aiocean
- 74 skills
- 0 followers
- 9 hours ago last updated
- ▌ Validate · aioceanRun the marketplace validation script to check plugin integrity. Use when finishing plugin work, after adding or modifying plugins, or before committing plugin changes.
- ▌ Aio Tui · aiocean bundleBuild interactive terminal UIs with Go + the charmbracelet v2 stack (charm.land/bubbletea/v2, charm.land/lipgloss/v2) — Elm architecture, restrained styling, and production-grade patterns for async rendering, layout geometry, keymaps and mode machines, mouse click/drag/wheel and resizable panes, floating modals and command palettes, responsive layout, horizontal scroll and soft wrap, test design and visual verdicts. Use when building a TUI, terminal UI, Bubbletea app, interactive dashboard, file explorer, monitor, or CLI UI in Go.
- ▌ Aio Boox · aiocean bundlePush books/docs and read notes from an Onyx BOOX e-reader account (push.boox.com / send2boox.com) WITHOUT the web UI, via the self-contained `boox.mjs` CLI. Uploads a file to Aliyun OSS, writes a digital_content doc into the device's MESSAGE sync channel, and calls saveAndPush to notify the device — the exact 3-step flow the web app performs. Also lists the push list, lists synced notes, removes pushed items, and shows device online status. Auth = long-lived JWT via BOOX_TOKEN env or a token file.
- ▌ Aio Map · aioceanTrace dependencies, call graphs, and blast radius for a file/function/module via GitNexus + LSP. Step 2 of the codeflow discover → map → plan trio (after aio-discover, before aio-plan).
- ▌ Aio X · aioceanPost tweets and threads, search timelines, read mentions, and manage Twitter/X content via x-mcp (auto-installs if missing). Use when the user mentions a tweet/x.com URL, asks to post on X, draft a thread, search Twitter, pull engagement data, or schedule social posts.
- ▌ Aio Plan · aioceanSynthesize discovery and dependency mapping into a step-by-step implementation plan via planner agent. Step 3 of the codeflow discover → map → plan trio (after aio-discover and aio-map).
- ▌ Aio Github · aioceanRead and manage GitHub repos, pull requests, issues, releases, and branches via github-mcp (auto-installs if missing). Use when the user mentions a GitHub URL, asks to open/review/merge a PR, comment on an issue, list repos, trigger a release, or run any GitHub action programmatically.
- ▌ Aio Gitlab · aioceanRead and manage GitLab merge requests, CI/CD pipelines, branches, and jobs via gitlab-mcp (auto-installs if missing). Use when the user mentions a GitLab URL, asks to open or review an MR, debug a failing pipeline, retry a CI job, protect a branch, trigger a pipeline run, or run any GitLab operation programmatically via glab or the MCP server. Supports gitflow commands (create feature, finish release, hotfix) and self-hosted GitLab instances.
- ▌ Aio Kanban · aiocean bundleMarkdown-based kanban board for AI agent task management. Board is a pure index (`.kanban/board.md`), every task lives in its own file (`.kanban/tasks/T-NNN-slug.md`). Use to init the board, add tasks, move them across Backlog/Todo/Doing/Done/Blocked, or archive completed work.
- ▌ Aio Xstate · aiocean bundleImplement XState v5 state machines with strict patterns — setup().createMachine(), actors, and TypeScript typing. Use when working with finite state machines (FSM), statecharts, state diagrams, or the actor model in TypeScript. Covers @xstate/react integration (useMachine, useActor, useSelector), parallel states, hierarchical (nested) states, XState migration from v4 to v5, and the full design-first workflow: state inventory, event catalog, transition table.
- ▌ Aio Debug · aiocean bundleDebug broken code — orchestrates codebase context gathering, root cause investigation, minimal fix, and code review validation via debugger agent.
- ▌ Aio Worktree · aiocean bundleManage git worktrees for parallel development workflows — create, sync, and spotlight preview.
- ▌ Aio Youtube · aiocean bundleSearch YouTube and extract video transcripts/subtitles/metadata via yt-dlp. Use whenever the user mentions a youtube.com URL, asks to summarize a video, pull a transcript, fetch video metadata, list a channel/playlist, or download subtitles in any language.
