Start here

Agent skill

Drop-in skills for Claude Code, Codex and other coding agents, with the full decision-machine-1 context.

The milliseconds.ai skills give your coding agent the eight capabilities, the rules for writing labels, the threshold bands and the evaluation loop. The agent reads the live docs as part of each task. Source: github.com/CloudRaker/milliseconds-skills.

Installation

Run these two commands in your terminal:

claude plugin marketplace add CloudRaker/milliseconds-skills
claude plugin install milliseconds@milliseconds-skills

The plugin also registers the docs MCP server, so the agent can search these pages.

Choose one installation method. Two copies of the same skill confuse the agent.

What the skills contain

SkillCovers
millisecondsThe umbrella: authentication, choosing a capability, label writing, thresholds per action, batching, errors, patterns
milliseconds-yes-noStatements, hints, batched flags, guardrails
milliseconds-classifyDescribed labels, probability with confidence, intent routing, classify-tree
milliseconds-rateOrdered scales, routing on score, composite scoring
milliseconds-answerOne span per question, offsets, null handling
milliseconds-extractJSON Schema to a typed object, the schema support matrix
milliseconds-entitiesEvery span per type, redaction with offsets
milliseconds-verifyChecking a held value against the text, reading found[]
milliseconds-openaiThe OpenAI-compatible surface and when to go native
milliseconds-evaluateGolden sets, threshold sweeps, monitoring

Updates

For the Claude Code plugin:

claude plugin marketplace update milliseconds-skills
claude plugin update milliseconds@milliseconds-skills

Restart Claude Code or run /reload-plugins. For skills.sh installations, run npx skills update.

Example prompts

Name the skill in your prompt. In Claude Code you can also invoke /milliseconds:milliseconds.

Find where a typed decision replaces fragile code:

Using the milliseconds skill, explore the project and find places where a typed
decision (classify, yes-no, rate, extract) could replace fragile parsing or an
LLM prompt-and-parse step.

Let the agent run cheap experiments with a key from the console:

Using the milliseconds skill and the key in MS_API_KEY, route inbound support
tickets to billing, shipping or account, with a review queue for uncertain cases.
Put the labels and thresholds in one file.

Point the agent at a recipe:

Using the milliseconds skill, apply the invoice extraction recipe
(https://docs.milliseconds.ai/recipes/invoice-extraction.md) to the PDFs parsed in
invoices/, and verify the total and invoice number before writing to the database.

Working with the agent

  1. Review the plan before the agent writes code. The capability choice and the label wording decide the outcome.
  2. Keep the labels, statements, scales and thresholds in one file. That file is what a person reviews.
  3. Agents write vague statements. Expect to edit wording together. The writing guide has the rules.
  4. Ask the agent to build a golden set before it tunes any threshold. Do not accept a threshold without a table behind it.

Common issues

Invoke /milliseconds:milliseconds in Claude Code, or write “use the milliseconds skill” in another agent. If it still does not load, confirm the installer targeted the agent you use, then restart it.

Read the label text first, then the thresholds. Labels that name a verdict rather than a case score noise. A threshold set too high causes false negatives. Too low causes false positives. The thresholds page gives the bands.

When you only need the best option, take the winner. Use confidence as a second axis on classify and rate, and probability on the rest. Never compare a yes-no probability with a classify probability on one scale.

A stale skill causes this. Update it with the commands above. The agent can also read any page of these docs as Markdown by adding .md to the URL.