Start here: the part that needs nothing
The registry’s read path is open. No account, no API key, no card, no trial clock:SKILL.md your runtime auto-discovers plus the 24-case eval.yaml that produced the +79-point number, so you can re-run the benchmark yourself instead of believing it. Note that the CLI prints the price alongside the lift: this skill buys those points with 126% more tokens, because it puts a command reference in the prompt. Lift is never free, and the registry shows you both halves.
(playwright-cli is just the example the first tutorial uses. Swap in any slug from the registry — the command is the same and so is the cost: nothing.)
Don’t want Python either? The same skill is a curl away, an MCP tool call, or — inside Claude Code — one /decimalai:install playwright-cli with nothing to pip install. See Use skills without the SDK.
Pick one
The two that are further away than they look.Skills Observability has no setup cost and a long wait: its payoff steps read analytics that only exist once your traffic has accumulated. The page’s own worked example is labelled “after 1 week” — treat it as the thing you read once traces are already flowing, not a thing you can do this afternoon.Training Pipeline lists four prerequisite bullets that unpack to seven: Python, the SDK, the
evals extra, the langchain extra, a DECIMAL_API_KEY, an agent already producing traces, and an OpenAI or Together.AI key for the fine-tune itself. It is the deepest tutorial here and it assumes everything the others teach.What actually needs an account
Nothing at all
Read any scorecard, pull any skill with its eval suite, re-run that benchmark locally on your own model key. Anonymous the whole way.
A free API key
Seeded demos, tracing your own agent, per-skill analytics. Signup shows you a key once; Free is generous on purpose.
Account + provider key
Anything that runs a model on your behalf — forking skills into your workspace, end-to-end agent tutorials, fine-tuning.
The five
Install a Skill
You use Claude Code or Cursor. Read one skill’s verified benchmark — the lift, the model, the token cost, the safety band — then put it on disk and watch it fire. No account.
The 2-Minute Demo
One command seeds a demo agent with two manifest versions and a trace corpus, then shows you the impact report. Another does the same for the ranked registry. No agent code, no LLM keys.
Build a Support Agent from Skills
Replace a 900-line mega-prompt with a lean prompt plus a routed skill bundle — every skill’s evidence read off its live scorecard, including the one that gets dropped for failing to earn its place.
Skills Observability
Which of your skills are actually being used, which version wins, and which one to retire. Read this once your own traces are flowing.
End-to-End Training Pipeline
Trace → evaluate → build a filtered dataset → fine-tune → deploy → new traces. The flywheel, with the staleness filtering that keeps a bad trace out of your training set.
Not sure any of these is the question you have
Introduction
What the product is and the one idea underneath it, in prose.
Quickstart
The reference setup path rather than a worked example — install, init, first trace.
Where these numbers come from. The install and pull timings were measured on 2026-08-17 in a fresh virtualenv with
DECIMAL_API_KEY unset, against decimalai 0.10.3 from PyPI. The lift and case count are pinned to the live scorecard in this page’s frontmatter, so a re-benchmark breaks the build rather than leaving a stale number here. The prerequisite counts are read off each tutorial’s own page. Times you see on your own machine will vary with your network — the point of the numbers is the order of magnitude, and which side of the account wall each tutorial sits on.