, performance optimization, quarterly reviews, codebase health assessments, legacy code modernization, or sustaining engineering. Triggers on: "tech debt", "refactor", "clean up the codebase", "update dependencies", "quarterly review", "codebase health", "legacy code", "modernize", "this is getting hard to maintain", "the code is messy", "performance optimization", "code quality", "codebase audit", "reduce complexity", "dependency audit". This skill treats existing systems with respect and makes changes that improve without breaking.
grandheman/claude-sdlc/skills/solution-architect Skill
1★ repoUse this skill for any architecture, system design, or major technical decision task. Triggers on: "design the system", "architecture for", "how should we structure", "ADR", "architecture decision", "data model", "API design", "system diagram", "technical design", "non-functional requirements", "how should this be built", "what pattern should we use", "scalability", "integration design". Use before any complex feature development begins. This skill produces artifacts that guide all downstream development.
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/api-contract-review Skill
1★ repoReview a specific REST, GraphQL, RPC, event, SDK, or internal-module contract across server, client, schema, documentation, and tests, classifying breaking, non-breaking, and behavioral changes. Use for API contract compatibility; do not perform a general code review, generic impact analysis, or modify the interface. 审查具体 REST、GraphQL、RPC、事件、SDK 或内部模块契约在服务端、客户端、Schema、文档和测试间的一致性,并分类破坏性、非破坏性和行为变化。用于 API 契约兼容性;不替代普通代码审查或通用影响分析,也不修改接口。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/architecture-decision-record Skill
1★ repoCreate or update an ADR from a real architectural problem, evidence, alternatives, tradeoffs, and an explicit decision state while respecting the repository's ADR location, numbering, and template. Use only when the user authorizes ADR or architecture-document edits; do not generate an implementation plan, fabricate team consensus, or modify business code. 根据真实架构问题、证据、候选方案、权衡和明确决策状态创建或更新 ADR,并遵循仓库 ADR 目录、编号和模板。仅在用户授权修改 ADR 或架构文档时使用;不生成实施计划、不虚构团队共识,也不修改业务代码。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/configuration-audit Skill
1★ repoAudit configuration sources, precedence, environment overrides, defaults, required fields, types, validation, drift, obsolete settings, dangerous defaults, undocumented variables, and credential-commit risk using repository evidence. Use for configuration-specific risk; do not perform a broad health check, read or display sensitive values, connect to external environments, or modify configuration. 基于仓库证据审计配置来源、优先级、环境覆盖、默认值、必填、类型、校验、漂移、过期项、危险默认值、未文档化变量和凭证误提交风险。用于配置专项风险;不替代广泛体检,不读取或显示敏感值、不连接外部环境,也不修改配置。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/dead-code-verification Skill
1★ repoVerify whether a specific symbol, file, route, configuration path, or feature is safely removable by checking static and dynamic usage, registries, build entries, templates, plugins, scripts, and external contracts. Use for evidence of unused code; do not perform general impact analysis, assume absence from text search proves safety, or delete code. 通过检查静态与动态使用、注册器、构建入口、模板、插件、脚本和外部契约,验证具体符号、文件、路由、配置路径或功能是否可安全删除。用于无用代码证据;不替代通用影响分析,不把文本搜索无结果当安全证明,也不删除代码。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/repo-onboarding Skill
1★ repoUnderstand an unfamiliar software repository before making changes. 在修改代码前理解一个陌生软件仓库。
clever-cc-plugins/cc-content/plugins/cc-content/skills/cc-content-onboarding Skill
1★ repoUse this skill when setting up a new marketing project with Claude Code, registering context files, or extending the context of an existing project. Invoke when the user asks to "onboard a new client", "set up context files", "initialize marketing project", "register context", "add context", or "set up project context". Also use when context files are missing and the user wants to set up through a guided interview.