- ▌ Aio RAG Kit · aioceanSet up vector database collections, index content, and run semantic search via RAG pipelines using Qdrant and rag-kit (auto-installs if missing). Use for retrieval-augmented generation, similarity search over a knowledge base, or embedding content for meaning-based retrieval.
- ▌ Aio Tanca · aioceanManage employee timekeeping, shifts, and attendance via tanca-mcp (auto-installs if missing).
- ▌ Aio Discover · aioceanFind code, locate implementations, and understand how features work via parallel Explore agents. Step 1 of the codeflow discover → map → plan trio used before implementation.
- ▌ Aio Gitnexus · aioceanInstall, configure, and manage the GitNexus code intelligence engine — index codebase, setup MCP, check status, troubleshoot, and document local git-hook auto-refresh for master-only workflows.
- ▌ Aio Snapshot · aioceanCapture a GitNexus baseline of the codebase before coding so aio-review-quick can detect what changed afterwards.
- ▌ Aio Uiux · aiocean bundleWeb UI design and review advisor — applies UX psychology, interaction patterns, WCAG accessibility, and modern CSS to design new interfaces or critique existing ones. Use proactively when reviewing any frontend UI, scaffolding new components, or deciding layout/color/typography trade-offs.
- ▌ Aio Anti Slop · aiocean bundleRemove AI slop from prose and code. Use when text or code reads AI-generated and the tells need removing — user says "deslop", "unslop", "anti-slop", "humanize", "bớt giọng AI", "nghe như AI viết", "văn AI quá", "sounds like ChatGPT", "make it sound human", "làm cho tự nhiên hơn"; before publishing any agent-drafted prose (README, docs, blog post, report, announcement, commit/PR message); or when reviewing an agent-written diff for code slop (narrating comments, defensive try/catch on trusted paths, any-casts, needless abstraction).
- ▌ Aio Doc Writer · aiocean bundleGenerate comprehensive architecture documentation — the Codebase Oracle that writes docs, module docs, and dependency maps — powered by the GitNexus knowledge graph and LSP analysis.
- ▌ Aio Mermaid · aioceanGenerate shareable Mermaid diagram URLs (LZ-String compressed). Use when you want to draw a diagram, create an architecture diagram, generate a flowchart, make a sequence diagram URL, build a mindmap, timeline, or gitgraph — and share it as a link. Supports all Mermaid v11 types: flowchart, sequenceDiagram, classDiagram, stateDiagram-v2, erDiagram, gantt, pie, mindmap, timeline, gitgraph.
- ▌ Aio Dream · aioceanMemory consolidation — review, merge, prune and re-index memory files so future sessions orient quickly.
- ▌ Aio Review Deep · aioceanDeep multi-agent code review — dispatch a fleet of parallel specialized agents (security, architecture, quality, performance) with GitNexus domain analysis. Use before merging a PR or after a major feature lands when a single-pass review is too shallow. For a quick pre-commit sanity check use aio-review-quick.
- ▌ Aio Rubber Duck · aiocean bundleRubber duck companion — Claude plays the duck (asks questions, probes assumptions, never rushes a solution); the user explains the problem step by step to externalize reasoning.
- ▌ Aio Atlassian · aioceanRead, create, and update Jira issues, sprints, and workflows plus Confluence pages via the Atlassian CLI. Use when the user mentions a Jira ticket key (e.g. PROJ-123), asks for a JQL/CQL search, wants to transition an issue, manage a sprint/backlog, or read/write a Confluence page.
- ▌ Aio Mental Models · aiocean bundleDecision and reasoning advisor — picks 2-3 relevant mental models, walks through applying each, and synthesizes a recommendation. Use proactively when facing a hard trade-off, an ambiguous decision, or any "should we do X or Y" question where structured reasoning beats gut feeling.
- ▌ Aio Threat Models · aiocean bundleThreat modeling framework advisor — selects the right framework(s) for the system (security, privacy, AI/ML, cloud, K8s), walks through application, and composes findings across frameworks. Use proactively when reviewing architecture for risk, conducting a security architecture review, assessing a system's attack surface, enumerating threats, analyzing security posture, modeling vulnerabilities, or performing a structured risk assessment.
