菜单
这个仓库中的 skills
SkillsMP 已收集 kitfunso/omniskill 中的 87 个 Skill。打开任一 Skill 可查看来源和详情。
kitfunso/omniskill已展示 40 / 87 个已收集 Skill。
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element…
原文语言：英语
Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version".
原文语言：英语
Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging…
原文语言：英语
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root…
原文语言：英语
Transform content into LinkedIn thought leadership posts using storytelling, personal anecdotes, professional insights, and algorithm-optimized formatting. Based on 100+ high-performing LinkedIn templates. Use for LinkedIn posts, articles, or professional…
原文语言：英语
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or…
原文语言：英语
Full commodity model improvement workflow — from audit through exhaustive feature engineering, two-stage selection, Optuna optimization, multi-layer validation, data source verification, and production deployment. Use PROACTIVELY when the user asks to…
原文语言：英语
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning,…
原文语言：英语
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
原文语言：英语
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE…
原文语言：英语
Designer's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Works in plan mode. For live site visual audits, use /design-review. Use when asked to…
原文语言：英语
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture",…
原文语言：英语
Adapt content tone, length, style, and formatting for specific social media platforms (Twitter, LinkedIn, Instagram, Threads, TikTok). Automatically adjusts voice from technical/casual to professional, optimizes for character limits, and applies…
原文语言：英语
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other…
原文语言：英语
Generate the four foundation documents for a new project: PRD, Architecture, AI Rules (CLAUDE.md), and Plan. Use when starting a new project, repo, or major initiative from scratch. Triggered by 'scaffold', 'new project', 'kickoff', 'project init', or 'set up…
原文语言：英语
Ship an npm package release: bump version, update CHANGELOG/README/manifests, build, test, commit, tag, npm publish, push, and optionally install globally. Use when the user says 'publish', 'release', 'ship the package', 'bump version and push', or 'update…
原文语言：英语
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For…
原文语言：英语
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix…
原文语言：英语
Use when presenting validation results, backtest metrics, model comparisons, or pipeline status. Formats output in consistent structured templates. Trigger on validation reports, model results, pipeline summaries, or when the user asks for a status check.
原文语言：英语
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
原文语言：英语
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
原文语言：英语
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro",…
原文语言：英语
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff".…
原文语言：英语
Check and fix futures contract roll adjustments. Detects when active contracts have rolled since signal entry, adjusts signal_price by the roll spread to maintain PnL continuity, and updates Supabase + local files. Use when asked to "check rolls", "contract…
原文语言：英语
Research-before-coding workflow. Use BEFORE implementing any significant feature to check for existing libraries, MCP servers, patterns, or solutions. Prevents reinventing the wheel. Use when adding new dependencies, building integrations, or starting…
原文语言：英语
Review all changes made in the current session for mistakes, missed requirements, and regressions. Use when the user asks to review changes, check work, or verify correctness before wrapping up.
原文语言：英语
Import cookies from your real browser (Comet, Chrome, Arc, Brave, Edge) into the headless browse session. Opens an interactive picker UI where you select which cookie domains to import. Use before QA testing authenticated pages. Use when asked to "import…
原文语言：英语
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push". Proactively suggest when the user says code is…
原文语言：英语
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…
原文语言：英语
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack…
原文语言：英语
Use when the user asks to smoke test, verify, or check the frontend after a deploy or frontend change. Runs Playwright smoke tests against production or local dev server.
原文语言：英语
Applies AUTOMATION Creators brand guidelines to social media content, presentations, and marketing materials. Use when creating content for AUTOMATION Creators that requires consistent branding including colors, typography, visual style, and brand voice.…
原文语言：英语
Guide for when to use /compact strategically. Use when context is getting large, when transitioning between task phases (research→planning→implementation), or when the user asks about compaction timing. Also use when tool call count is high or context feels…
原文语言：英语
Use when executing implementation plans with independent tasks in the current session
原文语言：英语
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
原文语言：英语
Replace with description of the skill and when Claude should use it.
原文语言：英语
Use when implementing any feature or bugfix, before writing implementation code
原文语言：英语
Convert long-form content into engaging Twitter threads with hooks, numbered tweets, visual hierarchy, and strategic CTAs. Optimized for Twitter's algorithm and thread readability. Use when adapting blog posts, articles, or complex ideas for Twitter's…
原文语言：英语
Clear the freeze boundary set by /freeze, allowing edits to all directories again. Use when you want to widen edit scope without ending the session. Use when asked to "unfreeze", "unlock edits", "remove freeze", or "allow all edits".
原文语言：英语
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
原文语言：英语