Découvrez les skills Outils, comparez leurs dépôts et consultez leurs instructions.
MLOps best practices for model versioning, experiment tracking, deployment, monitoring, and retraining workflows. Covers reproducibility, CI/CD for ML, model registry, and production ML system design.
Reusable React/JavaScript patterns for Somali dialect classifier dashboard. Covers Chart.js integration, data card components, filter patterns, responsive layouts, and dashboard-specific UI patterns. Auto-invok...
Voice, tone, and content guidelines for data/ML dashboards. Covers microcopy, error messages, success states, and data presentation language. Auto-invokes on copy, messaging, content, labels, error messages key...
Coordination protocol for main Claude Code agent. Explicit user invocation required ("mobilize agents", "coordinate", "check registry"). Provides agent orchestration, registry management, and handoff protocols....
Data quality validation rules, quality metrics, and acceptance criteria for Somali dialect classifier datasets. Covers duplicate detection, language filtering, quality scoring, and validation protocols. Auto-in...
Query and analyze Claude Code history joined with Git data using SQL. Use when user asks about their Claude conversations, productivity patterns, commit history correlation, session analytics, or wants to explo...
Interact with Messages app - read conversations, send messages, and check for new messages using AppleScript and SQLite database access
Automates the creation of documentation for solved problems.
Conversion Copywriter Specialist. Use this for landing page copy, email sequences, and optimizing conversion rates.
Invoke this skill whenever you are working on something related to YouTube. Assists in generating essential elements that drive engagement and discovery.
Guide for assistant-cloud persistence and authorization. Use when setting up thread persistence, file uploads, or authentication.
Apply AI-generated code edits from a response file to the local codebase.
Automated changelog generation with semantic versioning. Triggers on: generating changelogs, updating versions, releasing software, version bumps, changelog updates, semantic versioning, and when users ask to "...
Control macOS settings and apps (dark mode, volume, apps, Finder, Focus).
通过 XGo (xgo.ing) 开放接口整理和分类 Twitter/X 关注用户。适用场景: (1) 查看未分类的关注用户, (2) 自动分析用户并推荐列表归属, (3) 批量将用户分类到列表, (4) 整理关注列表，减少未分类用户。触发短语: '整理关注', '...
Adds a new Jinja/Kida filter to Bengal templates. Use when creating custom filters for formatting, filtering, or transforming template data.
Build Chrome Extensions with Manifest V3, background service workers, content scripts, and message passing. Use when developing TikTok Uploader extension or any browser extensions.
通过 Chrome CDP 在 Twitter/X 上执行操作。适用场景: (1) 发推文/发帖, (2) 回复推文, (3) 引用推文, (4) 转推/转发, (5) 点赞推文, (6) 取消点赞, (7) 取消转推。触发短语: '发推', 'post tweet', '发帖到X', '回复推文', 'r...
Token-efficient codebase exploration using RepoPrompt CLI. Use when user says "use rp to..." or "use repoprompt to..." followed by explore, find, understand, search, or similar actions.
Execute a Flow epic or task systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan or working through a spec. Triggers on /flow-next:work with Flow IDs (...
Carmack-level plan review via RepoPrompt or OpenCode. Use when reviewing Flow epic specs or design docs. Triggers on /flow-next:plan-review.
Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
Create structured build plans from feature requests or Flow IDs. Use when planning features or designing implementation. Triggers on /flow-next:plan with text descriptions or Flow IDs (fn-1, fn-1.2).
John Carmack-level implementation review via RepoPrompt or OpenCode. Use when reviewing code changes, PRs, or implementations. Triggers on /flow-next:impl-review.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.