ArthurZakirov/AgentDesk/skills/openclaw-browser-setup Skill
1★ repoTroubleshoot and operate OpenClaw browser on local or remote gateways. Use when Codex needs to enable the bundled browser plugin, resolve `pairing required` or device approval errors, choose between the managed `openclaw` profile and the attached `user` profile, handle Linux headless or Chrome CDP startup failures, or prove browser control with `profiles`, `start`, `open`, `snapshot`, and `screenshot`.
ArthurZakirov/AgentDesk/skills/setup-dell-monitors Skill
1★ repoTroubleshoot Arthur's Dell P2725DE/P2225D monitor setup, especially DisplayPort daisy chaining, "No DP signal from your device" on the P2225D, Windows Fast Startup or shutdown-related display breakage, and reset/reinstall steps for a Lenovo laptop or Dell desktop tower using original Dell cables.
ArthurZakirov/AgentDesk/skills/setup-macbook-productivity Skill
1★ repoConfigure repeatable macOS productivity settings on a user's MacBook, especially voice typing / Dictation setup. Use when Codex is asked to set up, repair, or document MacBook productivity features such as voice typing, Dictation, Dictation shortcuts, microphone input for Dictation, or future local macOS workflow preferences.
ArthurZakirov/AgentDesk/skills/wsl2-browser-setup Skill
1★ repoInstall and configure browsers for Windows plus WSL2. Use when a user wants native Linux Chrome inside WSL to work for normal browsing or sign-in flows, or when a tool in WSL needs a Windows host Chrome or Edge instance exposed over CDP. Prefer this skill before any tool-specific browser automation setup.
prvthmpcypher/skills-personal/skills/second-brain-architect Skill
1★ repoYou are a personal knowledge management (PKM) expert. When given knowledge management needs, design a complete second brain system using PARA, Zettelkasten, or similar frameworks. ## Process 1. Understand the user's knowledge needs and workflow 2. Design the folder/tag structure (PARA method or alternative) 3. Set up capture, organize, and retrieval workflows 4. Recommend tools and integrations 5. Create a maintenance and review system ## Output Format ## Second Brain Architecture ### System Overview Method: PARA (Projects, Areas, Resources, Archives) + Zettelkasten ### Folder Structure javascript Second Brain/ ├── 1-Projects/ (Active, time-bound work) │ ├── Project A/ │ └── Project B/ ├── 2-Areas/ (Ongoing responsibilities) │ ├── Health/ │ ├── Finance/ │ └── Career/ ├── 3-Resources/ (Topics of interest) │ ├── Programming/ │ ├── Design/ │ └──...
JohnWayneeee/ai-agent-skills/skills/workflow-node-setup Skill
1★ repoConfigure, adjust, debug, and verify React Flow workflow nodes. Use when working on custom node components, especially for node handles, multi-channel connections, edge ids/styles, NodeResizer behavior, drag handles, nodrag/nowheel areas, and markdown scroll containers.
The same file is in 2 other repositories
ronniepinnell/casper/collection/meta-and-tooling/project-init Skill
1★ repoBootstrap any repo with a full AI-ready scaffold. Runs as /project-init (full interview), /project-init --bootstrap (fast 5-question path), /project-init sync (drift check), /project-init update <section> (targeted refresh), or /project-init setup <service> (walk through setting up Supabase, Doppler, Vercel, GitHub App, Linear, Railway, etc.)
ajbarea/techne/plugins/techne/skills/paper Skill
1★ repoUse when starting or scaffolding a new research paper in a papers-style monorepo (a repo of LaTeX paper directories that share one bibliography). Triggers include "scaffold a paper", "start a new paper", "set up a paper dir", "new paper from <repo>", "add a paper to papers/".
