发现 Skills

Ecosystem branch for Linux kernel and kernel-module CVEs. Covers syscall surface, driver bugs, ring-0 heap analysis, and KASAN/kconfig build patterns. Distinct from cve-memory-linux because kernel exploitation has fundamentally different mitigations and tooling (SMEP/SMAP, KASLR, KPTI, lockdown).

Detect drift, plan updates, and apply changes to the Shokunin AI Ecosystem. Use this when user asks to update, fix, sync, or verify the ecosystem.

name: user-journey type: workflow version: '1.0' models:

When refactoring, rewriting, or migrating critical code paths, orchestrate a safe cycle: assess risks → implement → verify → document. Chains pre-mortem and prove-it with built-in implementation phase. Prevents "refactor broke production" disasters. Activates on "refactor", "rewrite", "migrate", or "clean up" for non-trivial code.

Generate images using Gemini Nano Banana Pro or Ideogram V3 APIs via curl. Use when the user says 'generate an image', 'create an image', 'image gen', 'draw me', 'make a picture', 'nano banana', 'ideogram', or wants AI-generated images from the terminal.

Coordinate release operations across mobile and web with preflight checks, staged rollout logic, and post-release verification. Use when users ask for release readiness, APK/IPA location checks, environment promotion, or combined web/mobile release sequencing.

Use to set up a project for spec-driven development - walks the user through each convention file (constitution, architecture, testing, glossary, domain, design) and the agent memory file (CLAUDE.md/AGENTS.md/GEMINI.md/.agents.md) by loading the matching ss-bs-discovering-<topic> inline skill for each, then scaffolds .sublime-skills/config.yml and supporting directories. Asks once at the top whether to run the prescriptive suggestion pass alongside the descriptive scan. User-invoked, not part of the SDD pipeline.

Practical DDD patterns for Jakarta EE web applications that distribute cognitive load. Use when designing controllers, entities, services, or when evaluating cohesion and load balance.

REST API design patterns and MicroProfile OpenAPI documentation. Use when designing endpoints, choosing HTTP methods, status codes, or documenting APIs with OpenAPI annotations.

name: encore-go-cron description: Schedule periodic / recurring work in Encore Go using `cron.NewJob` from `encore.dev/cron`. Covers `Every: "1h"` interval syntax and `Schedule: "0 9 * * 1"` cron expressions...

Show DevTrail documentation status. Use to verify if AI agents properly documented their changes.

Use when the user wants to step through a feature's checkpoints chronologically, pausing at each step to ask questions. Triggers on phrases like "replay <feature>", "walk me through how X was built", "show me the journey of", "step me through how Y was implemented", and "replay the last week"

Performs installation and deployment of the EPIR application (Cloudflare Workers, D1, Shopify, Hydrogen). Includes Shopify App build and deploy, extensions, and App Proxy. Use when the user requests deployment, installation, or a Shopify deploy for EPIR, or when running deploy.ps1, performing D1 migrations, managing secrets, deploying the RAG worker, or deploying Hydrogen Pages.

Iterative code review operator for PRs, diffs, and local changes. Use when the user asks to review code, review a PR, do a second-pass audit, run a review-fix-review loop, or says code review / PR review / re-review. Provides repo-adaptive preflight, fixed reviewer roles, findings deduplication, root-cause tracking, review-only and review-fix-loop modes, plus a root-cause-strict fix loop for stateful or cross-module problems.

Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok.

Semantic search, similar content discovery, and structured research using Exa API

Comprehensive guide for browser automation and web scraping with go-rod (Chrome DevTools Protocol) including stealth anti-bot-detection patterns.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth....

Monitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements stop-losses.

Use this skill when the user needs deep, multi-step research using native web tools (WebSearch/WebFetch) without external API keys.

Use this skill to properly format professional references and prepare reference materials.

This skill should be used when the user has a spec or requirements for a multi-step task before touching code.

Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email sequences, ad copy, headlines, form pages, CTA text, or any conversion-focused content. Triggers on "optimize this page", "run autoresearch", "score these variants", "A/B test this copy".

When to use this skill for systematic debugging including root cause analysis, error tracing, performance profiling, and memory leak detection