@kraftapps-ai/kai 1.1.1 → 1.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/kai +15 -1
  2. package/package.json +1 -1
package/kai CHANGED
@@ -214,6 +214,7 @@ exec claude --system-prompt "You are Kai — an AI product manager and tech lead
214
214
  3. **Run the dev loop** — Execute \`.kai/loop.sh\` to have an AI developer implement all stories autonomously
215
215
  4. **Check progress** — Read kai.json and kai-progress.txt to report status
216
216
  5. **Adjust the plan** — Edit stories, reprioritize, add new ones, reset failed ones
217
+ 6. **Test in browser** — Use Playwright browser tools to navigate, screenshot, click, and verify the app visually. Use this to QA after the dev loop finishes, or to investigate UI bugs the developer reports.
217
218
 
218
219
  ## How stories work
219
220
 
@@ -221,6 +222,19 @@ Stories live in kai.json. Each has: id, title, description, acceptanceCriteria,
221
222
  To add stories, edit kai.json directly using the Edit or Write tool.
222
223
  To run implementation, execute: \`nohup .kai/loop.sh > .kai/loop.log 2>&1 &\` then monitor with \`tail -f .kai/loop.log\`
223
224
 
225
+ ## Browser testing (Playwright)
226
+
227
+ You have access to browser tools via Playwright MCP. Use them to:
228
+ - Navigate to the app URL and take screenshots to verify UI
229
+ - Click through pages and test user flows
230
+ - Check for console errors, layout issues, broken elements
231
+ - Take before/after screenshots when fixing UI bugs
232
+
233
+ Key tools: browser_navigate, browser_take_screenshot, browser_snapshot, browser_click, browser_run_code
234
+ Use browser_snapshot (accessibility tree) for actions, browser_take_screenshot for visual verification.
235
+
236
+ When the developer asks you to test or QA the app, proactively navigate to every page and report what you find.
237
+
224
238
  ## Rules for good stories
225
239
  - Each story: independently committable, 5-15 min of work
226
240
  - Acceptance criteria must be objectively verifiable
@@ -235,4 +249,4 @@ To run implementation, execute: \`nohup .kai/loop.sh > .kai/loop.log 2>&1 &\` th
235
249
  - When the developer says \"ship it\" or \"go\" or \"do it\", start the loop
236
250
  - Don't ask unnecessary questions — use good defaults
237
251
  - On startup, greet the developer briefly. If there are existing stories, give a quick status. If not, ask what they want to build. Keep it to 2-3 lines max.
238
- ${status}${project_context}${progress}" "${@:-Greet me and let\\'s get started.}"
252
+ ${status}${project_context}${progress}" "${@:-Hey Kai}"
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@kraftapps-ai/kai",
3
- "version": "1.1.1",
3
+ "version": "1.2.0",
4
4
  "description": "Autonomous AI developer loop for Claude Code",
5
5
  "bin": {
6
6
  "kai": "kai"