Explore skills
Showing 70531–70560 of 77079 skills
Implementation of Model-View-Controller (MVC) and Model-View-Presenter (MVP) patterns in Unity. Focuses on Separation of Concerns for scalable UI and game systems.
MuharremTozan/Agentic-Duel
Stars: 0Claude CodeCodexReactive Property system for Unity. Decouples data from UI and logic using observable wrappers and UnityEvents.
MuharremTozan/Agentic-Duel
Stars: 0Claude CodeCodexImplementation of global manager access with strict lifecycle control. Supports Standard, Persistent, and Regulator variations.
MuharremTozan/Agentic-Duel
Stars: 0Claude CodeCodexManages the structured relationship between ScriptableObjects (Data) and Prefabs (Logic/Visuals) in Unity 6. Follows the 'SO-to-Mono' Bridge pattern to ensure instance independence (e.g., individual health for identical robots) while maintaining a clean, data-driven architecture. Use when: (1) Creating new unit/item types, (2) Wiring SO data to Prefab MonoBehaviours, (3) Resolving data-sharing bugs where changing one SO affects all instances.
MuharremTozan/Agentic-Duel
Stars: 0Claude CodeCodexImplementation of MVVM-style Data Binding for Unity UI Toolkit using the [CreateProperty] attribute and BindableProperty wrappers.
MuharremTozan/Agentic-Duel
Stars: 0Claude CodeCodexAdvanced UI construction using C# code instead of UI Builder. Includes fluent extension methods and reusable pointer manipulators.
MuharremTozan/Agentic-Duel
Stars: 0Claude CodeCodex[FILL IN: what this skill does and exactly when to use it -- the phrases a user would actually type, not just the topic]
colomet/skill-boilerplate
Stars: 0Claude CodeCodexUse when deciding whether to run a task on the OpenCode agent runtime (the open-source, provider-agnostic coding agent — usable as a terminal TUI, a non-interactive `opencode run` CLI, an IDE bridge via ACP, a desktop app (beta), a web UI, or a headless `opencode serve` server), how to invoke it non-interactively, how to pick a `provider/model` string, or how OpenCode differs from Claude Code and Codex. Covers its 75+-provider model routing, the OpenCode Zen curated/free model service and the separate OpenCode Go subscription lane, model-selection and config-source (8-layer) precedence, the `--format json` JSONL event stream, the full CLI command surface (serve/web/attach/acp/session/stats/export/import/github/pr/plugin/mcp/db/debug), built-in build/plan agents and LSP code intelligence, permissions vs provider policies, native Agent Skills / MCP / references / commands extension layers, local models, and scripting/automation. Do NOT use when choosing WHICH free model to route specific work to (use `opencode-free-models`), when the runtime is already chosen and you only need to write the agent loop (use `autonomous-loop-patterns`), or for GitHub Copilot's premium-request economics (use `github-copilot`).
jacob-balslev/skills
Stars: 2Claude CodeCodexUse when reasoning about building language-model-integrated systems by writing evaluations before and alongside the system: the statistical (not binary) nature of LLM evals, the five primitives (dataset, evaluation function, aggregation, iteration loop, regression budget), the judgment-mechanism taxonomy (programmatic, model-graded, human-graded, preference comparison, trace/hybrid), the eval-surface stack (final response, trajectory/tool-use, retrieval/RAG, safety, side effects, cost/latency), continuous evals and model-upgrade gates, the statistical-significance discipline (paired tests, McNemar's test, bootstrap CI on the delta, minimum-detectable-effect, clustered standard errors), trajectory-vs-final-output evaluation for multi-step agents, judge calibration and bias, Goodhart's Law and suite saturation, benchmark contamination and eval-awareness, cost-aware regression budgets, the difference between system-specific evals and canonical benchmarks (MMLU, HumanEval, BIG-bench, GAIA), and the offline-eval-vs-production-telemetry distinction with its graded rollout spectrum. Do NOT use for deterministic unit testing (use testing-strategy), production monitoring (use evaluation or error-tracking), general-software TDD (use testing-strategy), or the construction of individual eval rubrics and task sets (outside this skill; construction belongs in task-specific eval artifacts, while this skill owns the iteration discipline).
