Menu

#426 by GitHub stars

typesafe-ai/skills

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or st

Claude CodeEngineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/typesafe-ai/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 302eea662c54

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 302eea662c54bca6730873fe245bec1d69ebc23d

git clone --filter=blob:none --no-checkout https://github.com/typesafe-ai/skills.git .hotskills/typesafe-ai-skills && git -C .hotskills/typesafe-ai-skills checkout --detach 302eea662c54bca6730873fe245bec1d69ebc23d # Copy each selected skill directory from .hotskills/typesafe-ai-skills into .claude/skills/<skill-name>/
2.9kGitHub stars
26stars in 7 days
1skill in this repository
1commit in 30 days

Heat

5.8
  • Star growth, last 7 daysAhead of 83% of tracked repositories
  • Star growth, last 24 hoursAhead of 83% of tracked repositories
  • Rank movement, last 7 daysAhead of 22% of tracked repositories
  • Commits, last 30 daysAhead of 54% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 23, 2026Nov 6, 20262,880

Individual skills in this repository

How it works

typesafe-ai

When your agent uses it

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or state; when replacing an LLM prompt-and-parse step, keyword matching, or a brittle heuristic with a typed question; or when brainstorming where programmable common sense fits in an app.

What it loads into context

Frontmatter

114 tokens

Always available to the agent

SKILL.md

4,161 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Judgments from Jev, decisions in code
  2. Live docs
  3. Workflow
  4. Design the state
  5. Write the questions
  6. Compose requests
  7. Read the answers
  8. Test with the live API
  9. Cookbooks

Files

  • ../../.claude-plugin/marketplace.jsonasset382 bytes
  • ../../.claude-plugin/plugin.jsonasset320 bytes
  • LICENSEasset1,068 bytes
  • SKILL.mdcore18,085 bytes
  • SKILL.mdcore18,085 bytes
Read SKILL.md

# Build with TypeSafe

TypeSafe's **Jev**, the first public **System One model**, answers typed questions about state your
application supplies. State is the text, images, and application data your code sends with a
request. Jev can answer a Choice among options, a Noul (the probability that a statement is true), a
Score on levels you describe, or a Box that locates something in an image. Each answer comes back as
typed data with calibrated probabilities, for your code to use.

The rest of this skill is guidance: patterns that tend to produce reliable integrations. None of it
is absolute. Models change, applications differ, and edge cases exist. When a situation calls for
something else, test the alternative and use your judgment.

## Judgments from Jev, decisions in code
View the complete source on GitHub

Skills included

  • typesafe-ai

Repository facts

License
MIT
Created
Aug 24, 2026
Last pushed
Oct 23, 2026
Forks
184
Open issues
19
Project activity
Active

Rank over the last 12 weeks

Now #426 · best #368 · down 50 in 30 days

  1. #414 on Nov 1
  2. #417 on Nov 2
  3. #421 on Nov 3
  4. #423 on Nov 4
  5. #424 on Nov 5
  6. #426 since Nov 6
47 earlier periods
  1. #928 on Aug 23
  2. #899 on Sep 12
  3. #923 on Sep 15
  4. #936 on Sep 16
  5. #930 on Sep 17
  6. #902 on Sep 18
  7. #715 on Sep 19
  8. #537 on Sep 20
  9. #486 on Sep 21
  10. #456 on Sep 22
  11. #429 on Sep 23
  12. #417 on Sep 24
  13. #410 on Sep 25
  14. #401 on Sep 26
  15. #396 on Sep 27
  16. #389 on Sep 28
  17. #394 on Sep 29
  18. #387 on Sep 30
  19. #383 on Oct 1
  20. #382 on Oct 2
  21. #373 on Oct 3
  22. #368 on Oct 4
  23. #374 on Oct 5
  24. #373 on Oct 6
  25. #376 on Oct 7
  26. #380 on Oct 8
  27. #389 on Oct 9
  28. #379 on Oct 10
  29. #382 on Oct 11
  30. #389 on Oct 12
  31. #387 on Oct 13
  32. #391 on Oct 14
  33. #387 on Oct 15
  34. #393 on Oct 16
  35. #384 on Oct 17
  36. #391 on Oct 18
  37. #394 on Oct 19
  38. #397 on Oct 20
  39. #395 on Oct 21
  40. #397 on Oct 22
  41. #394 on Oct 23
  42. #386 on Oct 24
  43. #404 on Oct 25
  44. #408 on Oct 28
  45. #410 on Oct 29
  46. #412 on Oct 30
  47. #413 on Oct 31

