← all publishers

Adonis0123

@adonis0123 source repo

Report this profile Claim this profile

• 28 skills
• 0 followers
• 1 week ago last updated

1. ▌
   CSS Tailwind Styling · adonis0123 bundle

   Expert guidance for writing clean, performant CSS and Tailwind CSS. Use when creating styles, designing components, optimizing performance, or establishing styling conventions. Covers modern CSS features, Tailwind utility patterns, responsive design, accessibility, and team collaboration standards.
   2 installs
2. ▌
   Lingui Best Practices · adonis0123 bundle

   Implement or review Lingui message macros, catalog configuration, locale loading, and React or JavaScript integration. Use for Lingui-specific code and runtime issues, not plain text translation or another i18n library. For command-only catalog maintenance, use the project workflow.
   2 installs
3. ▌
   Decision First Technical Writing · adonis0123 bundle

   Create, rewrite, or review internal technical design documents after decisions are settled or while proposals and open questions are explicitly labeled. Use for design docs, architecture proposals, module designs, API or schema designs, and decision records. Route unresolved named-option convergence to discuss-before-plan and ready-spec task breakdown to writing-plans. Do not use for tutorials, marketing copy, or code-only implementation plans.
   2 installs
4. ▌
   Uxc Facade · adonis0123 bundle

   This skill should be used when the user invokes /uxc-facade or asks to package, harden, or reuse an MCP, OpenAPI, GraphQL, gRPC, or JSON-RPC interface through UXC; create or maintain a stable uxc link; reuse a daemon-backed stdio child; pin UXC for automation; or design a deterministic JSON CLI facade for another skill. Apply the facade contract without replacing service-specific identity checks. Do not use for ordinary one-off API calls, and hand Chrome DevTools-specific work to chrome-dev-mcp.
   2 installs
5. ▌
   Commit Push · adonis0123 bundle

   Commit or push one focused, inspected Git change set with an emoji Conventional Commit message and verified remote delivery. Use for explicit commit-and-push requests or pushing existing local commits to non-CNB remotes; cnb.cool remotes and CNB MR delivery go to coco-commit-push-mr. Excludes PR/MR, force-push, merge, rebase, tag, release, and deploy workflows.
   2 installs
6. ▌
   Weekly Report · adonis0123 bundle

   Generate structured weekly reports from Git commit history across one or multiple repositories. Use when you need concise, project-grouped progress summaries for status reporting.
   2 installs
7. ▌
   Workflow Gate · adonis0123 bundle

   Classify which workflow or skill should run when route choice matters: unresolved creative work, named-option decisions, explicit Goal management, destructive actions, architecture work, planning, debugging or ship checks, review handoff, and full-completion pipelines. Skip trivial one-line work and clearly matching safe named-skill requests. Treat first-principles analysis as a method, not a Challenge trigger unless the user is widening the option space.
   2 installs
8. ▌
   Branch Creator · adonis0123 bundle

   Create safe Git feature or hotfix branches with concise names. Use when the user asks to create a local branch or suggest a branch name. A name-only request stays read-only; an explicit creation request authorizes creation after local checks. Ordinary feature work alone does not request a branch. Do not push, commit, rebase, or create PRs.
   2 installs
9. ▌
   Chrome Dev MCP · adonis0123 bundle

   This skill should be used when the user invokes /chrome-dev-mcp or asks for Chrome DevTools MCP, CDP, list_pages/select_page, UXC packaging for Chrome DevTools, DOM snapshots, Console, Network, Performance, Lighthouse, browser-internal debugging, connection recovery, or correct-Chrome validation across Claude Code, Codex, Grok/Grok002, Hermes, or WorkBuddy. Establish or recover the shared managed connection and prove it with a real list_pages call. Do not use it for ordinary navigation, form filling, scraping, or desktop UI unless browser-internal signals are required. It is not a page-acceptance entry point: a passing readiness or list_pages check proves the connection only, and product-page verification stays with the calling task.
   2 installs
10. ▌
    Lingui Workflow · adonis0123 bundle

