ocr
PDF/이미지를 Claude vision으로 OCR하여 마크다운 변환. MUST use this skill when user: (1) asks to convert PDF/image to markdown, (2) asks to OCR any file, (3) sends PDF/image file and asks to extract/read/변환/...
发现 测试与安全 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
PDF/이미지를 Claude vision으로 OCR하여 마크다운 변환. MUST use this skill when user: (1) asks to convert PDF/image to markdown, (2) asks to OCR any file, (3) sends PDF/image file and asks to extract/read/변환/...
Stage meaningful diffs and create commits with WHY-focused messages. Use when agent needs to commit code changes.
Fast compliance fixes for design tokens, imports, and common violations
Guide API routes with Validate→Queue→Respond pattern and Inngest integration
CodeQL suppressions, security vulnerability troubleshooting, and security best practices
Testing patterns, 99% pass rate target, strategic skips, and E2E workflows
Enforce DCYFR design token patterns and fix hardcoded values
Pre-completion validation checklists and approval gates
Guide DCYFR component structure with PageLayout, barrel exports, and metadata
Summit/IntelGraph context-engineering skill pack. Routes to the vendored Agent Skills for Context Engineering library via progressive disclosure, and applies repo-specific guardrails (atomic PRs, evidence, gove...
Generate a GitHub PR URL with pre-filled title and body from story metadata and changed files. Run after code-review passes.
Use when creating new stories, writing requirements, or drafting feature specifications. Triggers on requests to create stories, write specs, or plan new features.
Use when implementing features, fixing bugs, writing new code, or making changes to Python files. Manages branch creation, TDD workflow, quality gates, and commit/push.
Use when reviewing code changes, checking staged files, or validating work against acceptance criteria. Triggers on requests to review changes, check work, or validate implementation.
Use when reviewing, validating, or checking story documents. Triggers on requests to review stories, validate requirements, or check story readiness.
Take UI screenshots using Playwright and attach them as PR comments. Use this skill to capture visual state of UI components for code review, visual regression testing, or documentation.
Run smoke tests to verify the Everruns system works correctly.
Set up full production-like backend (PostgreSQL + API + Worker) without Docker. Use for testing durable workflows, database persistence, or when DEV_MODE is insufficient.
Use when adding logging, error monitoring, metrics, Sentry, debugging production issues, or improving observability
Use when writing user-facing copy, error messages, UI text, empty states, onboarding, or reviewing voice/tone
Use when writing tests, verifying functionality, QA, test scenarios, user testing, or browser automation tests
Debug and test MCP servers directly from Claude Code - call tools, list capabilities, diagnose issues without going through the full LLM stack
Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering, or LLM-to-LLM content
codex review CLIを使用したコードレビュー。セルフレビュー、PR作成前チェック、コミット確認に使用。「レビューして」「変更を確認して」で発動
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。