Shape agent capabilities into your workflow.

OKR Master helps teams turn raw business context or weak drafts into measurable, outcome-focused Objectives and Key Results. It can validate strategic soundness, separate Objectives, Key Results, and Initiatives, and rewrite task-based statements. The skill is aimed at organizations that want a consistent OKR structure and quality bar across departments.

Apple Photos Cleaner queries the macOS Photos SQLite database to reveal duplicates, screenshots, low-quality images, storage trends, people, locations, and timeline recaps. Its analysis scripts are read-only and can return JSON or human-readable output. Actual cleanup is handled separately through an AppleScript executor that requires explicit confirmation before moving items to the trash.

Diffscribe reads the current branch name, commits, changed files, and git diff to draft a complete pull-request or merge-request description. It can populate summaries, motivation, testing notes, checklists, issue links, and breaking-change sections in an existing template. Because it works from local Git state, the skill can support GitHub, GitLab, Bitbucket, and Azure DevOps workflows.

Python Environment Doctor uses conda-lens to investigate missing dependencies, version conflicts, duplicate pip and conda packages, Python or platform incompatibilities, CUDA mismatches, and ABI problems. The Claude Code workflow combines diagnostic output with project files and logs, explains likely causes, proposes fixes with trade-offs, and can apply and verify a change after permission. It requires conda-lens, which the skill can install if missing.

VergingAI Agent Skills is a modular collection for media and AI-service tasks, including face swap, background removal, video enhancement, image generation, vision, chat, speech-to-text, and text-to-speech. Skills can be installed together or individually. Some tools accept local files or remote URLs, download inputs automatically, and show progress while using verging.ai services from an AI coding agent.

Anytime Search Skill drives Chromium with Playwright to query more than 18 search engines, including Google, Bing, Baidu, and DuckDuckGo, or fetch a URL and return its HTML body with scripts and styles removed. It supports text and JSON output, persistent cookies and storage, and headed or headless runs. The tool detects Google CAPTCHA pages and exits with a warning, and it requires Python 3.8+, Playwright, and Chromium.

Use this Claude Code skill to capture baseline screenshots, rerun pages after code changes, and inspect an HTML diff report when the UI shifts unexpectedly. It supports multiple viewports, masking for dynamic content, and configurable tolerances. For consistent results between macOS and Linux CI, the project recommends generating baselines in Docker.

This Claude skill reads your triage rules, scans Gmail through a read-only MCP connector, and classifies each message into built-in or custom labels. It sends an action plan to a Google Apps Script deployment, verifies the changes, and logs decisions for review. You can choose a review-first workflow or automatic labeling, but setup requires the Apps Script endpoint, a shared secret, and local rule and configuration files.

Use this skill for workflows such as interviews, project reviews, or multi-day programs that require several linked events. A Markdown instruction file defines the required details, scheduling constraints, approval behavior, and follow-up actions for each event type. Claude checks availability, proposes a schedule, creates and verifies events through Google Apps Script, and can then send confirmations or other configured notifications. Gmail and Google Calendar connectors are required.

This Claude skill searches Slack for direct messages, group DMs, and channel mentions received since the last successful run. It removes your own messages, deduplicates results, groups them by conversation, and sends one email per source with timestamps, message text, and Slack links. State advances only after successful delivery, so failed messages can be retried. It requires a read-only Slack MCP connector, Google Apps Script, a local config file, and Python 3.

This Claude Code skill inspects routes, request parameters, response types, middleware, and validation schemas to produce an `openapi.yaml` file without requiring decorators or annotations. It supports common JavaScript, Python, Go, Java, and Rust web frameworks, maps native types into OpenAPI schemas, and detects authentication patterns such as bearer tokens, API keys, and cookies. The generated specification can be validated with Swagger CLI or Redocly.

This Claude Code skill reads a configurable Git range and converts commits into readable release notes instead of copying log messages verbatim. It categorizes Conventional Commits, highlights breaking changes, detects versions from common project files or tags, and writes entries in Keep a Changelog format. It can create or append to `CHANGELOG.md`, generate commit links when a repository URL is known, and produce separate changelogs for monorepo packages.

Env Doctor scans JavaScript, TypeScript, Python, Go, Dockerfiles, and Compose files for environment-variable references. It compares code with `.env` and `.env.example` to identify missing, undocumented, or unused values, then checks common secret patterns and validates formats such as URLs, ports, email addresses, booleans, and timeouts. When no example file exists, it can generate a categorized `.env.example` template for the project.

This Claude Code skill inspects the language, framework, package manager, and monorepo layout before generating CI steps for linting, type checks, tests, builds, and optional deployment. GitHub Actions is the primary fully supported platform, with template support for GitLab CI and CircleCI. It can also add Dependabot configuration, minimal permissions, pinned action versions, OIDC authentication, path filtering, and stack-specific caches, then validate the workflow with `actionlint`.

This Claude Code skill analyzes the project's language, framework, package manager, and service dependencies, then creates a multi-stage Dockerfile, production and development Compose files, `.dockerignore`, and an environment template. It separates hot-reload development needs from a smaller production image and applies practices such as non-root users, fixed image tags, health checks, and excluding secrets from the build context. The result can be checked with `docker compose config`.

This Claude Code skill can turn a plain-language matching requirement into a regular expression with an explanation and test cases. It can also break down an existing pattern or run it against supplied strings, showing match positions and capture groups. Output adapts to JavaScript, Python, Go, or Java syntax, includes ready-to-use match or replace snippets, and warns about issues such as catastrophic backtracking and greedy matching.

Describe the entities, relationships, and ownership rules in natural language, and this Claude Code skill generates SQL migrations with Row Level Security, Supabase-style TypeScript types, Zod schemas, and Next.js App Router endpoints. It can also scaffold authentication choices, React forms, and many-to-many junction tables. Built-in checks call out common mistakes such as missing delete policies, unprotected junction tables, exposing the service-role key, or using imprecise numeric types for currency.

This Claude Code skill scans migration files, raw SQL, or ORM schemas to extract tables, columns, constraints, indexes, and relationships. It supports Prisma, Drizzle, TypeORM, Supabase, Knex, Django, Alembic, Go migrate, and SQL DDL. The generated `docs/database.md` includes a GitHub-renderable Mermaid ERD, per-table field documentation, relationship summaries, and index listings. Incremental runs update changed tables while preserving descriptions added by users.