Explore skills
Showing 44941–44970 of 77104 skills
Public-safe hackathon source registry + filtering output (no crawling, no submissions).
KingKaonix/minis-skills
Stars: 0Claude CodeCodexAOI Triple Memory (Lite) — file search + decision notes templates (no plugins).
KingKaonix/minis-skills
Stars: 0Claude CodeCodexUltra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
gstrainovic/zid
Stars: 0Claude CodeCodexUltra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
gstrainovic/zid
Stars: 0Claude CodeCodexCompress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"
gstrainovic/zid
Stars: 0Claude CodeCodexQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
gstrainovic/zid
Stars: 0Claude CodeCodexUltra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
gstrainovic/zid
Stars: 0Claude CodeCodexUltra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
gstrainovic/zid
Stars: 0Claude CodeCodexCompress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"
gstrainovic/zid
Stars: 0Claude CodeCodexQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
gstrainovic/zid
Stars: 0Claude CodeCodexSkeptically verify completed changes, agent work, merge readiness, and hidden regressions. Use after implementation when claims need independent proof; do not use as the primary implementation or ordinary code-review workflow.
nledford/engineering-review-board
Stars: 11Claude CodeCodexAPI design and contract guidance. Use when defining, changing, reviewing, or testing service or public interface contracts: HTTP/REST resources, RPC/GraphQL operations, webhooks, event/message schemas, request/response/error envelopes, pagination/filtering/sorting, idempotency, versioning/deprecation/backward compatibility, OpenAPI/AsyncAPI/JSON Schema/protobuf artifacts, SDK or CLI public surfaces, or consumer/provider compatibility. Do not use for ordinary language/framework implementation, Rust handler mechanics, SQL schema/query design, architecture boundary selection, security controls, BDD/TDD mechanics, observability instrumentation, or documentation-only API references after the contract is set; load those existing skills instead or alongside it when their trigger is primary. Use semantic-versioning when the primary question is choosing or applying a patch, minor, or major release bump after contract impact is understood.
nledford/engineering-review-board
Stars: 11Claude CodeCodexReview architectural boundaries, dependency direction, ports and adapters, Clean/Onion/Hexagonal/DDD hybrids, and modular monolith structure. Use for architecture-focused audits of existing systems or changes; do not use for ordinary implementation or architecture design without a review request.
nledford/engineering-review-board
Stars: 11Claude CodeCodexImplement, change, review, or test checked-in CI and release provider configuration, including workflow triggers, job graphs, matrices, caches, artifacts, permissions, concurrency, environments, automated versioning, tags, releases, and package or binary publication. Do not use to choose a semantic patch, minor, or major bump from application changes; use semantic-versioning. Do not use for underlying language/test commands, Justfile wrappers, manual Git operations, final ship/hold decisions, unexplained CI failures, supply-chain-only or security-review-only audits, or production deployment infrastructure implementation.
nledford/engineering-review-board
Stars: 11Claude CodeCodexClean Architecture guidance centered on the dependency rule, entities, use cases/interactors, and interface adapters that keep business policy independent from frameworks, databases, and UI. Use when the main design question is how policy flows through use cases and adapter boundaries. Use hexagonal-architecture when named inbound/outbound ports around external actors are the main concern, onion-architecture when explicit concentric domain/application rings are the requested model, and architecture-review for a read-only audit. Do not use for simple CRUD, prototypes, or framework-convention-first apps where added layers reduce clarity.
nledford/engineering-review-board
Stars: 11Claude CodeCodexImplement, change, review, or test Dockerfile, Containerfile, .dockerignore, BuildKit/OCI image, and Docker Compose configuration, including build contexts and stages, caches, runtime users, entrypoints, health checks, ports, networks, volumes, secrets, lifecycle, and resource or privilege controls. Do not use for routine command execution or log inspection, Kubernetes/Helm/ECS/Nomad/cloud deployment, application-only changes, supply-chain-only or security-review-only audits, hosted CI pipelines, final ship decisions, or unexplained container failures.
nledford/engineering-review-board
Stars: 11Claude CodeCodexC# and .NET engineering guidance. Use when adding, changing, reviewing, testing, packaging, restoring, building, publishing, or refactoring C# source, SDK-style .csproj projects, Directory.Build.props/targets, global.json, .sln/.slnx solutions, MSBuild, NuGet PackageReference, ASP.NET Core, Blazor, EF Core, or .NET test projects. Do not use for database-native schema/query design, general WebAssembly host/guest/runtime decisions, checked-in CI/release-provider configuration, Docker/OCI/Compose configuration, or a public API contract; use the owning SQL, WebAssembly, CI/release, container, or API skill instead.
nledford/engineering-review-board
Stars: 11Claude CodeCodexCSS, SCSS/Sass, and Tailwind CSS styling guidance. Use when adding, changing, reviewing, refactoring, adopting, or migrating .css, .scss, .sass, CSS modules, design tokens, cascade layers, container/media queries, responsive layout, stylesheet build pipelines, Tailwind or other utility-class conventions, CSS-in-JS, or styling integration in HTML, JavaScript/TypeScript, PHP/Smarty templates, Python templates, or Rust Leptos/Axum apps. Use ux-accessibility-review for interface accessibility or UX audits. Use language/framework skills for non-styling implementation mechanics and do not use for behavior changes with no styling surface.