- ▌ Aio Review Quick · aioceanQuick pre-commit sanity check — validate post-implementation changes against the aio-snapshot baseline via change detection, duplication detection, and type checking. Light pass; for deep multi-agent review use aio-review-deep.
- ▌ Aio Kanban Monitor · aiocean bundleWatch the kanban board (`.kanban/board.md`) and auto-dispatch a sub-agent for each task in a chosen column whose content matches a free-text goal. Use when you want one Claude session to run "headless executor" while another session triages and writes new tasks into the board. Trigger phrases: "monitor kanban", "auto run tasks", "watch board", "auto dispatch tasks", "kanban worker", "kanban auto", "/aio-kanban-monitor".
- ▌ Aio Research Kit · aioceanRun a structured 10-phase research workflow to investigate a topic, conduct a literature review, or deep-research a technical or market question via research-cli (auto-installs if missing). Use for any investigation that needs phase-gated discipline: question formulation → data collection → analysis → documentation.
- ▌ Aio Catch Me Up · aioceanTurn Claude into a wise, effective teacher whose only goal is to make sure YOU deeply understand the work an AI agent just did — the problem it solved, why that problem existed, the solution and its design decisions, the edge cases it handled, and the broader impact. Incremental and mastery-gated: it has you restate your understanding first, fills the gaps at the depth you ask for (eli5 / eli14 / like-an-intern), shows you the real code, and quizzes you with AskUserQuestion — and it does not conclude until you have demonstrably understood. Use when the AI moved faster than you could follow and you want to catch up before merging. Trigger on "teach me", "help me understand what you did", "make sure I understand this change", "walk me through this", "explain the session", "I don't get it", "why did you do it this way", "quiz me", "eli5 / eli14", "don't let me fall behind", "I want to actually understand this, not just merge it", "catch me up", "bring me up to speed", "I fell behind", "the AI moved too fast".
- ▌ Aio Feedback · aiocean bundleSubmit bug reports, feature requests, and plugin requests to aiocean/claude-plugins via GitHub Issues.
- ▌ Aio Skillify · aioceanCapture this session's repeatable process into a reusable SKILL.md file via guided interview.
- ▌ Aio Code Review · aiocean bundleRuns an adaptive, project-aware code-review workflow (profile the project, detect its lint tools + conventions, run mechanical + semantic review, consolidate into an LGTM verdict) and carries the Google eng-practices playbook it applies — reviewer (what to look for, when to approve, severity-labeled comments, handling pushback) and PR/CL author (CL descriptions, splitting changelists, responding to comments). Use when reviewing or authoring a PR/MR/CL/diff, running a code review, deciding LGTM or LGTM threshold, authoring a merge request, assessing code health, handling a hotfix review, or replying to review feedback.
- ▌ Aio Remove Background · aiocean bundleRemove image backgrounds via RMBG-2.0 alpha matting with despill + 1px erode — produces clean PNG RGBA cutout that handles hair, smoke, glow, soft edges. Use when the user wants to remove background, xoá nền, make transparent, cutout, chroma key, or post-process a text-to-image render (gpt-image, Imagen, FLUX, SDXL, Grok, Midjourney) — especially with flat magenta (#FF00FF) key.
- ▌ Aio Visual Diff · aioceanVerify AI-generated frontend UI against design via measurement-driven diff — extracts `getComputedStyle` + `getBoundingClientRect` through chrome-devtools MCP, diffs against Figma data or baseline JSON, reports numerical deltas. Catches library-specific token traps where class names lie about runtime values (Radix, Material UI, Tailwind, shadcn). Use when checking pixel-perfect implementation, validating design fidelity, catching layout regressions, or when the agent claims "it looks right" but you want numerical proof instead of eyeballed screenshots.
- ▌ Aio Patch Run · aiocean bundleExec the compiled patched Claude binary at dist/<arch>/claude. Pass-through args + env. Requires aio-patch-compile to have been run first (sentinel: dist/<host-arch>/claude exists).
- ▌ Aio HTML Deck · aiocean bundleA paced HTML deck — one self-contained file a presenter advances scene by scene while speaking. Reach for it when a human sits through the material at the author's tempo and leaves with one decision: executive briefing, proposal, demo walkthrough, narrative status review, conference talk. A human who reads and audits at their own pace wants aio-html-report; a human holding options side by side wants aio-html-explorer.