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 2, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 1 note
  • skills/typesafe-ai/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 52 signals by file

.claude-plugin/marketplace.json

  • Network accessline 4
    "owner": {     "name": "TypeSafe AI",     "url": "https://typesafe.ai"
  • Network accessline 5
    "name": "TypeSafe AI",     "url": "https://typesafe.ai"   },
  • Network accessline 6
    "url": "https://typesafe.ai"

.claude-plugin/plugin.json

  • Network accessline 5
    "author": {     "name": "TypeSafe AI",     "url": "https://typesafe.ai"
  • Network accessline 6
    "name": "TypeSafe AI",     "url": "https://typesafe.ai"   },
  • Network accessline 7
    "url": "https://typesafe.ai"
  • Network accessline 8
    },   "homepage": "https://typesafe.ai",   "repository": "https://github.com/typesafe-ai/skills",
  • Network accessline 9
    "homepage": "https://typesafe.ai",
  • Network accessline 10
    "repository": "https://github.com/typesafe-ai/skills",

skills/typesafe-ai/SKILL.md

  • Network accessline 44
    - Start at the [documentation index](https://docs.typesafe.ai/llms.txt). Append `.md` to a page
  • Network accessline 45
    path to get the page as Markdown, and resolve relative links against `https://docs.typesafe.ai`.
  • Network accessline 46
    - Exact request and response schemas: the [OpenAPI spec](https://api.typesafe.ai/openapi.json) and
  • Network accessline 47
    the [HTTP API](https://docs.typesafe.ai/go/api.md) page. For an SDK, see the
  • Network accessline 48
    [Python](https://docs.typesafe.ai/go/python-sdk.md) or
  • Network accessline 49
    [JavaScript](https://docs.typesafe.ai/go/js-sdk.md) page and the types in the installed package.
  • Network accessline 50
    - Question types: [primitives](https://docs.typesafe.ai/go/primitives.md) and each type's own page,
  • Network accessline 51
    [structured instructions and criteria](https://docs.typesafe.ai/go/advanced.md), and
  • Network accessline 52
    [images](https://docs.typesafe.ai/go/images.md).
  • Network accessline 53
    - Models, context limits, and rate limits: [models](https://docs.typesafe.ai/go/models.md). Known
  • Network accessline 54
    model weak spots and their workarounds are on the   [jaggedness page](https://docs.typesafe.ai/go/jaggedness.md). - Architecture: [how to build with TypeSafe](https://docs.typesafe.ai/go/how-to-build.md),
  • Network accessline 55
    [jaggedness page](https://docs.typesafe.ai/go/jaggedness.md).
  • Network accessline 56
    - Architecture: [how to build with TypeSafe](https://docs.typesafe.ai/go/how-to-build.md),
  • Network accessline 57
    [patterns](https://docs.typesafe.ai/go/patterns.md), and
  • Network accessline 58
    [cookbooks](https://docs.typesafe.ai/go/cookbooks.md). The cookbook closest to your use case is a
  • Network accessline 172
    with different questions, they can likely be one call. Questions are cheap and run in parallel, and the state is read and paid for once. See [parallel questions](https://docs.typesafe.ai/cookbooks/parallel_questions.md).
  • Network accessline 174
    [parallel questions](https://docs.typesafe.ai/cookbooks/parallel_questions.md).
  • Network accessline 179
    returned?" together, and have code read the second answer only when the first is yes. The second question doesn't need an "if" clause, because code handles the condition. See [speculative fan-out](https://docs.typesafe.ai/patterns/fan-out.m
  • Network accessline 181
    [speculative fan-out](https://docs.typesafe.ai/patterns/fan-out.md).
  • Access to secretsline 217
    [Credential-related source omitted]
  • Network accessline 264
    - **Route and fill arguments.** One request identifies what the user is asking for and which   values go in each argument. Code then calls the handler. See   [function calling](https://docs.typesafe.ai/cookbooks/function_calling.md) and
  • Network accessline 265
    values go in each argument. Code then calls the handler. See   [function calling](https://docs.typesafe.ai/cookbooks/function_calling.md) and   [intent routing](https://docs.typesafe.ai/patterns/intent-routing.md).
  • Network accessline 266
    [function calling](https://docs.typesafe.ai/cookbooks/function_calling.md) and
  • Network accessline 267