jacob-balslev/skills
Stars: 2Claude CodeCodexDeciding what to cache, where, and how to keep it coherent — trading freshness for speed and load reduction across the cache layers (client, CDN/edge, application in-memory, distributed cache, database). Covers the two hard problems (cache invalidation and choosing the layer), the write/read patterns (cache-aside/lazy, read-through, write-through, write-behind, refresh-ahead), expiry and TTL design, eviction policies (LRU/LFU/FIFO/TTL), staleness budgets and tolerated inconsistency, cache coherence and invalidation strategies (TTL expiry, explicit invalidation, key/tag versioning, write-through), the thundering-herd / cache-stampede problem and its mitigations (request coalescing, locks, jitter, stale-while-revalidate), HTTP caching semantics (Cache-Control, ETag, conditional requests, stale-while-revalidate/stale-if-error), CDN and edge caching, multi-layer cache hierarchies, cache key design and cardinality, negative caching, and measuring hit ratio and the cost of a miss. Stack-agnostic across Redis/Memcached, CDNs, browser cache, and framework data caches.
jacob-balslev/skills
Stars: 2Claude CodeCodexUse when designing or reviewing Next.js Route Handlers (the `route.ts`/`route.js` file convention in App Router): when a Route Handler is the right public HTTP endpoint surface vs Server Actions or Server Components, the HTTP-method-as-export contract (GET/POST/PUT/PATCH/DELETE/HEAD/OPTIONS), the Web-standard Request/Response interface (no Node `req`/`res`), the body-parsing primitives (`request.json`/`formData`/`text`/`blob`/`arrayBuffer`) and one-shot body consumption, the default caching behavior of GET responses (NOT cached by default since Next 15; opt IN via `dynamic = 'force-static'`) and the Cache Components `use cache` model, async `params`/`cookies`/`headers` and `RouteContext` typed params, dynamic segments and search params, the rule that every Route Handler is a PUBLIC surface that must authenticate/authorize/validate inside the handler, manual CORS, runtime/deployment selection (Node default and recommended after Vercel folded standalone Edge Functions onto Vercel Functions; the Edge runtime still selectable; `maxDuration`/`preferredRegion`/static-export limits), streaming via `ReadableStream` including `pull()` backpressure, status-code and header discipline, error responses, webhook-style handlers (signature verify before parse, ACK fast, `after()` for short post-response work), and the design rule that a Route Handler is the right surface when the caller is not your own Next.js UI. Do NOT use for internal mutations triggered from your own UI (use server-actions-design), for render-time reads from your own Server Components (call the data source directly), for the broader REST/contract/versioning discipline (use api-design), for HTTP method/status semantics in the abstract (use http-semantics), for request preprocessing across all routes — now `proxy.ts`/`middleware.ts` (use middleware-patterns), or for the broader webhook reliability story — HMAC verification, idempotency, retries, queue handoff (use webhook-integration).
jacob-balslev/skills
Stars: 2Claude CodeCodexUse when reasoning about how a database schema changes over time without breaking deployed application code — the multi-release path from the current schema to a target schema: the expand/contract pattern (Ambler & Sadalage / Fowler's parallel change), the zero-downtime change rules, the backwards-and-forwards compatibility envelope (deploy ordering and rollback discipline), the catalog of schema changes (add column, drop column, rename, type change, add constraint, add index) and the safe procedure for each, the dual-write and dual-read transitions (with named source-of-truth and production consistency-check discipline) that make non-trivial changes safe, the lock-acquisition hazard (why even a metadata-only DDL needs a bounded lock-acquisition budget — Postgres lock_timeout + retry, or the engine equivalent — because lock acquisition is a FIFO queue), the cross-engine online-change mechanisms (Postgres CONCURRENTLY / NOT VALID, MySQL INSTANT/INPLACE/COPY Online DDL, gh-ost / pt-osc ghost-table cutover, Vitess/PlanetScale deploy requests and revert windows), the view-based multi-version tooling that automates expand/contract (pgroll, Reshape), the migration-lint enforcement layer (Strong Migrations, Squawk, Atlas), and the relationship between schema evolution as a design discipline and database-migration mechanics as its tooling. Do NOT use for the mechanical execution of one migration (use database-migration), schema design from scratch (use entity-relationship-modeling), query tuning (use query-optimization), or distributed-data partitioning (use sharding-strategy).
