发现 Skills

Analytical framework for calculating Total, Serviceable, and Obtainable market sizes.

| name | description | triggers | |------|-------------|---------| | dropshipping | One-click China dropshipping: procurement, QC, shipping, tracking. Triggers on: "dropship", "daigou", "ship to", "fin..."

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, and Gemini backends with file references (@syntax) and structured output.

This skill should be used when the user asks to 'pentest SSH services', 'enumerate SSH configurations', 'brute force SSH credentials', 'exploit SSH vulnerabilities', 'perform SSH tunneling', or 'audit SSH security'. It provides comprehensive SSH penetration testing methodologies and techniques.

Use when searching for ComfyUI nodes, finding nodes by keyword/author/pack/category, discovering what nodes exist for a task, or browsing the node registry.

Search Peter's ideation history across all conversation exports — Claude Code sessions, ChatGPT, Claude.ai, Gemini, and PKB. Find real moments, decisions, what broke, and how Peter actually talks. Atomic skill called by /copy-edit, /audit, and /grip-test.

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Expert guidance for Cerebras Inference, the ultra-fast LLM inference service powered by the world's largest chip (Wafer-Scale Engine). Helps developers integrate Cerebras' API for applications requiring the fastest possible token generation — real-time chat, code completion, and interactive AI experiences.

Expert guidance for PlanetScale, the serverless MySQL platform built on Vitess (the database clustering system powering YouTube). Helps developers set up databases with Git-like branching for schema changes, non-blocking schema migrations, and connection pooling for serverless environments.

Plan and prioritize content that drives organic traffic and conversions. Use when the user mentions "content strategy," "content plan," "what should I write about," "blog strategy," "content calendar," "keyword research," "content pillars," "topic clusters," or "content ideas." For writing the actual copy, see copywriting. For social media content, see social-content.

Plans, implements, reviews, and ships a fix for a GitHub issue. Handles fork workflows with upstream detection. Use when fixing a GitHub issue, resolving a bug report, implementing a feature request from an issue, working on issue numbers, closing an issue, or addressing a ticket.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable — requires technical rigor and verification, not performative agreement or blind implementation.

Generate App Store and Play Store screenshots with device frames. Use when: preparing for app store submission, updating marketing assets, localizing screenshots, or automating screenshot generation in CI. Uses fastlane (free) not SaaS. Keywords: App Store, Play Store, screenshot, device frame, fastlane, snapshot, frameit, localization.

Analyze user feedback data to identify segments with sentiment scores, JTBD, and product satisfaction insights. Use when analyzing user feedback at scale, running sentiment analysis on reviews or surveys, or identifying satisfaction patterns.

Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline, or similar.

Appraise gemstone value using the four Cs (color, clarity, cut, carat), origin assessment, treatment detection, and market factor analysis. Advisory educational guidance only — not a certified appraisal. Use when understanding factors that determine a gemstone's value, pre-screening stones before a professional appraisal, evaluating whether a seller's asking price is reasonable, learning gemstone grading methodology, or understanding how treatment status affects value.

Deploy and configure an API gateway (Kong or Traefik) to handle API traffic management, authentication, rate limiting, request/response transformation, and routing. Covers plugin configuration, upstream services, consumer management, and integration with existing infrastructure. Use when multiple backend services need a unified API endpoint, when centralized authentication or rate limiting is required, when implementing API versioning, or when needing detailed analytics and load balancing for microservices.

Solve trigonometric equations and triangle problems systematically using identities, law of sines/cosines, inverse functions, and unit circle analysis. Covers equation solving, triangle resolution, identity verification, and applied trigonometric modeling. Use when solving trigonometric equations for unknown angles, resolving triangles from partial information (SSS, SAS, ASA), verifying identities, or applying trigonometry to real-world problems in surveying, physics, or engineering.

Update the flaky test tracker. Use when you encounter test failures unrelated to your current work, after committing a fix for a known flaky test, or to check flaky test status.

Advanced Prisma ORM patterns for schema design, migrations, query optimization, and relations. Trigger on complex schema changes (>10 models), migration strategies, query performance issues, relation patterns (many-to-many, polymorphic), multi-tenant data isolation, or Prisma-specific debugging.

Verifies that code implements exactly what documentation specifies for blockchain audits. Use when comparing code against whitepapers, identifying gaps between specifications and implementation, or performing compliance checks on protocol implementations.

Creates production-ready pull requests with automatically updated AGENTS.md and project docs. Use when the user asks to create a PR, make a PR, is ready to merge, has finished a feature and wants a PR, or says they're done for the day with changes to commit.

Figure out how networked events that connect clients and servers are being used in the project. You can't answer questions about them without this skill.