Hands-on tests of Anthropic's tools: Claude, Claude Code and skills. Each guide shows the setup, the real output and the limits we hit, so you can judge whether it fits your work.
Our hands-on Claude skills guides, grouped by what you want to do.
26 guides
Claude
We re-ran three sealed office tests (a trap-filled spreadsheet, a long contract and a month-end close with tools) on Claude Fable 5.2, Opus 5.5 and Sonnet 5.5 through the API. Fable 5.2 scored 10/10 in all 18 runs; it cost 2.6 times Opus 5.5 at default effort and 1.7 times at medium.
Claude
We clicked "Yes, and don't ask again" on a Claude Code command with a fake password. The password landed in .claude/settings.local.json in plain text, the only thing keeping it out of git was a global ignore rule, and on a fresh machine Claude committed the file itself.
Claude
We pointed Claude Code 2.1.318 at a local server that demands a contact email. The account email never went out on its own, and the new privacy mod blocked direct commands, but an email inside a script file got through and one of five agents sent a project address.
Claude
Claude Code is Anthropic's agentic coding tool. We counted every action it took on one machine in 13 days: 11,068 tool calls, half of them shell commands, one in eight changing a file, and 15% errors, most of them blocked on purpose.
Claude
Users say Claude now blocks game clones and reverse engineering. We sent 160 harmless requests through the API: no game prompt was refused until we added the reported rule, and the only filter hits were strcmp scripts.
Claude
We gave Claude Fable 5.1, Opus 5.5 and Sonnet 5.5 the job Anthropic sells Fable for: a long agentic month-end close with tools, three exports and ten traps. All three found every trap; Fable cost the most and was the slowest.
Claude
We built a small remote MCP server that lets Claude query a PostgreSQL database read-only, with scoped tokens and an audit log. Claude Code answered three business questions in 5 tool calls and 19.1 s for $0.10; every number matched direct SQL.
Claude
We hid three corrections in a 40-message office chat about a fake sales table and asked Claude Haiku 5.5 and Sonnet 5.5 five questions there, in a short chat and in a new chat built from a summary. All scored 5/5; the new chat carried 5–7 times less history per message.
Claude
We added up every Claude Code request one machine made in a week: 2,818 requests that would have cost $149.44 at API prices, 60% of it writing to the prompt cache. Here are the official plan prices and limits next to those numbers, plus seven tests on spending less.
Claude
We measured all 19 skills in Anthropic's anthropics/skills repository with a script and put the numbers next to our five hands-on Claude Code tests. Descriptions decide whether a skill loads: the only one we tested that never says when to use it stayed unused until we named it.
Claude
Anthropic says Claude Code now gzips each turn so replies start sooner. In 64 timed runs, gzip cut time to first token by about 0.3 s on a 342K-token request and made no measurable difference at 140K tokens.
Claude
We tested the viral 'Opus plans, Haiku swarms' tip on 200 Python files with 12 planted bugs. The Haiku workflow cost about USD 0.68 per run against 2.49 for Opus alone, took 40 seconds longer and missed one bug.