    Choose and troubleshoot extract, translation-check, compile, and catalog-manifest commands in an existing Lingui project. Use for daily catalog maintenance and command semantics, not initial setup, plain text translation, or choosing an i18n library.
    2 installs
11. ▌
    Kimi Computer Use · adonis0123 bundle

    This skill should be used when the user asks to install, configure, upgrade, repair, or diagnose Kimi Computer Use (kimi-cu), especially for Cursor CLI, Grok, WorkBuddy, Claude Code, Codex, or Hermes MCP clients.
    2 installs
12. ▌
    Local Web Surface · adonis0123 bundle

    Build or extend a persistent macOS local web surface when the request includes a stable *.localhost URL, an existing loopback daemon/gateway, login startup, or a thin .app launcher that opens or wakes a persistent local HTTP surface. Once triggered, it can add file-backed CRUD or local/public content projections without changing public publishing. Covers domain ownership, exact Host routing, explicit access/threat boundaries, safe mutations, launchd lifecycle, TDD, curl checks, and proportional browser QA. Do not use for public or remote URL launchers, public hosting, production deployment, ordinary frontend/CRUD work on an existing dev server, merely opening or interacting with an existing URL, website audits, or native apps with no local HTTP surface.
    2 installs
13. ▌
    Agent Symlink Init · adonis0123 bundle

    Initialize or migrate agent-skill symlinks in any repository. Use when a project needs `.claude/skills` linked to `.agents/skills`, `AGENTS.md` linked to `CLAUDE.md`, migration away from `.ruler`-based AI rules, or removal of legacy `sync-llm-skills` copy/sync setups. Trigger on requests about Claude/Codex skill symlinks, AGENTS/CLAUDE symlinks, `.claude/skills` setup, replacing copied skill folders with symlinks, or cleaning old ruler/sync automation.
    2 installs
14. ▌
    Code Inspector Init · adonis0123 bundle

    Set up or migrate code-inspector-plugin across modern frontend frameworks. Use when you need click-to-source IDE navigation, hotkey customization, or inspector troubleshooting.
    2 installs
15. ▌
    Discuss Before Plan · adonis0123 bundle

    Resolve a bounded design choice before planning. Use when the user presents named alternatives, a proposal with an implicit status-quo alternative, or delegates a decision and asks to compare, recommend, or decide. Do not use for open-ended option generation, a fully specified implementation, or a ready spec that only needs task planning.
    2 installs
16. ▌
    Task Completion Loop · adonis0123 bundle

    Finish an existing named plan/spec or clearly bounded unfinished non-trivial coding task through the explicit task-completion-loop: work ledger, Goal, implementation proof, agentic review, architecture hardening, and a fresh Claude audit. Use only for the whole requested pipeline, not ordinary implementation, planning, or review.
    2 installs
17. ▌
    UI UX Pro Max · adonis0123 bundle

    UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
    2 installs
18. ▌
    Open Code Review Loop · adonis0123 bundle

    Run a bounded OCR-delegation review-fix-re-review loop on a Git workspace until current evidence validates NO_FINDINGS. Use only when the user wants verified findings fixed and independently re-reviewed until clean with codex, claude-code, grok-build, or cursor-cli. Do not use for one-shot open-code-review-delegate or read-only review. A full loop request starts with safe product defaults and host mutation checks instead of redundant confirmation. Fail closed on missing ocr, reviewer mutation, skipped files, malformed output, stale evidence, or exhausted rounds.
    2 installs
19. ▌
    Web Performance Audit · adonis0123 bundle

