发现 Skills

Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).

Lists available make commands for Streamlit development. Use for build, test, lint, or format tasks.

DCE-safe require() patterns and edge runtime constraints. Use when writing conditional require() calls, guarding Node-only imports (node:stream etc.), or editing define-env-plugin.ts / app-render / stream-utils for edge builds. Covers if/else branching for webpack DCE, TypeScript definite assignment, the NEXT_RUNTIME vs real feature flag distinction, and forcing flags false for edge in define-env.ts.

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automating code vulnerability detection.

CCXT cryptocurrency trading library. Use for cryptocurrency exchange APIs, trading, market data, order management, and crypto trading automation across 150+ exchanges. Supports JavaScript/Python/PHP.

Fraud risk assessment skill based on the fraud triangle with red flag detection

Full-stack diagnostics for agent and LLM applications. Audits the 12-layer agent stack for wrapper regressions, memory contamination, tool-discipline failures, hidden repair loops, and rendering corruption. Generates prioritized findings and code-first fixes. Essential for developers building agent applications, autonomous loops, or LLM-powered features.

A regression testing strategy for AI-assisted development. Sandbox-mode API tests that do not depend on a database, an automated defect-check workflow, and a pattern for catching AI blind spots when the same model both writes and reviews code.

Build a new API connector or provider that precisely matches the existing integration patterns of the target repository. Use this when adding one or more integrations without inventing a second architecture.

name: blueprint description: Transform a single-line objective into a step-by-step construction plan for a multi-session, multi-agent engineering project. Each step contains a self-contained context brief so a newly started agent can execute it directly. Includes adversarial review gates, a dependency graph, parallel-step detection, an antipattern catalog, and a plan-mutation protocol. Trigger conditions: when the user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that requires multiple sessions. Non-trigger conditions: when the task can be completed in a single PR or with fewer than three tool calls, or when the user says "execute directly." ...

Bun as a runtime, package manager, bundler, and test runner. When to choose Bun instead of Node, migration considerations, and Vercel support.

Create CodeTour `.tour` files — step-by-step walkthroughs for specific personas that include real file paths and line anchors. Useful for onboarding, architecture tours, PR walkthroughs, RCA exercises, and structured “explain how it works” requests.

A universal coding standard, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Cache expensive file-processing results using a SHA-256 content hash — path-independent, automatically invalidated, and separating the service layer.

DeFi automated market maker (AMM) smart contract security audit patterns. Covers flash loans, slippage, sandwich attacks, price manipulation, reentrancy, and incorrect integer arithmetic.

Asynchronous task processing using Django and Celery. Task queuing, worker management, error handling, and scheduling. Integration with Redis/RabbitMQ brokers.

An evidence-first revenue, pricing, refunds, team-billing and billing-model truth workflow for ECC. Use when users need sales snapshots, pricing comparisons, duplicate-charge diagnostics, or a code-grounded billing reality instead of generic payment advice.

Create reproducible, cross-platform development environments with Flox — a declarative environment manager built on Nix. Use this skill whenever you need to set up projects with system-level dependencies (compilers, databases, native libraries such as openssl, libvips, BLAS, LAPACK); configure reproducible toolchains for languages like Python, Node.js, Rust, Go, C/C++, Java, Ruby, Elixir, PHP, or others; manage environments that behave identically on macOS and Linux; pin exact package versions for a team; run local services (PostgreSQL, Redis, Kafka) alongside development tools; onboard a new developer with a single command; or solve “works on my machine” problems. This is especially valuable for AI-assisted workflows and vibe coding — Flox lets agents install tools into a project-scoped environment without sudo, without polluting the system, and without sandbox restrictions, and the resulting environment is committed to the repository so anyone can reproduce it instantly. Even if a user doesn't mention Flox, use this skill when they describe the need for reproducible, declarative, cross-platform development environments and system packages. Also use it when the user mentions .flox/, manifest.toml, flox activate, or FloxHub.

Home-lab WireGuard VPN setup, remote access, key management, and end-to-end encryption.

Kotlin coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, testing.

Ktor server pattern (includes routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSocket, and testApplication tests).

Japanese translation: This file requires a Japanese translation for plankton-code-quality.

name: returns-reverse-logistics description: Standardized expertise for returns authorization, receiving and inspection, disposition decision-making, refund processing, fraud detection, and warranty-claim management. Based on insights from a returns operations manager with over 15 years of experience. Includes a grading framework, disposition economics, fraud pattern recognition, and vendor recovery processes. Applicable for handling product returns, reverse logistics, refund decisions, return-fraud detection, or warranty-claim handling. license: Apache-2.0 ver...