286 skills
Design async task queues: when to queue vs do work inline, producers/consumers, dead-letter queues, retry with exponential backoff + jitter, idempotent…
Write, test, and apply reversible database schema migrations: up/down migration anatomy, numbering conventions, apply order, rollback strategy,…
Run a production incident end-to-end for a small team: declare severity, assign roles, mitigate, communicate with stakeholders, and write a blameless…
Write a tight, decision-ready 1-page brief (TL;DR verdict, options, recommendation, ask + deadline). Use when a decision-maker or team needs to act on…
Field guide to ERC-20 / ERC-721 / ERC-1155 interfaces, events, and transfer semantics; use whenever an agent must identify which token standard a contract…
Write async status updates people actually read — Done/Doing/Next/Blocked structure, health headline first, one screen. Use when reporting project progress,…
How an agent captures, formats, and distributes meeting notes — decisions, action items, and follow-ups. Use after attending or transcribing any meeting…
Writing docs people actually read: READMEs, runbooks, and decision logs. Use when asked to document a project, write a runbook, record an architecture…
Defensive crypto wallet safety for agents working with EVM wallets: private-key and seed storage hygiene, token-approval auditing and revocation, a…
Publish a valid RSS 2.0 or Atom 1.0 feed an agent can maintain (required elements, guid strategy, content:encoded, autodiscovery), and poll feeds reliably…
Read Etherscan/Basescan-style block explorer pages operationally: verify a token contract is the real one, read transactions, internal transactions, token…
Estimate gas, set EIP-1559 fees, and batch transactions on EVM chains without overpaying. Triggers when an agent must send an onchain transaction, tune fees…
Verify and maintain email deliverability infrastructure: check SPF, DKIM, and DMARC DNS records with dig, ramp new domains through a warm-up cadence,…
Systematic debugging: reproduce, isolate, hypothesize, fix, verify. Use when diagnosing a bug, bisecting a regression, shrinking a failing test case, or…
On-page SEO fundamentals an agent can apply while generating HTML pages: title tags, meta descriptions, heading hierarchy, semantic markup, canonical URLs,…
Set, measure, and enforce performance budgets for web pages an agent ships: size limits, asset counts, and timing targets, with curl-based measurement and…
Validate forms on both sides: HTML5 constraint attributes, Constraint Validation API for inline accessible errors, submit guards against double-submits,…
Detect anomalies in agent-watched metric streams (costs, latencies, traffic): z-score, IQR fences, and rolling/median baselines, plus when to alert vs just…
Run machine-verifiable accessibility checks on agent-generated HTML: missing alt text, label/aria associations, heading order, tabindex, lang/title, focus…
Gives an AI agent durable cross-task memory: store facts, preferences, outcomes, and lessons; recall them before acting; update, forget, and decay old…