Skills de Claude Code · página 67

将直播排期、货盘节奏、场控流程、主播话术、互动机制、异常预案和复盘指标等资料，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理直播运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。

检索图片、背景音乐、音效、视频等素材；图片优先直搜候选，其他资源走任务主链。

将团队 SOP、交付流程、角色职责、项目复盘、FAQ、决策边界和升级机制，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的组织经验知识库。适用于用户要求“整理组织知识库”“沉淀团队 SOP”“把交付经验变成项目资料”“维护组织 know-how”的场景。

读取本地或工作区 PDF 内容，并输出结构化解读结果。

将访谈稿、聊天记录、简历、公开内容、业务资料、案例和既有 DOCX/Markdown 文档，提炼成可被 AI 长期调用的个人 IP 知识库。适用于用户要求“生成个人知识库”“整理成个人 IP 成品知识库”“为创始人/专家/讲师/主播/顾问建立AI知识库”“把资料变成个人IP底层提示词/写作风格库/故事素材库/话术库”的场景。

根据目标说明生成一份可直接讲述、继续导出的单文件演示稿 Markdown，并落到工作区供右侧 viewer 预览。

将用户分层、社群 SOP、触达节奏、转化话术、活动机制和服务边界等资料，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理私域 / 社群运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。

联网检索并产出结构化研究报告，强调结论、证据、风险与建议。

联网信息检索与趋势调研（优先产出可引用结论，而非原始片段堆砌）。

通过站点适配器检索指定站点内容（GitHub、知乎、B站、36Kr、linux.do、什么值得买、Yahoo Finance、X 长文）。

提炼当前文本、对话或显式文件内容中的关键要点与结论。

提交音频或视频转写任务，生成逐字稿或字幕任务。

将当前文本、对话或显式文件内容翻译成目标语言，并保留原意与关键信息。

优化文稿排版与可读性，不改变原始事实与核心表达。

解析外部 URL 内容，并沉淀为可阅读的文本结果。

提交视频生成任务，并触发前端视频生成流程。

根据目标说明生成可直接预览的单文件 HTML 网页，并落到工作区供右侧 viewer 预览。

Lime CLI 平台技能，统一任务创建、状态查询、重试、队列与幂等语义。

通过 Lime CLI 创建播客文本整理任务。

通过 Lime CLI 创建素材检索任务。

通过 Lime CLI 创建文稿排版优化任务。

通过 Lime CLI 创建链接解析任务。

准备并执行 Lime 发版；覆盖版本号、发布说明、产物清理、验证门禁、commit、tag 和推送。

Govern Lime legacy cleanup, fact-source convergence, current/compat/deprecated/dead classification, and guardrails.

Choose Lime validation commands for GUI, command/bridge, config, version, and PR-readiness changes.

Research and inspect pages through Lime's managed browser session.

Before answering a substantive question, quietly check whether the user has already resolved this question in the past.

List the Claude Code plugins currently enabled for the agent, read straight from settings.json.

Weekly self-audit playback. Surface patterns from the user's past week that they probably cannot see themselves.

Find commitments the user made in the last two weeks and did not follow through on. A promises audit.

Discover recurring behaviors from memory and offer to formalize them as scheduled jobs.

List the agent's current skills, memory files, plugins, subagents, hooks, and a settings summary plus dashboard URLs. The user-facing discovery path for everything the operator can edit.

Show how the user's thinking on a specific topic has evolved over time. A chronological narrative with turning-point callouts.

Reference for all Nixopus API operations callable via nixopus_api(method, path, body)

Generate Caddyfile configurations for static sites and reverse proxies — SPA fallback routing, cache headers, compression, redirects, and error pages. Use when deploying a static site that needs custom Caddy configuration, or when the user needs SPA routing, caching, or redirect rules.

Generate docker-compose.yml for multi-service setups including databases, caches, and service dependencies. Use when the app needs a database, cache, message broker, or has multiple independently deployable services.

Size container memory and CPU limits, diagnose OOM kills and CPU throttling, and recommend resource adjustments by ecosystem. Use when containers are being OOM-killed, running slowly, or when setting initial resource limits for a deployment.

Build and deploy C/C++ applications — CMake, Meson, Ninja, and Dockerfile patterns. Use when deploying a C or C++ project, or when CMakeLists.txt or meson.build is detected.