- ▌ Aio Architect Advisor · aioceanArchitecture decision advisor — guides pattern selection, application, synthesis, and stress-testing for system design, scaling, resilience, and migration decisions.
- ▌ Aio Epub Setup · aioceanSetup guide for EPUB translation service — register account, purchase license, and configure API key.
- ▌ Aio Workflow Creator · aiocean bundleAuthor Workflow-tool scripts that spend effort like it's free and waste none of it. A maximal-effort playbook for multi-agent orchestration: choose an effort tier, then scale fan-out width, verification votes, and discovery rounds. Compose named amplifiers — multi-modal sweep, adversarial and perspective-diverse verify, judge panels, loop-until-dry discovery, completeness critic, synthesis — into a canonical harness. Use when authoring or editing a Workflow script, or when the user signals thoroughness: "exhaustive", "comprehensive", "thorough audit", "maximize", "spare no cost", "result-oriented orchestration".
- ▌ Aio Patch Setup · aiocean bundleScaffold a new Claude-binary-patching project at CWD (or [target_dir]). Copies generic pipeline tools (extract/build/run, Python pipeline scripts, cli-nav AST navigator) + generic docs/guides into the target. Patches.json starts EMPTY — user fills it in; a reference example from the dirty-claude project is shipped beside it.
- ▌ Aio Neobrutalism · aiocean bundleApply neobrutalism design to a web project — detects tech stack, generates CSS tokens, and transforms existing UI components.
- ▌ Aio Epub Export · aioceanPack a translated EPUB into a downloadable file — bilingual (original + translation side-by-side) or translation-only output. Use when the user wants to export/xuất sách, đóng gói sách, generate an EPUB file, download a finished book, or send a translation to Kindle.
- ▌ Aio Epub Manage · aioceanBrowse books, check translation progress, manage guidelines, view TOC, fork books, publish to community, reset chapters, and view usage stats.
- ▌ Aio Epub Review · aioceanDeep literary review of translated EPUB chapters — evaluate translation quality, fix consistency issues, and check cross-chapter coherence.
- ▌ Aio Epub Upload · aioceanUpload an EPUB file and prepare it for chapter translation — extracts TOC, counts words, queues for analysis. Use when the user wants to add a new book, start translating an EPUB, tải sách lên, import a `.epub` file, or onboard a new title into the translation workspace.
- ▌ Aio HTML Editor · aiocean bundleOne self-contained HTML instrument for changing a specific set of real values and handing the change back — flags, config, prompts, priorities, annotations. Reach for it when the work is a set of concrete edits to structured data and describing those edits in chat costs more than making them. When the human reads and audits instead, that is aio-html-report; when they hold options side by side, aio-html-explorer.
- ▌ Aio HTML Report · aiocean bundleOne self-contained HTML file carrying an evidence-led verdict — or, when nothing is being decided, an evidence-led answer — that a skeptical reader can audit offline and print. Reach for it when the deliverable is long-form, every claim needs its proof attached, and Markdown would flatten the hierarchy or leave a claim on a different screen from the evidence for it. A human who sits through the material at a presenter's tempo wants aio-html-deck; a human holding two or more live options side by side wants aio-html-explorer.
- ▌ Aio Architect Reference · aioceanLook up architecture patterns and concepts via semantic search — read the full article on demand, compare patterns side-by-side, or browse by volume.
- ▌ Aio Patch Anchor · aiocean bundleFind and navigate anchors in the extracted cli.js — wraps tools/cli-nav/{find-anchors,navigate,build-explorer}.cjs (acorn-based AST navigator). Used primarily for drift recovery when Claude version bumps shift the location of anchored patch points.
- ▌ Aio Grafana Diagram · aioceanCreate Grafana diagrams for live system visualization — analyzes codebase to auto-generate Mermaid diagrams with Prometheus metric binding. Each node is colored by health thresholds, turning a static architecture diagram into a live system diagram or service health monitor. Use when you need a dynamic Grafana dashboard with node coloring driven by real metrics. For standalone shareable diagrams use aio-mermaid instead.