turntuptechnologies-ai/skills/skills/new-project-init Skill
1★ repo新しいプロジェクト/リポジトリを共通規約で立ち上げるとき。「新しいプロジェクトを作る」「リポジトリを初期化」「CLAUDE.md を用意」等で使う。フェーズ制・Conventional Commits・Issue→PR フローを定めた CLAUDE.md、常時効かせる Rules、main 保護フックなど基本ファイルを整える。stack 固有の雛形は scaffold-* Skill に任せる。
turntuptechnologies-ai/skills/skills/scaffold-cf-worker Skill
1★ repoCloudflare Workers のサーバレスアプリ/API を新規に作るとき。「Workers でアプリを作る」「Cloudflare で API を立ち上げ」等で使う。wrangler + Hono + TypeScript + Vitest(workers pool) + Biome の構成で雛形を用意する。土台は new-project-init を先に使う。
turntuptechnologies-ai/skills/skills/scaffold-deno-api Skill
1★ repoDeno で型付きの API サーバー(REST/JSON)を新規に作るとき。「Deno で API を作る」「Hono+Drizzle でバックエンドを立ち上げ」等で使う。Deno + Hono + Drizzle ORM + PostgreSQL の構成で雛形を用意する。土台は new-project-init を先に使う。
turntuptechnologies-ai/skills/skills/scaffold-python-tool Skill
1★ repoPython の CLI ツールやバックエンドサービスを新規に作るとき。「Python のツールを作る」「uv でプロジェクト初期化」等で使う。uv + ruff + mypy(strict) + pytest の構成で雛形を用意する(任意で FastAPI / SQLAlchemy / click)。土台は new-project-init を先に使う。
turntuptechnologies-ai/skills/skills/scaffold-react-app Skill
1★ repoReact のフロントエンド/SPA Web アプリを新規に作るとき。「React アプリを作る」「Vite でフロントを立ち上げ」等で使う。Vite + React + TypeScript + Tailwind v4 + Vitest の構成で雛形を用意する(API 連携なら TanStack Query)。土台は new-project-init を先に使う。
turntuptechnologies-ai/skills/skills/scaffold-wxt-extension Skill
1★ repoブラウザ拡張機能を新規に作るとき。「拡張機能を作る」「WXT で拡張を立ち上げ」等で使う。WXT + React + TypeScript + Tailwind CSS v4 + Vitest の構成で雛形を用意する。土台(CLAUDE.md・git)は new-project-init を先に使う。
broneq/bdk/skills/bdk-rules-architecture Skill
1★ repoArchitecture principles (layering, boundaries, dependency direction). Preloaded into agents that reason about structure; not user-facing.
broneq/bdk/skills/bdk-tier-explore Skill
1★ repoTool-tier guidance for codebase exploration and architecture overview. Preloaded into agents that explore code structure; not user-facing.
broneq/bdk/skills/refactor Skill
1★ repoBDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.
broneq/bdk/skills/setup Skill
1★ repoBDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.
anshmajumdar121/skill-x/skills/super-skill Skill
1★ repoApply the combined rigor + delegation framework for complex tasks. Two operating modes: (1) **Rigor mode** — use the GPT-5.6 Sol 7-step loop, 10 principles, 9-stage architecture, task classification, risk register, validation layers, acceptance/rejection criteria, adversarial review, and pre-delivery checklist (default for any non-trivial task); (2) **Delegation mode** — for codebase-heavy or token-heavy work that can be split into independent parallel slices, use the Efficient Fable delegation pattern: cheap subagents do the heavy lifting, the orchestrator keeps judgment, architecture, synthesis, and final review; always apply the vetting protocol (treat subagent reports as leads, not facts). Trigger when the user says "super skill", "use the super framework", "delegate this efficiently", or any complex task where you want both auditable artifacts AND cost/speed efficiency. Do NOT trigger for trivial single-step questions, or for tasks that don't tolerate any subagent delegation (legal, medical, single-source-of-truth). This skill is **self-evolving**: it can add, update, or remove its own content when triggered by `evolve this skill`, when the agent notices stale/garbage content, or when a clearly better technique becomes available. Self-evolution is bounded by the constitution in `references/self-evolution.md` §1 (evidence-based, bounded scope, conservative, reversible, quality floor, no-garbage filter, privacy).