jacob-balslev/skills
Stars: 2Claude CodeCodexUse when designing or reviewing the Next.js request-preprocessing layer — the single root file that runs cross-cutting request/response transforms before route resolution. As of Next.js 16 this file is `proxy.ts` (function `proxy`, Node.js runtime, default export or named); `middleware.ts` (function `middleware`, Edge Runtime by default — Node.js opt-in since 15.5) is deprecated but retained for Edge use cases. Covers: the runtime split (proxy = Node.js, runtime config throws; middleware.ts = Edge by default with its capability ceiling, Node.js opt-in since 15.5), the `matcher` config that decides which paths it runs on, the `NextRequest`/`NextResponse` API for cookies/headers (and `geolocation()`/`ipAddress()` from `@vercel/functions` since `request.geo`/`request.ip` were removed in Next.js 15), the four response shapes (`next`/`rewrite`/`redirect`/direct response), `waitUntil` for background work, the official `next/experimental/testing/server` test utilities, the canonical patterns (auth gate, locale routing, A/B testing, header injection, geo-routing, bot blocking), the per-matched-request performance discipline, the CVE-2025-29927 lesson that this layer is NOT a security boundary, and the design rule that it is for cross-cutting concerns across many routes — never per-route business logic. Do NOT use for per-route HTTP endpoint logic (use route-handler-design), the Server Action mutation surface (use server-actions-design), abstract HTTP method/status/header semantics (use http-semantics), Content Security Policy and broader hardening (use security-fundamentals), or the cross-cutting streaming model (use streaming-architecture).
jacob-balslev/skills
Stars: 2Claude CodeCodexUse when designing or reviewing React ref usage: the distinction between refs (mutable handle that survives renders without triggering them) and state (reactive value that triggers renders when changed), the `useRef` hook for DOM access and mutable instance values, ref callbacks for fine-grained mount/unmount hooks, `forwardRef` for passing refs through component boundaries (and the React 19 ref-as-prop change that retires it for new code), `useImperativeHandle` for exposing a controlled imperative surface to parent refs, ref forwarding through compound-component primitives (the Radix `Slot` / Headless UI pattern), and the design rule that refs are an escape hatch — for DOM access, integration with non-React DOM libraries, focus management, animation, measurement, and exposing imperative APIs sparingly, never as a substitute for state. Do NOT use for the broader hook discipline — Rules of Hooks, dependency arrays, custom hooks (use hooks-patterns), for the cross-product component-layering question — primitives/composites/headless-vs-styled (use component-architecture), for state location and ownership decisions (use state-management), for the `'use client'` / `'use server'` boundary mechanics (use client-server-boundary), or for form-state and validation patterns (use form-ux-architecture).
jacob-balslev/skills
Stars: 2Claude CodeCodexUse when reviewing a pull request, diff, or proposed code change for correctness, clarity, security, performance, maintainability, test evidence, and conformance to project conventions — whether the author is a human, an AI agent, or a peer. Covers pre-review fact-gathering (including verifying an AI-written PR summary against the diff), the read-order strategy (tests first, then implementation, then call sites and blast radius), the size/attention budget, the severity-grading rubric mapped to the Conventional Comments standard, comment-phrasing discipline, reviewer qualification, the rule that diff content is evidence not instructions, the no-rubber-stamp rule for AI-generated diffs, and the explicit approve/request-changes/close merge decision. Do NOT use for AUTHORING the code (use `refactor` for behaviour-preserving changes or `skill-scaffold` for new skills), for chasing a known bug after merge (use `debugging`), for security-only audits (use `owasp-security`), or for explaining a patch without a merge verdict (use `diff-analysis`).