- ▌ Aio Epub Analyze · aioceanPre-translation analysis for EPUB books — analyze writing style, characters, tone, and build glossary before translating.
- ▌ Aio Epub Quality · aioceanGenerate a translation quality report and surface chapters that need re-translation. Use when the user wants to check quality, kiểm tra chất lượng bản dịch, run QA, tìm bản dịch kém, find bad translations, or decide which chapters to retranslate before exporting.
- ▌ Aio Google Workspace · aioceanInteract with Google Workspace services via the gws CLI. Use when the user wants to send email, read Gmail, upload to Drive, create a Google Calendar event, read or write Google Sheets, generate a standup report, manage Google Tasks, or work with Google Docs, Slides, Chat, or Contacts.
- ▌ Aio Watermill Kit · aiocean bundleBuild event-driven Go apps with Watermill (ThreeDotsLabs) — Router, middleware chains, pub/sub Go patterns, CQRS, and broker integrations (Kafka, AMQP, NATS, Redis Streams, SQL). Use for async messaging, message queue design, message bus architecture, event sourcing, and Go event broker setup.
- ▌ Aio Patch Compile · aiocean bundleApply tools/pipeline/patches.json + bun build --compile → patched claude binary at dist/<arch>/claude. Default: current host arch only (fast inner-loop ~1.2s). Opt-in --target=all (4 platforms) or csv list (e.g. --target=darwin-arm64,linux-amd64). If cli.js for a target arch is not yet extracted, transitively calls extract first. Strict by default (fails fast on MISSING patches).
- ▌ Aio Patch Control · aiocean bundleScaffold a reference HTTP control-channel gateway (sample shell clients + bun TUI) into <project>/control/, OR print the control-channel protocol docs. Reference example based on the dirty-claude project (Phase 1 patched binary exposes HTTP+SSE server on 127.0.0.1:$DC_PORT inside the running Claude). NOT a generic abstraction — adapt to your own transport (WebSocket / ZMQ / named pipes) if needed.
- ▌ Aio Patch Extract · aiocean bundleExtract Claude Code's cli.js + native .node modules from an installed claude binary (or a binary you pass as positional arg). Output lands in dist/<arch>/. Required before aio-patch-compile. Default arch detected from host; ARCH env var overrides for cross-arch extraction.
- ▌ Aio Epub Vn Style · aiocean bundleVietnamese literary translation style guide — word choice, sentence rhythm, genre conventions, and common error patterns for natural Anh-Viet translation.
- ▌ Aio HTML Explorer · aiocean bundleOne self-contained HTML file holding genuinely different options side by side on a shared set of criteria, so the choice gets made from the page instead of from memory. Reach for it when two or more real alternatives are live and someone has to pick one and record why.
- ▌ Aio Browser Cookie · aiocean bundleExtract cookies from local browsers and export them for use in authenticated requests. Use when extracting Chrome cookies, Firefox cookies, or Safari cookies from the local browser store; reusing a browser session to replay an authenticated request; exporting a Netscape cookie jar for curl, wget, or yt-dlp cookies; making an authenticated curl request with your live browser session; or using rookiepy to read browser cookies programmatically. Also covers session replay — sending HTTP requests with the browser's own cookies injected automatically.
- ▌ Aio Epub Translate · aioceanTranslate EPUB book chapters into literary Vietnamese with cross-chapter consistency (guideline + glossary + previous-chapter summary). Use when the user says dịch sách, dịch chương, dịch tiếp, continue translating, translate epub, or sends a book/chapter URL to translate.
- ▌ Aio Gherkin Refine · aiocean bundleComprehensive BDD field guide for writing and reviewing Gherkin scenarios with expert quality. Use proactively when a request is ambiguous, spans multiple conditions, or edge cases need clarification.
- ▌ Aio Golang Mastery · aiocean bundleWrite, review, and lint Go code. Lint mode runs go build, go vet, golangci-lint, govulncheck, nilaway, deadcode, and race detection (race detector), then applies idiomatic fixes. Reference mode covers concurrency, error handling, generics, testing, gRPC, and production hardening. Use when asked to lint golang, run a go lint pipeline, review go code quality, do go static analysis, write idiomatic go, or apply go best practices.