    Run a read-only, evidence-led runtime performance audit of a real web application, especially authenticated editors, dashboards, media tools, long-lived SPAs, and pages with many tabs or states. Use when the user asks to profile slowness, inspect every tab, use Chrome DevTools or Chrome Recorder, run React Scan, compare normal and throttled interactions, find memory or rendering risks, or produce a performance report and recommendations without changing code. Discover available browser capabilities, guide the user through official installation when an important capability is missing, route to validated fallbacks, isolate measurement pollution, and distinguish measured facts from screen observations, hypotheses, and unverified paths. Do not use for a Lighthouse-only SEO/accessibility audit, tool installation with no audit goal, or when the user already wants a specific optimization implemented.
    2 installs
20. ▌
    Agentic Review Handoff · adonis0123 bundle

    Validate pasted review findings before fixes; run same-session automatic Git review-fix-re-review with a headless Reviewer and no redundant confirmation; start fresh-eyes Git diff Review Intake; resume review-loop sessions or packets; get a DecisionConsult from another AI; or run first-principles/DDD/high-cohesion review. Requires Git.
    4 installs
21. ▌
    Review Prompt Composer · adonis0123 bundle

    Compose one repository-local, copy-ready Markdown prompt for another team or AI agent to review Git changes in the same working tree. Use for prompt-only requests covering committed ranges, staged, unstaged tracked, untracked, or all uncommitted changes when the reviewer can read the same repository and index. Persist under $repo_root/.review-handoff/prompts/ with branch-aware naming, 24-hour expiration, strict scope evidence, and a Review-Prompt-ID. Do not execute the review, run tests, modify reviewed code, commit, stage, stash, push, send the prompt, duplicate code, or use when the receiver lacks working-tree access. Use agentic-review-handoff to execute reviews, validate returned feedback, or run review-fix-re-review loops.
    2 installs
22. ▌
    Frontend Design · adonis0123 bundle

    Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
    2 installs
23. ▌
    Code Plugin Architecture · adonis0123 bundle

    Design, review, refactor, or explain recurring extension mechanisms when adding or removing one variant requires scattered coordinated edits. Use for plugin architecture, registries, extension points, and cross-stack contract/host mappings. Assess whether a typed map, existing framework mechanism, or lifecycle-owning core is justified. Skip one plugin's internal styling or bugs, user signup, DI containers, and package registries.
    2 installs
24. ▌
    Repo Skill Creator · adonis0123 bundle

    Create and maintain repository skills for adonis-skills. Use when users ask to scaffold a new skill under skills/, generate agents/openai.yaml, run skill validation, refresh web index data, or standardize the skill authoring workflow.
    2 installs
25. ▌
    Architecture Hardening Loop · adonis0123 bundle

    Run a bounded scan-triage-fix-Grok-review-rescan loop on an explicit or uniquely resolvable user-supplied code scope until no evidence-backed architecture fixes remain. Use for implementation-inclusive architecture cleanup, DDD or high-cohesion hardening, and autonomous architecture improvement.
    2 installs
26. ▌
    Commit · adonis0123 bundle

    Generate read-only emoji-prefixed Conventional Commit messages or create focused local commits from staged changes or a clear user-authorized unstaged scope.
    2 installs
27. ▌
    Figma MCP · adonis0123 bundle

    Use this skill whenever the user invokes /figma-mcp or asks to install, authenticate, switch accounts, recover, or verify the official Figma MCP server across Codex, Claude Code, or Cursor. Keep registration account-neutral and each supported host's OAuth flow authoritative. Use whoami for readiness, named-account, recovery, write, and multi-host checks; for a current-account single-host read-only task, let the first requested official read prove tool and auth readiness without a redundant identity call. Never copy OAuth tokens between hosts.
    2 installs
28. ▌
    Goal Gate · adonis0123 bundle

    Gate whether a coding-agent task benefits from a durable, verifiable contract, then draft, validate, start, continue, or close it for Codex, Grok, Claude Code, Cursor CLI, or an unknown host. Use for explicit goal or /goal requests and autonomous multi-checkpoint coding work with one checkable end state. Native Goal creation or mutation requires an explicit user or system request. Do not use for quick one-shot work, unrelated backlogs, OKRs, reminders, or token-budget-only changes.
    2 installs