agent-decision-receipts
alirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kAgent Skills
共 5381 个 Skill，按仓库 star 排序。分类自动生成，仅供参考。
全部文档与办公202前端与设计261需求与规划324编码与调试449浏览器与测试380安全269Git 与发布465运维与云391数据181图表98写作与翻译239图像与视频451营销与商业510扩展智能体662科研189其他310
agent-designeralirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kagent-harnessalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kagenthubalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kagent-launcher-orchestratoralirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kagent-memoryalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kagent-protocolalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kagent-workflow-designeralirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kagile-product-owneralirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kai-act-readinessalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kaims-auditalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kai-securityalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kanalytics-trackingalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kandreessenalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kapi-design-revieweralirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kapi-test-suite-builderalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kapple-hig-expertalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kapp-store-optimizationalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kboost-asio-proalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kboost-asio-pro
Use when writing or reviewing asynchronous C++ networking code with Boost.Asio or standalone Asio — TCP/UDP servers and clients, SSL/TLS, timers, strands, io_context, co_spawn, awaitable, async_read/async_write, asio::spawn, yield_context, or pre-C++20 completion-handler callbacks.
写作与翻译
deepreadalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kdeepread
Use when the user asks to deeply read a book, article, PDF, or document set; extract claims and evidence; build a knowledge map; or learn through Feynman explanation and recall. Covers quick, deep, map, Feynman, and whole-book reading modes.
文档与办公
hivemindalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28khivemind
Orchestrate free opencode workers from Claude Code to cut token costs. Use when delegating grunt work to a single worker or a parallel swarm (scout/coder/tester) with worktree isolation, benchmarking against opencode, or when the user says "spawn a worker", "swarm", "delegate to opencode", or "/oc".
扩展智能体
loop-libraryalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kloop-library
Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs. Use when a user asks to analyze a codebase for potential loops, mine coding-thread history for work done more than once, turn repeated engineering work into a loop, find or recommend a published loop, create a recurring agent workflow or automation cadence, turn an outcome into a bounded copy-ready loop, or review an existing loop for weak checks, unsafe authority, unbounded repetition, stale state, or unclear stopping behavior.
扩展智能体
minimalistalirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kminimalist
Use when the user asks to write code efficiently, avoid over-engineering, reduce dependencies, or prevent unnecessary abstractions. Enforces a strict efficiency ladder: YAGNI, reuse, stdlib, native platform, existing deps — before writing any new code.
写作与翻译
strict-apialirezarezvani/claude-skills28k
alirezarezvani/claude-skills28kstrict-api
Use when the user says 'no hallucinations', 'verify APIs', 'reality check', or 'don't invent functions'. Prevents the agent from calling methods, imports, or variables that do not provably exist in the user's installed version.
其他