发现 Skills

Write effective discussion sections that interpret results and impact

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

Expert at handling file uploads and cloud storage. Covers S3, Cloudflare R2, presigned URLs, multipart uploads, and image optimization. Knows how to handle large files without blocking. Use when: file upload, S3, R2, presigned URL, multipart.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging and splitting documents, and handling forms. Use when Claude needs to fill PDF forms or programmatically process, generate, or analyze PDF documents at scale.

Use this skill when the user asks to "run pentest commands", "scan with nmap", "use Metasploit exploits", "crack passwords with hydra or john", "scan web vulnerabilities with nikto", "enumerate networks", or needs essential penetration testing command references.

Interactive debugger for Deno/TypeScript applications using the V8 Inspector Protocol. This skill should be used when investigating issues in Deno applications, including memory leaks, performance bottlenecks, race conditions, crashes, or any runtime behavior that requires step-by-step debugging, heap analysis, or CPU profiling. Provides CDP client tools, heap/CPU analyzers, and investigation tracking.

Extract study data into a structured table (`papers/extraction_table.csv`) using the protocol’s extraction schema. **Trigger**: extraction form, extraction table, data extraction, 信息提取, 提取表. **Use when**: systematic review 在 screening 后进入 extraction（C3），需要把纳入论文按字段落到 CSV 以支持后续 synthesis。 **Skip if**: 还没有 `papers/screening_log.csv` 或 protocol 未锁定。 **Network**: none. **Guardrail**: 严格按 schema 填字段；不要在此阶段写 narrative synthesis（那是 `synthesis-writer`）。

Invoke the local Claude Code CLI from Codex for delegated development tasks, second-opinion codebase analysis, implementation attempts, test fixing, PR preparation, or automation. Use when the user asks Codex to call, run, use, consult, compare with, or delegate work to Claude Code, or when a task benefits from having Claude Code inspect or modify the same repository under Codex supervision.

Use when creating Claude Code hooks - covers hook patterns, composition, testing, progressive enhancement from simple to advanced

Automated extraction and analysis of tender/bid PDF documents. Extracts key information including project name, tender number, budget, deadlines, contact info, technical requirements, commercial terms, evaluation criteria, and more. Outputs structured markdown reports. Supports both Chinese and English tender documents. Use when analyzing tender documents, RFPs, procurement notices, or bid announcements.

Execute the implementation plan autonomously with intelligent atomic commits. Agent manages work order and git history.

Extract and formalize domain terminology into a glossary. Use when: defining domain terms, building a glossary, hardening terminology, domain model, DDD, ubiquitous language, glossary.

Generate comprehensive "Shownotes" summaries from longform articles, papers, transcripts, videos, or audio content. Use when users request shownotes, episode summaries, content summaries with takeaways, or when they reference the mdynotes.com format. Creates structured summaries with metadata, hooks, takeaways, quotes, and references.

Create and manage project plans, PRDs, and phase documentation in the .trent/ folder. Use when planning projects, creating requirements documents, defining phases, validating scope, or gathering requirements. Triggers on requests mentioning plan, PRD, requirements, phases, scope, or project planning.

Privacy-focused workflow to merge PDFs, combine PDF files, and create an application PDF for German-speaking users. Use this skill for requests about PDF order, merging, application materials, GDPR requirements, and secure in‑browser tools.

Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.

Guide for working with Next.js App Router (Next.js 13+). Use when migrating from Pages Router to App Router, creating layouts, implementing routing, handling metadata, or building Next.js 13+ applications. Activates for App Router migration, layout creation, routing patterns, or Next.js 13+ development tasks.

IBM i File Spec — generates structured File Specifications for Physical Files (PF), Logical Files (LF), Printer Files (PRTF), and Display Files (DSPF) using DDS (Data Description Specifications). V2.1.2 — DDS-first, dual-layer output (human-readable Markdown + machine-readable JSON), cross-spec interoperability via stable IDs, execution-mode routing by file type (PF/LF, DSPF, PRTF), skeleton output gate for incomplete inputs, delta-first change specs, tiered spec levels (Lite/Standard/Full), machine-checkable validation rules, upstream escalation for design gaps, scoped Business Rules boundary, artifact-first gating, no silent defaults, and fail-fast Skeleton classification. Use this skill whenever a user asks to define, design, or spec out an IBM i file object — PF, LF, PRTF, or DSPF. This is a DDS file specification skill, not a DDS source generator, not a program spec, not a database design skill.

Get an informative summary of a file, especially for code files. Use when you need to understand the purpose and functionality of a specific file.

Update documents under the `.aidocs` directory to reflect recent code changes. Use when new non-documentation commits occurred since the last ai documentation commit.

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Use when the user provides a procurement, solicitation, inquiry, negotiation, or bidding document and wants response files, quote sections, or technical-business sections drafted from the document's own template, qualification rules, pricing rules, and technical-commercial requirements.