mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-01 19:25:10 +02:00
Garry Tan
76803d789a
Adds comprehensive eval infrastructure: - Tier 1 (free): 13 new static tests — cross-skill path consistency, QA structure validation, greptile format, planted-bug fixture validation - Tier 2 (Agent SDK E2E): /qa quick, /review with pre-built git repo, 3 planted-bug outcome evals (static, SPA, checkout — each with 5 bugs) - Tier 3 (LLM judge): QA workflow quality, health rubric clarity, cross-skill consistency, baseline score pinning New fixtures: 3 HTML pages with 15 total planted bugs, ground truth JSON, review-eval-vuln.rb, eval-baselines.json. Shared llm-judge.ts helper (DRY). Unified EVALS=1 flag replaces SKILL_E2E + ANTHROPIC_API_KEY checks. `bun run test:evals` runs everything that costs money (~$4/run). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
46 lines
1.7 KiB
JSON
46 lines
1.7 KiB
JSON
{
|
|
"name": "gstack",
|
|
"version": "0.3.3",
|
|
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
|
|
"license": "MIT",
|
|
"type": "module",
|
|
"bin": {
|
|
"browse": "./browse/dist/browse"
|
|
},
|
|
"scripts": {
|
|
"build": "bun run gen:skill-docs && bun build --compile browse/src/cli.ts --outfile browse/dist/browse && bun build --compile browse/src/find-browse.ts --outfile browse/dist/find-browse && git rev-parse HEAD > browse/dist/.version && rm -f .*.bun-build",
|
|
"gen:skill-docs": "bun run scripts/gen-skill-docs.ts",
|
|
"dev": "bun run browse/src/cli.ts",
|
|
"server": "bun run browse/src/server.ts",
|
|
"test": "bun test browse/test/ test/ --ignore test/skill-e2e.test.ts --ignore test/skill-llm-eval.test.ts",
|
|
"test:evals": "EVALS=1 bun test test/skill-llm-eval.test.ts test/skill-e2e.test.ts",
|
|
"test:eval": "EVALS=1 bun test test/skill-llm-eval.test.ts",
|
|
"test:e2e": "EVALS=1 bun test test/skill-e2e.test.ts",
|
|
"test:all": "bun test browse/test/ test/ --ignore test/skill-e2e.test.ts --ignore test/skill-llm-eval.test.ts && EVALS=1 bun test test/skill-e2e.test.ts test/skill-llm-eval.test.ts",
|
|
"skill:check": "bun run scripts/skill-check.ts",
|
|
"dev:skill": "bun run scripts/dev-skill.ts",
|
|
"start": "bun run browse/src/server.ts"
|
|
},
|
|
"dependencies": {
|
|
"playwright": "^1.58.2",
|
|
"diff": "^7.0.0"
|
|
},
|
|
"engines": {
|
|
"bun": ">=1.0.0"
|
|
},
|
|
"keywords": [
|
|
"browser",
|
|
"automation",
|
|
"playwright",
|
|
"headless",
|
|
"cli",
|
|
"claude",
|
|
"ai-agent",
|
|
"devtools"
|
|
],
|
|
"devDependencies": {
|
|
"@anthropic-ai/claude-agent-sdk": "^0.2.75",
|
|
"@anthropic-ai/sdk": "^0.78.0"
|
|
}
|
|
}
|