Skip to content

drafael/coding-harness / skills/typesafe-ai

typesafe-ai

Verified

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.

FileKindSize
LICENSEother1.0 KB
README.mdmarkdown2.5 KB
SKILL.mdskill md10.9 KB
scripts/evaluate.mjsexecutablescript3.4 KB
scripts/evaluate.test.mjsscript6.1 KB
# TypeSafe AI skill

Designs and implements TypeSafe System One workflows using the current official documentation. This local copy also includes a small command-line helper for direct API experiments.

## Requirements

- Node.js 20 or newer for the helper
- A TypeSafe API key exported as `TYPESAFE_API_KEY`
- Network access to `https://api.typesafe.ai`

Do not commit the API key or include it in request files.

## Direct evaluation

Create a request containing `state` and one or more questions:

```json
{
  "state": "My card was charged twice.",
  "questions": {
    "refund_requested": {
      "type": "noul",
      "instructions": "Does this message request a refund?"
    }
  }
}
```

Run it from the skill directory:

```bash
node scripts/evaluate.mjs request.json
```

The helper also accepts stdin:

```bash
node scripts/evaluate.mjs < request.json
```

It uses `jev-latest` when the request does not specify a model. Responses are written as formatted JSON to stdout; diagnostics are written to stderr. Requests time out after 10 seconds, matching the official JavaScript SDK default. HTTP error bodies are omitted because they may echo submitted state.

The helper performs one request without retries. Production integrations should use the current TypeSafe SDK or implement the retry behavior documented by TypeSafe.

Sending a request transmits its state and questions to TypeSafe. Review the content and obtain the required authorization before using repository, private, or user data.

## Tests

Run the zero-dependency subprocess test suite with Node.js 20 or newer:

```bash
node --test scripts/evaluate.test.mjs
```

The tests replace `fetch` in child processes and do not contact the live TypeSafe API.

## Installation

This directory follows the [Agent Skills specification](https://agentskills.io/specification). Copy or symlink it into the skill directory used by the target coding agent:

- Claude Code: `.claude/skills/typesafe-ai` or `~/.claude/skills/typesafe-ai`
- Pi, Codex, OpenCode, or Copilot: `.agents/skills/typesafe-ai` or `~/.agents/skills/typesafe-ai`

## Upstream and updates

- Official skill: <https://github.com/typesafe-ai/skills/tree/main/skills/typesafe-ai>
- Documentation index: <https://docs.typesafe.ai/llms.txt>
- API reference: <https://docs.typesafe.ai/api>

To update, compare `SKILL.md` with the official version and retain the local “Run a direct evaluation” section. Review API changes before modifying the helper.

## License

The official skill is distributed under the MIT License. See [`LICENSE`](LICENSE).
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall