docs: reposition as the human-in-the-loop for AI coding (v0.6.1)#27
Merged
Merged
Conversation
Lead with what groundtruth is, not just what it catches: the automated human-in-the-loop for AI coding. It verifies an agent's claims against the real diff AND (opt-in) makes the agent run/screenshot/test its own work and self-fix before finishing — catching the lies, typos, and skipped work that slip through when an AI codes unsupervised. - README hero + intro rewritten around the human-reviewer framing and the two-stage value (verify claims → prove it works); leads with `setup`. - package.json + .claude-plugin/plugin.json descriptions refreshed; new keywords (self-healing, code-review, playwright). GitHub repo description and topics updated to match. - Docs/metadata only — no behavior change. 141 tests pass. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Sharpens how groundtruth is described everywhere — README, npm + GitHub descriptions, plugin manifest — to lead with what it is, not just what it catches.
The story: left unsupervised, an AI agent confidently reports work it didn't do, misses requirements, and leaves typos/half-edits — and the faster it codes, the more slips through. groundtruth is the human-in-the-loop, automated:
→ higher-quality output you don't have to babysit.
Changes
npx @veltiq/groundtruth setup.package.json+.claude-plugin/plugin.jsondescriptions refreshed; +keywords (self-healing,code-review,playwright).Ships as 0.6.1 so the new description + README reach the npm page.
🤖 Generated with Claude Code