发现 Skills

Review a Pull Request for code quality, tests, merge conflicts, and readiness to merge.

Scores any open-source software project on whether rebranding it is worth doing — and explains exactly why, with a plain-English verdict. Outputs: score, verdict (Recommended / Possible / Not Recommended / Strongly Discouraged), suggested deployment mode, what breaks, what survives. Use whenever a user wants to fork and rebrand an OSS project, evaluate white‑labelling risk, or understand what rebranding breaks. Also called by other skills (e.g. coolify-one-click-deploy) as a pre-flight check. Trigger on: "should I rebrand X", "is it worth rebranding", "what breaks if I rename", "can I white-label X", "rebrand risk", "is X safe to fork and rebrand".

Browse, reserve, complete, and submit AgentPMT bounty jobs to earn credits using wallet-signed API calls. Use when the agent needs to earn credits, find available work, complete tasks for payment, or interact with the AgentPMT jobs board. Covers the full lifecycle from listing jobs through payout.

Use AgentPMT external API to run the Global Gender Equality Data tool with wallet signatures, credits purchase, or credits earned from jobs.

Network reconnaissance and security auditing using Nmap for port scanning, service enumeration, and vulnerability detection. Use when: (1) Conducting authorized network reconnaissance and asset discovery, (2) Enumerating network services and identifying running versions, (3) Detecting security vulnerabilities through NSE scripts, (4) Mapping network topology and firewall rules, (5) Performing compliance scanning for security assessments, (6) Validating network segmentation and access controls.

Use when user asks to "create repo map", "generate repo map", "update repo map", "repo map status", or "map symbols/imports". Builds and validates an AST-based repo map using ast-grep.

React Testing Library patterns - query hierarchy, userEvent, async utilities, renderHook, custom render with providers, accessibility-first testing

Aider is an open-source AI pair programming tool that runs in your terminal, letting you collaborate with LLMs to edit code across your entire codebase. With 42k+ GitHub stars and 15 billion tokens...

audioFlux is a deep learning tool library for audio and music analysis and feature extraction, supporting dozens of time-frequency transforms and hundreds of feature combinations for classification, separation, MIR, and ASR tasks.

Coolify is an open-source, self-hostable Platform-as-a-Service alternative to Heroku, Vercel, and Netlify. It enables developers to deploy static sites, full-stack applications, databases, and 280+ one-click services on their own servers with just an SSH connection.

Queries Datadog APM trace data via the Datadog Tracing API v2 to identify latency bottlenecks and error hotspots. Generates flame graph summaries and service dependency impact reports.

Docling is an open-source document processing toolkit for turning PDFs and other files into structured outputs for AI systems. It handles advanced PDF understanding, OCR, multiple export formats, and integrations with agent and retrieval frameworks.

Monitors container runtime events using Falco sysdig libraries and sends alerts on suspicious syscall patterns. Integrates with Kubernetes audit logs and Prometheus AlertManager for real-time threat detection.

Pulls search analytics from Google Search Console’s /searchanalytics/query API to identify declining pages and keyword cannibalization. Calculates CTR optimization opportunities by comparing actual vs expected click-through rates.

Diagnoses restart storms with the Kubernetes Events API, Pod status conditions, and the Metrics API to explain why workloads are stuck in CrashLoopBackOff. Great for agents that need to summarize cluster evidence before an operator starts digging through kubectl output by hand.

LangExtract by Google is a Python library for extracting structured information from unstructured text using LLMs with precise source grounding. With 35,000+ GitHub stars, it handles everything fro...

Monolith is a CLI tool and Rust library that saves complete web pages as a single HTML file by embedding CSS, images, JavaScript, and fonts as data URLs. It produces self-contained HTML5 documents that render correctly offline without external dependencies.

Queries the npm registry API and npms.io scoring endpoint to evaluate package quality, maintenance scores, and download trends. Uses npm-audit for security vulnerability detection against the GitHub Advisory Database.

Generates Playwright test suites from natural language descriptions using the Playwright Test API. Supports cross-browser testing with Chromium, Firefox, and WebKit via BrowserContext fixtures.

Automates systemd service failure diagnosis and recovery using journalctl log analysis and systemctl status inspection. Applies structured runbook logic for common failure modes like socket activation.

Validates TLS/SSL certificate chains using OpenSSL x509 verification and checks OCSP stapling status. Integrates with Let’s Encrypt ACME protocol for automated certificate renewal alerts and CT log monitoring via crt.sh API.

Typst is a modern markup-based typesetting system designed to replace LaTeX with a faster, easier-to-learn alternative. It features built-in markup, a scripting system, math typesetting, bibliography management, and incremental compilation for near-instant builds.

This skill should be used when the user asks to "perform cloud penetration testing", "assess Azure or AWS or GCP security", "enumerate cloud resources", "exploit cloud misconfigurations", "test O365 security", "extract secrets from cloud environments", or "audit cloud infrastructure". It provides comprehensive techniques for security assessment across major cloud platforms.

Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.