Loading...
Loading...
Found 266 Skills
Audit and fix responsive/mobile issues across every page of a project, using Chrome MCP screenshots at two breakpoints (375px mobile, 1440px desktop). Design-aware: reads existing design docs to preserve aesthetic intent, not just "make it fit." Use when asked to "make it responsive", "fix mobile", "responsive audit", or after building a desktop-first UI that needs mobile adaptation.
Market prediction skill using Kronos. Use when user needs finance market time-series forecasting or news-aware finance market adjustments.
Strategic AI thinking frameworks and mental models from Satya Nadella's perspective on platform shifts, AI deployment, and building successful AI products. Use when evaluating AI strategy decisions, assessing platform opportunities, thinking through AI product positioning, considering enterprise AI deployment challenges, evaluating talent and team capabilities, or needing frameworks for justifying AI investments in terms of economic surplus. Triggers on questions about AI platform strategy, change management for AI adoption, building AI scaffolding layers, evaluating AI opportunities, or thinking through AI's societal implications.
Review code after implementation work to identify design flaws, abstraction issues, or maintenance risks that only became clear once real code was written. Use whenever the user asks whether a recent change exposed architectural problems, whether an abstraction is fighting the implementation, or whether a refactor is justified. Be conservative and avoid suggesting refactors without concrete evidence of recurring cost or complexity.
Autonomous SDLC router. Takes a job, classifies complexity, executes the appropriate lev-* workflow (from trivial fix to full epic), and returns "done" with runnable instructions. One shot to full auto: spec/bd/poc/impl. Subagent returns completion artifact. Triggers: "sidequest", "side quest", "just do it", "autonomous", "one shot"
Interact with GitLab via the glab CLI. Supports five MR workflows — Read (summarize), Review (full code/security/QA review), Fix (review + implement), CI Fix (fix pipeline failures), and Feedback (address review comments). Trigger whenever the user provides a GitLab MR URL or says anything like "อ่าน MR", "ดู MR", "check MR", "review MR", "ช่วย review MR นี้", "ตรวจ MR", "แก้ตาม MR", "fix MR", "fix CI", "fix pipeline", "แก้ pipeline", "แก้ตาม comment", "แก้ตาม feedback", "address feedback", or just pastes a GitLab MR URL. Also supports listing MRs, viewing MR status, checking CI/CD pipelines, approving MRs, and other glab operations. Trigger on "check pipeline", "list open MRs", "pipeline failed", or any GitLab-related task.
Proofread and improve English text written by the user before answering their actual question. Use this skill whenever the user's message contains English sentences or paragraphs — even mixed with Korean — and a substantive answer is expected. Trigger on any message where English prose is present: questions, requests, opinions, descriptions, or explanations written (fully or partly) in English. Do NOT skip proofreading just because the English looks mostly correct; always run the correction block first. Skip only for: single English words, proper nouns, code snippets, or messages written entirely in Korean with no English prose.
Generates detailed, architect-quality GitHub issues from short instructions. Analyzes the project's actual stack, architecture, and codebase before writing. Detects duplicate issues with intelligent multi-strategy search, validates and creates labels, enforces title conventions, controls scope, and publishes via `gh` CLI with robust error handling. Use this skill whenever the user wants to create a GitHub issue, report a bug, propose a feature, request a refactor, or file any kind of technical issue — even if they just say something brief like "we need to fix the auth flow" or "create an issue for X". Also triggers on: "open an issue", "file a bug", "I want to propose...", "add this to the backlog", "gh issue", or any request that implies creating a trackable work item on GitHub.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
Tone down overly bold or visually aggressive designs. Reduces intensity while maintaining design quality and impact.
Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.
Convert content generated by general writing Skills into formats and styles suitable for publishing on Zhihu. Zhihu favors content styles with professional depth, clear logic, and well-supported arguments.