scoobydont-666/shared-claude-skills/skills/code-consistency Skill
1★ repoEnforce, review, and generate consistent code across registered languages: Python, Golang, Bash/Shell, Rust, PowerShell, Terraform, Ansible. Auto-expands when new languages are encountered. Includes inline quality triage (performance, security, testability, architecture smells). Trigger on: "consistency", "style", "conventions", "review my code", "refactor", "clean up", "idiomatic", "linting", "best practices", "code review", "code smell", or when code is present and a consistency/quality task is implied. Also trigger when generating code alongside existing snippets. Do not wait to be asked explicitly — if code is present, use this skill.
scoobydont-666/shared-claude-skills/skills/code-quality Skill
1★ repoDeep code quality analysis: performance (Big-O, hot paths, resource management), security (injection, secrets, auth, input validation), testability (coverage gaps, untestable design, DI), architecture (SOLID, coupling, abstraction leaks, layering). Language-agnostic with language-specific patterns from references. Trigger on: "code quality", "performance audit", "security review", "OWASP", "SOLID", "coupling", "testability", "technical debt", "code smell", "architecture review", "Big-O", "complexity analysis", "hot path", "memory leak", "injection", "vulnerability", "dependency injection", "clean architecture", "is this code good", or "can this be better". Also triggers on escalation from code-consistency quality triage.
scoobydont-666/shared-claude-skills/skills/config-auditor Skill
1★ repoCross-reference all CLAUDE.md files, memory files, skill descriptions, and project registries for contradictions, stale data, and inconsistencies. Trigger on "check for contradictions", "audit configs", "config consistency", "are my configs consistent", or any request to verify configuration coherence across Project Swarm.
scoobydont-666/shared-claude-skills/skills/inbound-sync Skill
1★ repoGenerate a structured sync bundle that captures decisions, architecture changes, conventions, bug fixes, and roadmap updates from the current Claude.ai conversation for ingestion into local Project Swarm projects via Claude Code. Trigger when the user says "sync", "sync project details", "generate sync bundle", "save this for Claude Code", "update local projects", "export decisions", or any variation of requesting that conversation outcomes be persisted to the local codebase. Also trigger at the end of long conversations where significant decisions were made, if the user asks to wrap up or summarize. Do NOT trigger for general summaries unrelated to project sync.
scoobydont-666/shared-claude-skills/skills/infosec-architect Skill
1★ repoSecurity architect persona with CISSP/GSE/OSEE-depth expertise. Hardening infrastructure, reviewing code for vulnerabilities, auditing Docker Swarm GPU clusters, securing OpenClaw/NemoClaw agent deployments, and red-teaming your own systems. Trigger on ANY security topic: firewall rules, SSH hardening, TLS configuration, container isolation, Docker daemon security, secrets management, network segmentation, CVE triage, vulnerability assessment, pen testing, exploit analysis, threat modeling, OWASP, prompt injection, agent security, sandbox escape, OpenShell policies, NemoClaw hardening, ClawHub skill vetting, WebSocket security, RBAC, IAM, zero trust, SIEM, incident response, forensics, malware analysis, supply chain security, credential rotation, API key management, secure coding review, NIST frameworks, CIS benchmarks, or any mention of 'is this secure', 'harden this', 'security audit', 'attack surface', 'lock this down'. Even casual security questions trigger this skill.
scoobydont-666/shared-claude-skills/skills/openclaw-ops Skill
1★ repoOpenClaw and NemoClaw operations — sandbox management, inference provider config, policy configuration, Tailscale integration, security hardening, skill vetting. Trigger on: "OpenClaw", "NemoClaw", "OpenShell", "sandbox", "openclaw tui", "agent assistant", "ClawHub", "gateway token", or any task involving personal AI assistant deployment and operations.
RealDougEubanks/ClaudeMarketplace/skills/api-design Skill
1★ repoDesigns REST, GraphQL, and gRPC APIs (OpenAPI/schema/proto output) and reviews existing APIs for consistency, best practices, and breaking change risks.
RealDougEubanks/ClaudeMarketplace/skills/architecture-design Skill
1★ repoDesigns new systems from requirements: C4 model diagrams, service boundaries, API contracts, data design, failure modes, and cross-cutting concerns.