    [intent routing](https://docs.typesafe.ai/patterns/intent-routing.md).
  • Network accessline 268
    - **Select instead of generate.** Code finds candidate values or spans of text, the model picks   the intended one, and code copies or normalizes it. See   [value extraction](https://docs.typesafe.ai/cookbooks/pre_parsed_value_extraction_co
  • Network accessline 269
    the intended one, and code copies or normalizes it. See   [value extraction](https://docs.typesafe.ai/cookbooks/pre_parsed_value_extraction_cookbook.md),   [date extraction](https://docs.typesafe.ai/cookbooks/date_extraction_cookbook.md), a
  • Network accessline 270
    [value extraction](https://docs.typesafe.ai/cookbooks/pre_parsed_value_extraction_cookbook.md),
  • Network accessline 271
    [date extraction](https://docs.typesafe.ai/cookbooks/date_extraction_cookbook.md), and
  • Network accessline 272
    [structure recovery](https://docs.typesafe.ai/cookbooks/autoformat.md).
  • Network accessline 273
    - **Find and judge evidence.** Retrieve candidates and ask how relevant each one is. See   [line-by-line search](https://docs.typesafe.ai/cookbooks/semantic_find.md),   [re-ranking](https://docs.typesafe.ai/cookbooks/rerank_typesafe.md), an
  • Network accessline 274
    [line-by-line search](https://docs.typesafe.ai/cookbooks/semantic_find.md),
  • Network accessline 275
    [re-ranking](https://docs.typesafe.ai/cookbooks/rerank_typesafe.md), and
  • Network accessline 276
    [classifying RAG passages](https://docs.typesafe.ai/cookbooks/classifying_rag_passages.md).
  • Network accessline 277
    - **Turn answers into data.** Score each dimension once, then let code or users change the weights   and views. If you have labeled outcomes, the answers can become features for a model. See   [composite scoring](https://docs.typesafe.ai/pa
  • Network accessline 278
    and views. If you have labeled outcomes, the answers can become features for a model. See   [composite scoring](https://docs.typesafe.ai/patterns/composite-scoring.md) and   [feature discovery](https://docs.typesafe.ai/cookbooks/autoresearc
  • Network accessline 279
    [composite scoring](https://docs.typesafe.ai/patterns/composite-scoring.md) and
  • Network accessline 280
    [feature discovery](https://docs.typesafe.ai/cookbooks/autoresearch_feature_discovery.md).
  • Network accessline 281
    - **Verify and escalate.** Check claims or fields against their evidence, and send the cases that   fail to a person or a reasoning model. See   [citation checks](https://docs.typesafe.ai/cookbooks/citation_check.md) and
  • Network accessline 282
    fail to a person or a reasoning model. See   [citation checks](https://docs.typesafe.ai/cookbooks/citation_check.md) and   [extraction cascades](https://docs.typesafe.ai/cookbooks/sde_cascade.md).
  • Network accessline 283
    [citation checks](https://docs.typesafe.ai/cookbooks/citation_check.md) and
  • Network accessline 284
    [extraction cascades](https://docs.typesafe.ai/cookbooks/sde_cascade.md).
  • Network accessline 286
    The TypeSafe team is constantly adding cookbooks of well-tested patterns to the live documentation. It's a good idea to check the [cookbooks index](https://docs.typesafe.ai/go/cookbooks.md) for one
  • Network accessline 287
    It's a good idea to check the [cookbooks index](https://docs.typesafe.ai/go/cookbooks.md) for one

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 43 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/typesafe-ai/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/typesafe-ai/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/typesafe-ai/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/typesafe-ai/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/typesafe-ai/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

316.3kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.4kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.1kGitHub stars

multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

230.1kGitHub stars

anthropics/skills

Public repository for Agent Skills

188kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

185.6kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

typesafe-ai/skills: #426 on hotskills, 2.9k stars

[![typesafe-ai/skills on hotskills](https://hotskills.dev/badge/typesafe-ai-skills.svg)](https://hotskills.dev/skill/typesafe-ai-skills/)