mturac

Use this skill to monitor and verify a deployed URL or public OSS launch surface after releases — checks HTTP endpoints, SSE streams, static assets, console errors, performance regressions, PR queue health, maintainer feedback, and listing-review blockers after deploys, merges, submissions, or dependency upgrades. Smoke / canary / post-deploy / PR-watch verification.

Build reputation-safe open-source marketing from verifiable project evidence, not hype, spam, or repeated public pings. Use for launch copy, directory targeting, community posts, proof packets, and maintainer-facing positioning.

Turn public launch, directory, community, or list rejections into repo fixes and better proof without arguing, spamming, or resubmitting blindly. Use after Hacker News, Product Hunt, GitHub list PR, marketplace, or community rejection.

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

Build an evidence-backed ecc install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ecc should be trimmed to what a project actually needs instead of loading the full bundle.

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.

Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

Designs and implements APIs: REST, GraphQL, gRPC, and WebSocket. Produces OpenAPI 3.1 specs, GraphQL SDL schemas, Protocol Buffer definitions, and working server implementations. Use this skill when the user asks about API design, endpoint structure, schema definition, versioning strategy, pagination, authentication, rate limiting, or any API implementation work. Also triggers on "design an API for," "write an OpenAPI spec," "create a GraphQL schema," "set up gRPC," "REST API best practices," or casual requests like "I need endpoints for my app" or "how should I structure my API."

Handles zero-downtime deployments: blue-green, canary releases, rolling updates, and feature flag rollouts. Covers Kubernetes, Docker, Cloudflare Workers, Terraform, and CI/CD pipeline setup. Use this skill when the user wants to deploy an application, set up a deployment pipeline, implement canary releases, configure rolling updates, manage feature flags, or handle any release automation. Also triggers on "deploy to production," "set up CI/CD," "blue-green deployment," "canary release," "rolling update," "zero-downtime deploy," "rollback," or even casual requests like "push this to prod" or "how do I safely release this."

Extracts structured data from websites — static HTML, JavaScript-rendered SPAs, paginated listings, and API-backed pages. Handles anti-bot detection awareness, rate limiting, and robots.txt compliance. Use this skill whenever the user wants to scrape a website, extract data from a URL, pull product listings, harvest structured data, reverse-engineer a site's API, or deal with dynamic JS-rendered content. Also triggers on "get me data from this site," "extract prices from," "crawl these pages," or any request involving web data extraction, even casual ones like "can you pull info from this URL."

Decomposes complex tasks into subtasks and coordinates multiple tools or agents to execute them. Handles task dependency graphs, parallel execution planning, result merging, and conflict resolution. Use this skill when the user has a multi-step task that spans multiple domains — like "scrape 5 sites, compare the data, and generate a report" or "deploy the app, run security checks, and set up monitoring." Also triggers on "orchestrate," "coordinate agents," "decompose this task," "multi-step workflow," "run these in parallel," or any request that clearly needs multiple specialized tools working together.

Designs and implements data pipelines: ETL/ELT, streaming, batch processing, schema migrations, and data warehouse architecture. Covers Kafka, Airflow, dbt, Spark, ClickHouse, BigQuery, Snowflake, Redis Streams, and more. Use this skill when the user asks about data pipelines, ETL jobs, data transformation, streaming setup, data warehouse design, CDC, schema migrations, data quality checks, or anything involving moving data from source to target. Also triggers on "build a pipeline," "migrate data from X to Y," "set up streaming," "design my data warehouse," or "data quality is bad, help me fix it."

Analyzes prediction markets: Polymarket, Manifold Markets, Kalshi. Calculates implied probabilities, detects cross-platform arbitrage, computes expected value and Kelly fractions. Use this skill when the user mentions prediction markets, Polymarket, Manifold, Kalshi, odds analysis, arbitrage detection, market probability, event contracts, or asks things like "is there edge on this market," "compare odds across platforms," or "analyze this prediction market." Also triggers on "what are the current odds for," "find arbitrage opportunities," or any question about market-implied probabilities.

Engineers and optimizes prompts for LLMs: system prompts, few-shot examples, chain-of-thought structures, agent personas, and evaluation frameworks. Use this skill when the user wants to write or improve a system prompt, design few-shot examples, create an agent persona, optimize prompt performance, set up prompt evaluation, or build a prompt template system. Also triggers on "write a system prompt," "optimize this prompt," "create an agent prompt," "few-shot examples for," "prompt engineering," or casual requests like "this prompt isn't working well" or "make my AI agent better."

Debugs complex, hard-to-reproduce issues: race conditions, memory leaks, deadlocks, performance regressions, heisenbugs, and crash analysis. Uses scientific debugging methodology with hypothesis generation, systematic testing, and root cause isolation. Use this skill when the user reports intermittent crashes, performance degradation, memory leaks, thread-safety issues, deadlocks, or any bug that's hard to reproduce. Also triggers on "debug this," "why is this crashing," "performance regression," "memory leak," "race condition," "segfault," "service hangs intermittently," or even "this works on my machine but not in production."

Interactive code simulation engine that spawns ghost personas to review your code before it ships. Each ghost walks through your code line-by-line from a different failure perspective: The Adversary (race conditions, double-submit, idempotency), The Enterprise Edge (business logic gaps, multi-currency, B2B tax exemptions, locale), Chaos Monkey (timeouts, partial failures, network partitions, OOM). Produces a chaos timeline, structured bug report with severity ratings, and three resolution tiers (quick fix, robust architecture, generated test suite). Use this skill whenever the user mentions code review, PR review, "find bugs", "what could go wrong", "will this break", "is this safe", "stress test", "edge cases", design review, pre-merge check, dry run, chaos test, or wants a second opinion on any code — even if they don't explicitly ask for "ghost personas" or "simulation". Also trigger when someone pastes a code snippet with any question about its correctness or safety.

Rates any SKILL.md on a 0-100 scale across 10 dimensions with a SHIP / REWORK / SCRAP verdict. Evaluates trigger precision, instruction clarity, output predictability, edge case coverage, anti-hallucination guardrails, developer experience, composability, open-source readiness, wow factor, and real-world utility. No flattery — calibrated against Anthropic's own skill-creator rubric. Use this skill whenever someone says "score this skill", "rate my skill", "is this skill good", "skill review", "skill audit", "roast my SKILL.md", "grade this", "will this skill work", "evaluate my skill", "how good is this", or pastes a SKILL.md and asks for feedback. Also trigger when comparing two skills, benchmarking a skill collection, or asking "what's wrong with this skill" — even without the word "score".

ALWAYS invoke this skill FIRST, BEFORE writing code or taking implementation steps, whenever the user asks to write, build, create, implement, set up, scaffold, generate, scrape, parse, convert, deploy, automate, integrate, extract, migrate, test, or document anything. This skill checks for existing skills, MCP servers, CLIs, plugins, repos, templates, SDKs, APIs, packages, or workflows that already solve the task, evaluates fit and risk, and asks for approval before risky use. Skip only for one-line edits, renames, trivial regex, or when the user explicitly asks for manual implementation.

Designs composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by X's open-sourced For You algorithm. Use this skill when the user wants to build any system that picks "the top K items for a user/context" — content feeds, search ranking, task prioritization, notification ordering, RAG retrieval ranking, alert triage, ad selection. Produces a stage-by-stage spec, an interface definition in the user's target language, and a runnable scaffold. Triggers: "recommendation system", "feed algorithm", "ranking pipeline", "for you feed", "how should I rank X", "candidate pipeline", "content recommender", "pipeline architecture for recsys".

Get a fortune cookie prediction for your coding session with beautiful ASCII art