Run database migrations safely during deployment — framework-specific commands, pre-deploy vs post-deploy timing, health gates, and rollback strategies. Use when the app has a database migration system and needs migrations run during deployment.

Build and deploy Deno applications — version detection, dependency caching, and Dockerfile patterns. Use when deploying a Deno project, or when deno.json or deno.jsonc is detected.

Sub-agent routing table — which agent handles diagnostics, machine health, infrastructure, GitHub, billing, and notifications. Load when the current task is not a direct deployment.

Full deploy pipeline — source detection, hints-driven analysis, project creation, deployment monitoring, and live URL delivery. Load when the user wants to deploy an application.

Analyze a repository to determine ecosystem, deployment targets, ports, build commands, and monorepo structure. Use when starting a new deployment, onboarding a repository, or when the user asks what stack or framework a project uses.

Layer-by-layer diagnostic workflow for application and container issues — deployment logs, container state, HTTP probes. Load when investigating a deployment failure or runtime issue.

Generate production-ready multi-stage Dockerfiles per ecosystem with best practices. Use when the user needs a Dockerfile, asks about containerization, or when no Dockerfile exists in the repository.

Generate ecosystem-specific .dockerignore files to reduce build context size and prevent secret leaks. Use when no .dockerignore exists, when the build context is large, or when secrets may be leaking into images.

Domain setup for applications. Preferred path is passing domains at creation time via createProject. Falls back to add_application_domain for post-creation attachment or custom domains.

Diagnose domain resolution, TLS certificate provisioning, and reverse proxy routing issues. Use when a domain is not resolving, TLS certificates fail, proxy returns 502/503/504, or custom domains are stuck in pending status.

Build and deploy .NET applications — ASP.NET Core, version detection, self-contained builds, and Dockerfile patterns. Use when deploying a .NET or C# project, or when a .csproj file is detected.

Build and deploy Elixir and Phoenix applications — version detection, mix releases, and Dockerfile patterns. Use when deploying an Elixir or Phoenix project, or when mix.exs is detected.

Detect required environment variables from source code, config files, and .env examples. Use when preparing for deployment, checking for missing env vars, or when the user asks about required environment configuration.

Diagnose deployment failures, container crashes, and networking issues using structured pattern matching on logs and container state. Use when a deployment fails, a container crashes or exits unexpectedly, or the app is unreachable after deployment.

Guide users through connecting GitHub to Nixopus when no GitHub connector exists. Covers GitHub App installation for cloud users and GitHub App manifest setup for self-hosted users.

Fix-via-PR workflow, file operations, connector resolution, and GitHub safety rules. Load when performing GitHub operations like creating branches, PRs, or file changes.

Build and deploy Gleam applications — erlang-shipment, version detection, and Dockerfile patterns. Use when deploying a Gleam project, or when gleam.toml is detected.

Build and deploy Go applications — version detection, static binaries, CGO, workspaces, and Dockerfile patterns. Use when deploying a Go project, or when go.mod is detected.

Structured incident response workflow — severity classification, diagnosis delegation, auto-fix decisions, notification, and post-incident review. Use when an automated failure event is received or when the user reports a production incident.

Build and deploy Java applications — Maven, Gradle, Spring Boot, version detection, and Dockerfile patterns. Use when deploying a Java project, or when pom.xml or build.gradle is detected.

Machine-level diagnostic layers, lifecycle management (restart/pause/resume), metrics analysis, and backup operations. Load when investigating server health or managing machine state.

MCP server discovery, tool invocation, and provider catalog integration. Load when a task involves external services, third-party tools, or when the user asks about MCP servers.

Deploy multi-service monorepo applications — service discovery, dependency ordering, shared build contexts, selective deployment, and compose generation. Use when the repository contains multiple deployable services, apps, or packages.

Look up Nixopus platform documentation at runtime. Use when the user asks about Nixopus features, configuration, concepts, self-hosting, API reference, guides, or anything where accurate product information is needed. Prevents hallucination by fetching the latest docs.

Build and deploy Node.js applications — version detection, package managers, framework-specific builds, monorepo support, and Dockerfile patterns. Use when deploying a Node.js, JavaScript, or TypeScript project, or when package.json is detected in the repository.

