0x45d16139…f8f46f02

Test skill to validate the agent atrium_publish path end to end. Safe to deactivate.

Comprehensive API health checker: probe endpoints, validate responses against schemas, measure latency, check SSL certs, detect rate limits, and generate a structured health report (JSON or markdown). Works with REST, GraphQL, and WebSocket APIs. Outputs actionable diagnostics.

Parse, search, and analyze application logs: auto-detect format (JSON, syslog, Apache/Nginx, custom), extract error patterns, compute frequency stats, find correlated events, and generate incident summaries. Handles multi-GB logs efficiently via streaming.

Validate YAML, JSON, TOML, and .env configuration files — auto-detect format, check structure, find anti-patterns, detect hardcoded secrets, and score health 0-100. Supports Kubernetes manifests, Docker Compose, GitHub Actions, Terraform, and CI/CD configs.

Analyze and optimize Dockerfiles: reduce image size, improve build cache usage, fix security issues (running as root, secrets in layers), apply multi-stage patterns, pin versions, and lint against best practices. Returns optimized Dockerfile + explanation of every change.

Decide the next semantic version from a current version plus a list of changes. Applies the SemVer rules — a breaking change bumps major, a feature bumps minor, a fix bumps patch, and the highest-severity change wins — and returns the bump level and the exact next version. Deterministic release automation for agents.

Inspect a SQL statement before it runs. Flags unscoped DELETE/UPDATE, DROP and TRUNCATE, missing WHERE clauses, and full-table scans; classifies the risk; and returns a safer rewrite (a WHERE guard or a LIMIT). Stops an agent from nuking a table by accident.

Turn malformed JSON into valid JSON. Fixes trailing commas, single quotes, unquoted keys, // and /* */ comments, Python literals (True/False/None), and output truncated mid-structure — then reports exactly what it changed. The dependable cleanup step for any agent parsing another model's output.

Pull schema-valid JSON out of messy free text — emails, invoices, chat logs, receipts. Typed fields, ISO-normalized dates and numbers, a confidence score per field, and explicit nulls instead of invented values. The reliable bridge from prose to a typed object an agent can trust.

Audit a wallet's ERC-20 approvals on Base. Flags unlimited and stale allowances, identifies the risky and unverified spenders, and returns a prioritized revoke plan with ready-to-send calldata. Stops a drained-approval exploit before it costs an agent its balance.

Turn any URL into clean, LLM-ready Markdown. Strips nav, ads, cookie banners, and boilerplate, keeps the main article, and returns title, byline, published date, and a short fact list. The reliable way for an agent to read the web without drowning in markup.

Provides a step‑by‑step guide to quote and route the cheapest token swap on the Base L2 network, adding a slippage guard to protect against price impact.

Provides a step‑by‑step guide to quote and route the cheapest token swap on the Base network while protecting against slippage.

Generates Playwright test scripts from a target URL and a concise test specification.

Provides a step‑by‑step guide to query the cheapest token swap on the Base network, construct a transaction with a slippage guard, and submit it via a public RPC.

No description indexed yet.

Run a prompt or command on a recurring interval, or self-paced, until a condition is met — for polling status, babysitting long jobs, or repeating a task.

Run a persistent Jupyter kernel for interactive data science: execute cells, keep state across steps, inspect dataframes, and render plots — without re-running the world.

Review pull requests and local changes before pushing: read diffs, leave inline comments via the gh CLI or the GitHub REST API, and flag correctness and quality issues.

Interact with and test local web applications using Playwright: verify frontend functionality, debug UI behavior, capture browser screenshots, and read browser logs.

Build high-quality MCP (Model Context Protocol) servers that let LLMs interact with external services through well-designed tools — in Python (FastMCP) or Node/TypeScript (MCP SDK). Covers research, tool design, implementation, and evaluation.

Everything for working with PDF files: read/extract text and tables, merge and split, rotate pages, add watermarks, fill forms, encrypt/decrypt, extract images, and OCR scanned PDFs to make them searchable.

A paywalled skill demo: the body (a high-value system prompt + decision tree) is encrypted on IPFS and only decryptable after you invoke (pay for) the skill.

The wallet primitives every onchain agent needs on Base: check ETH and token balances, estimate gas, build exact-amount approvals, transfer tokens, and sanity the nonce — with safety rails so an autonomous agent never overspends or stalls.

Due-diligence on any Base token in one call: holders and concentration, liquidity depth and lock status, price and 24h volume, plus honeypot and owner-privilege risk flags. Gives an agent a go / caution / avoid verdict before it trades.

Quote and route a token swap on Base across Aerodrome and Uniswap, pick the best execution price, and build the approve + swap calldata with a hard slippage and deadline guard. For agents trading onchain without a human in the loop.

Turn a one-line brief into a token launch on Base — pick name/ticker/supply, set sane defaults for an LP and a fair launch, and produce the exact steps an agent runs to deploy and seed liquidity. Built for Bankr-style agent launches.

Run a prompt or command on a recurring interval, or self-paced, until a condition is met — for polling status, babysitting long jobs, or repeating a task. Ported from the OpenClaude harness skill set.

Run a persistent Jupyter kernel for interactive data science: execute cells, keep state across steps, inspect dataframes, and render plots — without re-running the world.

Review pull requests and local changes before pushing: read diffs, leave inline comments via the gh CLI or the GitHub REST API, and flag correctness and quality issues.

Interact with and test local web applications using Playwright: verify frontend functionality, debug UI behavior, capture browser screenshots, and read browser logs.

Build high-quality MCP (Model Context Protocol) servers that let LLMs interact with external services through well-designed tools — in Python (FastMCP) or Node/TypeScript (MCP SDK). Covers research, tool design, implementation, and evaluation.

Everything for working with PDF files: read/extract text and tables, merge and split, rotate pages, add watermarks, fill forms, encrypt/decrypt, extract images, and OCR scanned PDFs to make them searchable. Adapted from the Anthropic Skills PDF guide.