tpmjs/packages/tools
Ajax Davis 1234b383e7 feat(judge): add AI conversation quality evaluation tool
- Evaluates conversations across 10 metrics:
  taskCompletion, accuracy, relevance, clarity, efficiency,
  userIntentAlignment, actionability, progress, errorHandling, completeness
- Returns weighted overall score (0-10)
- Provides verdict (pass/retry/fail) with reasons
- Detects conversation loops and stuck states
- Lists must-dos, suggestions, and next steps
- Designed for frequent use in agentic loops
2026-01-17 10:49:40 +10:00
..
create-basic-tools fix(create-basic-tools): fix clack select types 2026-01-16 02:46:07 +10:00
discord-post feat: add environment variables support for agents and collections 2026-01-12 01:35:29 +10:00
discord-read feat: add environment variables support for agents and collections 2026-01-12 01:35:29 +10:00
emoji-magic refactor: replace exportName with name throughout codebase 2026-01-14 14:18:36 +10:00
hello refactor: replace exportName with name throughout codebase 2026-01-14 14:18:36 +10:00
markdown-formatter refactor: replace exportName with name throughout codebase 2026-01-14 14:18:36 +10:00
official feat(judge): add AI conversation quality evaluation tool 2026-01-17 10:49:40 +10:00
registryExecute refactor: replace exportName with name throughout codebase 2026-01-14 14:18:36 +10:00
registrySearch refactor: replace exportName with name throughout codebase 2026-01-14 14:18:36 +10:00
search-registry refactor: replace exportName with name throughout codebase 2026-01-14 14:18:36 +10:00
src feat: implement playground app with AI SDK v6 tool execution 2025-12-04 02:51:02 +10:00
test-file-writer feat: complete MCP Bridge implementation 2026-01-13 00:59:34 +10:00
unsandbox refactor: replace exportName with name throughout codebase 2026-01-14 14:18:36 +10:00
package.json chore: update dependencies with compatibility fixes 2026-01-09 22:49:41 +10:00
tsconfig.json feat: implement playground app with AI SDK v6 tool execution 2025-12-04 02:51:02 +10:00