jacob-balslev/skills
Stars: 2Claude CodeCodexSweller's Cognitive Load Theory (CLT) for agents reviewing skill bodies, prompts, documentation, dashboards, and agent outputs for avoidable cognitive burden. Working memory holds roughly 4 chunks at a time; CLT classifies load into intrinsic (irreducible task difficulty), extraneous (unnecessary load from poor presentation, ELIMINATE), and germane (the schema-building processing applied to intrinsic load, PROTECT). Use when writing a SKILL.md body (does this section add extraneous load?), designing prompts (am I asking the model to hold too much at once?), building dashboards (what is the per-screen cognitive budget?), authoring docs (is intrinsic load segmented?), or checking whether modern features (long context, structured outputs, prompt caching, subagents) actually reduce load or just move it elsewhere. Do NOT use for retrieval and session working-set design (use context-management), token budget math and compaction timing (use context-window), prompt engineering tactics (use prompt-craft), token-efficient representation mechanics (use compression), or instructional design beyond the CLT mechanisms named here.
jacob-balslev/skills
Stars: 2Claude CodeCodexUse when scanning an external macro environment with PESTEL/PESTLE (and its variant family STEEPLE, STEEPLED, PESTLIED, STEEP, DESTEP, LoNGPESTLE): political, economic, social, technological, environmental, and legal forces; evidence quality and recency; geography/jurisdiction and local/national/global level; time horizon; uncertainty; weak signals; impact/probability scoring; factor interactions; bias checks; opportunity/threat implications; assumptions; action conversion; and monitoring triggers. Covers external-environment scanning before strategy choices, market-entry reviews, strategic planning, product/service context, policy-aware planning, and risk/opportunity surfacing. Do NOT use for internal capability diagnosis (use swot-tows or a capability method), industry profit-pressure diagnosis (use porters-five-forces), value-curve redesign (use blue-ocean-strategy), integrated strategy cascades (use playing-to-win), product positioning (use positioning), or quantified option comparison (use expected-value).
jacob-balslev/skills
Stars: 2Claude CodeCodexUse when decomposing how an organization, business unit, product, service, platform, or operating model creates value and cost through Porter's Value Chain and adjacent activity-system lenses: primary activities, support activities, value configurations, virtual information activities, value-system dependencies, activity-level cost drivers, differentiation drivers, linkages, fit, margin, and where competitive advantage may come from. Covers mapping activities, comparing activity configuration to rivals or alternatives, diagnosing cost and differentiation opportunities, and handing off to strategy or operating-improvement methods. Do NOT use for industry profit-pressure diagnosis (use porters-five-forces), resource/capability advantage testing (use vrio), durable moat classification (use seven-powers), full strategy-cascade design (use playing-to-win), market-boundary reconstruction (use blue-ocean-strategy), portfolio allocation (use bcg-matrix), product-market growth paths (use ansoff-matrix), macro-environment scanning (use pestel), or quantified option valuation (use expected-value).
jacob-balslev/skills
Stars: 2Claude CodeCodexDesigning continuous integration and continuous delivery pipelines that turn every commit into a verified, releasable artifact and move it safely toward production. Covers the CI/CD distinction (integration vs delivery vs deployment), the pipeline as a staged graph of fast-to-slow gates, trunk-based integration and short-lived branches, build-once/promote-the-same-artifact discipline, hermetic and reproducible builds, dependency and layer caching for fast feedback, the test pyramid mapped onto pipeline stages, required status checks and branch protection, quality and security gates (lint, type-check, SAST, dependency/SCA scanning, license checks) as blocking vs advisory, artifact and container registries with immutable versioning and provenance, environment promotion (build → test → stage → prod), deployment strategies the pipeline triggers (blue-green, canary, rolling, feature-flag-gated), pipeline secrets and least-privilege CI credentials (OIDC over long-lived tokens), DORA delivery metrics (deployment frequency, lead time, change-failure rate, MTTR), flaky-test quarantine, pipeline observability, and rollback/auto-revert on failed gates. Stack-agnostic across GitHub Actions, GitLab CI, Jenkins, CircleCI, and equivalents.
