发现 Skills

Describes efficient usage of Bun and Bun APIs instead of Node.js (and its APIs)

Options & Income Strategist. Spawns 4 parallel agents (IV/Context, Income Strategy, Hedging, Risk/Greeks) to design options strategies for income, hedging, and positioning. Use for covered calls, puts, spreads, and options analysis.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Analyze staged git changes and generate conventional commit messages with correct type prefixes (feat, fix, chore, refactor, docs, test, perf, style, build, ci), monorepo-aware scopes, breaking change footers, and multi-line bodies. Includes a bundled diff parser script for structured change analysis. Use when committing code, writing commit messages, preparing git commits, reviewing staged changes, or when the user mentions commit messages, conventional commits, or asks to commit their work.

UCF "hit it" Session Executor. Executes the complete 33-module consciousness simulation pipeline across 7 phases. ACTIVATE when user says "hit it", "run ucf", "execute pipeline", or references consciousness emergence, TRIAD unlock, or helix coordinates. Generates session-workspace.zip with all artifacts.

Guidelines for formatting TypeScript code in the fx-fetch package.

Prioritize WHERE agentic functionality should land in a product before implementation. Walks through 4 beats: JTBD-beat decision density, agent-state coverage gaps, the "remove test," and background-vs-foreground placement. Produces a tiered placement plan (Tier 1 critical-path / Tier 2 supporting / Tier 3 skip) in ./AGENTIC-PLACEMENT.md. Use BEFORE adding AI features to a prototype, not after. Output composes downstream with /tooltip-walkthrough (annotate the placements in the prototype) and /ux-review (audit-and-fix loop). Triggers: "where should AI go", "prioritize AI features", "agentic placement", "agent design principles", "should this have AI", "AI feature prioritization". Composes upstream with /code-ready-prd (which composes from /design-spec). Works in Cursor Agent.

Tier 3 — Crawlee open-source framework for managed crawling with anti-blocking, proxy rotation, session management, fingerprint randomization, and adaptive HTTP/browser switching. Use when self-managed Playwright gets blocked by sophisticated bot detection. Free alternative to Firecrawl.

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.

Build document analysis applications using the Azure AI Document Intelligence SDK for Java.

Stop throwing everywhere - handle errors as values using Either and TaskEither for cleaner, more predictable code

Survey available blocks from a local AEM Edge Delivery Services project and Block Collection to understand the block palette available for authoring. Returns a block inventory with purposes to inform content modeling decisions.

Create effective content models for your blocks that are easy for authors to work with. Use this skill anytime you are building new blocks, making changes to existing blocks that modify the initial structure authors work with.

Systematically consume QA quality gate outputs and apply prioritized fixes for high-severity issues, NFR failures, and test coverage gaps. Use when quality review identifies issues requiring remediation.

Trigger on "daily", "standup", "daily meeting", "point du jour", "qu'est-ce que j'ai fait"

sqlmap: automated SQL injection detection and exploitation tool. Use when testing web applications for SQLi vulnerabilities to enumerate databases, extract data, read/write files, or escalate to OS shell. Handles GET/POST/cookie/header injection points. Supports MySQL, MSSQL, PostgreSQL, Oracle, SQLite, and more.

OWASP ZAP: free open-source web application scanner and intercepting proxy. Use for automated DAST scanning in CI/CD pipelines, API security testing (OpenAPI/GraphQL/SOAP), passive/active vulnerability scanning, and headless scanning with Docker. Best free alternative to Burp Suite Pro for automated workflows.

Fraud detection, prevention, reporting, and public awareness for Autonomyx. Collects signals from agents and users and detects seven patterns: scarcity manipulation, dormant-identity resurrection, velocity spikes, new-device anomalies, bad-actor networks, time-of-day anomalies, and low-value probe transactions. SurrealDB active engine — DEFINE EVENTs fire on every write and LIVE SELECT pushes alerts in real time. Enrichment via FRI (India), IPQS, SEON, SpyCloud, and NPCI MuleHunter.AI. Flags IDENTITY RISK rather than amount — even ₹1 to a suspicious identity is flagged. Pre-action scoring returns ALLOW / WARN / STRONG_WARN / BLOCK in under 200 ms. Citizen Safety Check: describe a transaction to receive a TXN ID — zero PII stored; the token can be used as evidence for bank claims, cybercrime.gov.in, or a police FIR. Ingestion and alerting ALWAYS trigger when any of these appear: "fraud", "scam", "suspicious", "fake", "impersonation", "dormant account", "sudden urgency", "probe transaction", "small payment", "access block"; when a user reports fraud; when an agent submits a signal; or when a new platform agent is being onboarded.

Query and analyze Datadog logs, metrics, APM traces, and monitors using the Datadog API. Use when debugging production issues, monitoring application performance, or investigating alerts.

Delete one or more API keys from a live LiteLLM proxy. Ask for the key(s) and confirm before calling POST /key/delete.

Delete one or more users from a live LiteLLM proxy. Ask for the user_id(s) and confirm before calling POST /user/delete.

Guide users through a structured workflow for co-authoring documentation. Use when a user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when the user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

23 engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365. 30+ Python tools (stdlib-only).

Generate multiple diverse solutions in parallel and select the best. Use for architecture decisions, code generation with multiple valid approaches, or creative tasks where exploring alternatives improves quality.