Proactive welcome flow for new Nixopus users. Triggered by the frontend __ONBOARD__ signal when a user has no GitHub connectors and no deployed applications. Greets the user warmly, explains what Nixopus is, and immediately loads the github-onboarding skill to deliver correct GitHub connection steps.

Build and deploy PHP applications — Composer, Laravel, Symfony, FrankenPHP, PHP-FPM, and Dockerfile patterns. Use when deploying a PHP project, or when composer.json or index.php is detected.

Verify a deployment is healthy after it completes — HTTP probes, healthcheck endpoints, container stability, log scanning, and port alignment. Use after any deployment to confirm the app is running and reachable.

Validate deployment readiness before triggering a build — check Dockerfile, ports, env vars, healthchecks, and resource config. Use before any deployment to catch common configuration issues early.

Build and deploy Python applications — uv, poetry, pdm, pipenv, pip, framework detection, and Dockerfile patterns. Use when deploying a Python project, or when requirements.txt, pyproject.toml, or Pipfile is detected.

Guide rollback decisions after failed deployments — when to rollback vs retry, verification after rollback, and state preservation. Use when a deployment fails repeatedly, the app is unreachable after deploy, or the user requests a rollback.

Build and deploy Ruby applications — Bundler, Rails, Rack, asset pipeline, bootsnap, and Dockerfile patterns. Use when deploying a Ruby or Rails project, or when a Gemfile is detected.

Build and deploy Rust applications — version detection, release binaries, cargo-chef, and Dockerfile patterns. Use when deploying a Rust project, or when Cargo.toml is detected.

Self-healing loop for failed deployments — diagnose, fix, redeploy up to 3 attempts, then escalate or rollback. Load when a deployment fails or build errors occur.

Deploy shell script applications — interpreter detection, setup scripts, and Dockerfile patterns. Use when deploying a shell script project, or when start.sh is detected.

Deploy static file sites — Caddy/nginx serving, Staticfile config, and Dockerfile patterns. Use when deploying a static HTML site with no server-side runtime, or when index.html or a Staticfile is detected at the project root.

Initialize evo for the current repository by exploring the codebase, proposing unexplored optimization dimensions, constructing the benchmark inside a baseline worktree, and running the first experiment. Use when the user invokes /evo:discover, mentions setting up evo, wants to instrument a codebase for autonomous optimization, or asks to start a new evo run on a project.

Non-user-invocable provider/setup reference for evo backend switching, prerequisite checks, and auth/install guidance.

Run the evo optimization loop with parallel subagents until interrupted.

Read-only evo run reporting. Use when the user invokes /evo:report, asks what happened overnight, asks what improved recently, asks for the best/frontier candidates, asks for a quick score chart without opening the dashboard, or wants the scatter plot in chat output. Never run benchmarks, gates, Slurm commands, evo run, or ad-hoc verification scripts for report requests.

Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to understand the brief shape its dispatched subagents expect + what they're required to emit -- useful when writing briefs or debugging a subagent's behavior.

This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.

Land the winning experiment from an evo run as a clean, mergeable change -- open a PR when the repo has a remote, otherwise merge into the working branch. Distills the best-scoring experiment down to the minimal diff that reproduces its behaviour, shaped for the qualities a maintainer merges on (scope discipline, test integrity, style adherence), then attaches an advisory mergeability report. Use when the user invokes /evo:ship, asks to land/merge/ship the best result, or wants to turn a finished optimization into a pull request.

Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.

Present time-aware itineraries with clear actions and citations

Keep activity suggestions safe and respect local conditions

Apply the standard Coding workspace workflow with explicit inspection, scoped edits, and proportionate validation.

別エージェントのinboxにメッセージを送信する。agent-to-agent通信の唯一の手段。

全エージェント（家老・足軽1-7・軍師）の稼働状態を一覧表示するスキル。tmux pane状態（稼働中/待機中/不在）とタスクYAML状態（task_id, status）と未読inbox数を統合表示。「稼働確認」「エージェント状態」「布陣確認」「agent status」で起動。

>

>

|

README.md（英語）とREADME_ja.md（日本語）の同期を確認・実行するスキル。README変更時に両言語版を必ず同時更新するために使用。「README更新」「README同期」「readme sync」で起動。

|

|

>-

>-

Draft a new release of the project.

>-

Automate browser interactions, test web pages and work with Playwright tests.

Dry run for release: summarize changes since last release and suggest version bump.