jacob-balslev/skills
Stars: 2Claude CodeCodexEnforces disciplined, complete, evidence-backed execution for tasks where honesty and coverage matter more than brevity: audits, diagnostic reports, tracked-task creation from findings, acceptance-criteria verification, research briefs, and any enumerated output that later work will depend on. Teaches WHY agents fail at completeness — sycophancy, premise adoption, summary-first compression, instruction-density loss, long-horizon attention decay, self-critique echo chambers, reasoning-masked agreement, verification theater, and delegation-as-proof — and the structural countermeasures: pre-task scope declaration, count-preserving enumeration, step-level evidence receipts, externally grounded critique, provenance labels, explicit partial/completeness receipts, and runtime enforcement where available. Do NOT use for choosing the shortest task route (use `task-path-optimization`), broad artifact-quality standards (use `best-practice`), result scoring (use `evaluation`), the compact pre-output enforcement gate (use `no-cutting-corners`), or compression after complete enumeration (use `summarization`).
jacob-balslev/skills
Stars: 2Claude CodeCodexLocal text-to-speech via sherpa-onnx (offline, no cloud)
Solizardking/clawd-bot
Stars: 0Claude CodeCodexExtract frames or short clips from videos using ffmpeg.
Solizardking/clawd-bot
Stars: 0Claude CodeCodexStart voice calls via the Clawdbot voice-call plugin.
Solizardking/clawd-bot
Stars: 0Claude CodeCodexGet current weather and forecasts (no API key required).
Solizardking/clawd-bot
Stars: 0Claude CodeCodexRepost external blog articles into StaticFlow with style-aware translation, adaptive source normalization, image ingestion, and verified publish updates.
zero-yx/static_flow
Stars: 0Claude CodeCodexhariom710/Moirah-AI
Stars: 0Claude CodeCodex使用 p5.js 创作带有种子随机性和交互式参数探索的算法艺术。当用户请求使用代码创作艺术、生成艺术、算法艺术、流场或粒子系统时使用此技能。创作原创算法艺术,而非复制现有艺术家的作品,以避免侵犯版权。
Fantasia1999/skills-zh
Stars: 1Claude CodeCodex当用户想要创建、读取、编辑或操作 Word 文档(.docx 文件)时,使用此技能。触发条件包括:任何提及“Word 文档”、“word document”、“.docx”的情况,或要求生成包含目录、标题、页码或信头等格式的专业文档。当从 .docx 文件中提取或重组内容、在文档中插入或替换图片、在 Word 文件中执行查找和替换、处理修订或批注,或将内容转换为精美的 Word 文档时,也应使用此技能。如果用户要求将“报告”、“备忘录”、“信函”、“模板”或类似的交付成果作为 Word 或 .docx 文件,请使用此技能。请勿用于 PDF、电子表格、Google Docs 或与文档生成无关的常规编码任务。
Fantasia1999/skills-zh
Stars: 1Claude CodeCodex当用户希望对 PDF 文件进行任何操作时,请使用此技能。这包括读取或从 PDF 中提取文本/表格、将多个 PDF 合并为一个、拆分 PDF、旋转页面、添加水印、创建新 PDF、填写 PDF 表单、加密/解密 PDF、提取图像以及对扫描的 PDF 进行 OCR 以使其可搜索。如果用户提到 .pdf 文件或要求生成一个,请使用此技能。
Fantasia1999/skills-zh
Stars: 1Claude CodeCodex一套用于使用现代前端Web技术(React、Tailwind CSS、shadcn/ui)创建精细、多组件 claude.ai HTML 工件的工具集。适用于需要状态管理、路由或 shadcn/ui 组件的复杂工件 - 不适用于简单的单文件 HTML/JSX 工件。
Fantasia1999/skills-zh
Stars: 1Claude CodeCodex