nledford/engineering-review-board
Stars: 11Claude CodeCodexData-platform engineering guidance for implementing, changing, reviewing, or testing source-to-landing ingestion, post-landing lakehouse or warehouse transformations, analytical semantic contracts, Power BI semantic models and DAX, and Microsoft Fabric or Power BI operations. Use for CDC, watermarks, replay, Delta tables, medallion layers, analytical grain, governed metrics, TMDL, RLS or OLS, refresh, promotion, gateways, capacity, recovery, and runbooks. Do not use for application domain modeling, physical OLTP database design, generic distributed protocols, generic UX, or final release decisions.
nledford/engineering-review-board
Stars: 11Claude CodeCodexDependency and software supply-chain security review. Use for dependency audits, SBOM/SCA output, CVE/GHSA advisories, package or binary provenance, registry trust, manifests, lockfiles, checksums/signatures, install/postinstall scripts, vendored/generated code, transitive dependency risk, CI actions, container or base-image pinning, or package-manager security policy. Do not use for routine package-manager workflow, language-specific dependency implementation, or third-party API docs without a supply-chain risk question.
nledford/engineering-review-board
Stars: 11Claude CodeCodexDigital asset management (DAM) engineering guidance for photo and video ingest, asset identity, immutable originals, derivatives, metadata, non-destructive edits, organization, smart collections, hierarchies, viewing, sharing, and validation. Use when building, changing, reviewing, or testing a photo/video catalog, media library, asset browser, editing workflow, or related API and data model. Do not use for standalone codec implementation, generic SQL/API/CSS work, or non-media document management without a DAM lifecycle.
nledford/engineering-review-board
Stars: 11Claude CodeCodexDocumentation engineering guidance. Use when creating, editing, refactoring, or reviewing Markdown docs, README files, API docs, code comments, docstrings, examples, Rustdoc, pydoc, Javadoc, JSDoc/TSDoc, PHPDoc, perldoc/POD, XMLDoc/PasDoc, DocC, documentation tests, or developer-facing instructions. Do not use for code-only changes unless docs or comments are part of the change. For reusable SKILL.md contracts, use create-agent-skill.
nledford/engineering-review-board
Stars: 11Claude CodeCodexApply Domain-Driven Design to complex business logic and module boundaries. Use when modeling domains, bounded contexts, aggregates, value objects, repositories, domain services, policies, domain events, ubiquitous language, or refactoring toward clearer domain behavior. Do not use for focused audits of an existing domain model; use domain-modeling. Avoid simple CRUD or data-centric work without meaningful domain pressure.
nledford/engineering-review-board
Stars: 11Claude CodeCodexReview tactical DDD models, aggregates, entities, value objects, invariants, domain services, and ubiquitous language. Use for a focused audit of an existing domain model; do not use to design a new model or force DDD onto simple data-centric work.
nledford/engineering-review-board
Stars: 11Claude CodeCodexUse the DonSeTch MCP server for public web research, source discovery, URL or PDF retrieval, bounded same-domain crawling, OCR, and evidence capture with web_search, web_fetch, web_crawl, or web_screenshot. Use when current external evidence is needed. Do not use for repository-local facts, structured GitHub platform objects, signed-in browser interaction, checked-in Playwright tests, private or sensitive resources, or DonSeTch installation, configuration, and upgrades unless explicitly requested.
nledford/engineering-review-board
Stars: 11Claude CodeCodexSafe Git branch, remote, history-inspection, integration, rewrite, conflict, recovery, tag, and worktree workflows. Use when switching or restoring, fetching/pulling/pushing, managing upstreams or remotes, inspecting history with log/blame/bisect, merging/rebasing/squashing/cherry-picking/reverting/resetting, resolving conflicts, recovering with reflog, or managing tags and worktrees. Do not use for commit grouping or message drafting, checked-in CI/release automation, code review, GitHub pull-request operations, or release-readiness decisions.
nledford/engineering-review-board
Stars: 11Claude CodeCodexHexagonal Architecture / Ports and Adapters guidance centered on how external actors drive or are driven by an application through explicit inbound and outbound ports and adapters. Use when classifying port ownership, replacing delivery or infrastructure mechanisms, or testing the core through those seams. Use clean-architecture when entities, use cases/interactors, and interface-adapter policy flow are primary, onion-architecture for explicit concentric domain/application rings, and architecture-review for a read-only audit. Do not use for simple CRUD, prototypes, or trivial pass-through interfaces.
nledford/engineering-review-board
Stars: 11Claude CodeCodexMCP server engineering guidance. Use when creating, updating, refactoring, testing, or reviewing Model Context Protocol servers, tools, resources, prompts, capability discovery, stdio transport, Streamable HTTP, or legacy HTTP+SSE compatibility. Do not use merely to operate an existing MCP server; use the applicable provider or service skill instead.
nledford/engineering-review-board
Stars: 11Claude CodeCodexOnion Architecture guidance centered on explicit concentric domain, application, and infrastructure rings with dependencies pointing inward. Use when the main design question is ring membership, domain/application separation, or keeping infrastructure at the edge, especially when the project names Onion Architecture. Use hexagonal-architecture when inbound/outbound ports around external actors are primary, clean-architecture for use-case/interactor and interface-adapter policy flow, and architecture-review for a read-only audit. Do not use for simple CRUD, prototypes, or framework-convention-first apps where added layers reduce clarity.
nledford/engineering-review-board
Stars: 11Claude CodeCodexDesign and implement cross-language CPU-bound, data-parallel, and task-parallel computation. Use when decomposing a measured workload into partitions or tasks; selecting granularity, executors or worker pools, reductions, cancellation, failure handling, or deterministic concurrency tests. Do not use for routine async I/O, distributed coordination, Spark, GPU programming, or review-only performance work.
nledford/engineering-review-board
Stars: 11Claude CodeCodex