- ▌ Aio Message Bridge · aiocean bundleGive Claude Code an event loop. A local HTTP + WebSocket relay plus the Monitor tool let anything OUTSIDE Claude — a CLI in another terminal, a mobile app, a webhook, another running program, a web page — push events to Claude mid-task and receive pushes back, in real time. Inbound: the external client POSTs an event, the relay prints a MSG:: line to stdout, the Monitor tool surfaces it as a notification. Outbound: Claude POSTs a push, the relay broadcasts it over WebSocket to every connected client. The protocol is generic and language-agnostic; a ready-to-run reference relay is included. Use when an external process or device needs a live two-way channel to Claude, when you need a webhook or event source to wake Claude, or when you want to "give Claude an event loop". "external to Claude bridge", "Monitor + WebSocket relay", "wake Claude from outside", "kết nối bên ngoài với Claude", "cầu nối tương tác với Claude".
- ▌ Aio Dashboard Design · aiocean bundleDesign and review SaaS analytics dashboards — chart selection, anti-patterns, WCAG 2.2 a11y, color palettes, and storytelling.
- ▌ Aio HTML Interactive · aiocean bundleBridge Claude to a browser UI in real time via a frozen Bun + Vue3 + Tailwind scaffold — browser events become Monitor-tool notifications, AI pushes become WebSocket broadcasts. Use when Claude needs to drive an interactive UI mid-task: form capture, multi-step decision flow, live preview, approval queue, or side-by-side review. See body for the "why" (Claude has no event loop) and architecture details.
- ▌ Aio Starrocks Query Tuning · aioceanStarRocks query performance tuning — EXPLAIN plans, Query Profile analysis, operator metrics, tuning recipes, schema optimization, query hints, and text-based profile analysis. Use when diagnosing slow queries, reading EXPLAIN or ANALYZE PROFILE output, finding operator bottlenecks via pipeline metrics, enabling profiling with enable_profile or big_query_profile_threshold, understanding runtime filter effectiveness, investigating spill to disk, or forcing join strategies with SHUFFLE or BROADCAST hints.
- ▌ Aio IOS Device Debug · aiocean bundleDebug iOS apps on physical devices from the terminal — deploy to iPhone or iPad with xcodebuild, capture syslog via idevicesyslog, pull crash reports from the device, analyze .ips crash files, and take device screenshots. Covers the full loop: build, install, launch, capture syslog, pull crash report, analyze .ips crash file, and grab a device screenshot. Uses libimobiledevice (idevicesyslog, idevicecrashreport) and pymobiledevice3 for iOS 17+ compatibility. Use when debugging an iOS app on a physical device, deploying to iPhone without the Xcode GUI, troubleshooting a crash from a .ips file, or capturing a device screenshot over USB.
- ▌ Aio Starrocks Best Practices · aioceanStarRocks table design best practices — partitioning strategy, sort key selection, bucketing decisions, Primary Key table tuning, authentication/authorization, and resource group configuration. Use when designing a StarRocks table, reviewing DDL, choosing partition granularity, sizing tablets (tablet sizing), setting up colocated joins, configuring LDAP or OIDC authentication, tuning Primary Key compaction, adjusting FE memory limits for large partition counts, or isolating workloads with resource group isolation.
- ▌ Aio Bun Fullstack Setup · aioceanBootstrap or scaffold a Bun fullstack project in one shot — single-port server, Vite dev proxy, monorepo layout, and Docker config. Use when starting a new fullstack project with Bun, setting up a bun server with vite proxy, creating a monorepo bun layout, configuring docker bun deployment, or bootstrapping a bun project from scratch. Skips files that already exist so it never overwrites your work.
- ▌ Aio Monitoring Observability · aiocean bundleDesign metrics, alerts, dashboards, and SLOs for any service using monitoring and observability best practices. Use when setting up observability from scratch, designing alert rules, building Grafana dashboards, integrating OpenTelemetry instrumentation, configuring Prometheus, implementing SLI/SLO tracking and error budgets, aggregating logs with ELK or Loki, debugging with distributed tracing, applying the RED method or USE method or Four Golden Signals, migrating from Datadog to an open-source stack, or comparing monitoring tools like Datadog, Grafana Cloud, Jaeger, and Tempo.