@smartsoft001/pro-claude-plugins 0.7.0 → 0.8.0
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.
- package/package.json +1 -1
- package/plugins/flow/.claude-plugin/plugin.json +1 -1
- package/plugins/flow/skills/impl/SKILL.md +1 -1
- package/plugins/flow-external/.claude-plugin/plugin.json +1 -1
- package/plugins/flow-legacy/.claude-plugin/plugin.json +1 -1
- package/plugins/smart-pro/.claude-plugin/plugin.json +1 -1
package/package.json
CHANGED
|
@@ -915,7 +915,7 @@ When verification fails, delegate to appropriate fix agent:
|
|
|
915
915
|
19. **Capture before screenshots in background**: Launch `screenshot-reporter` agent with `run_in_background: true` BEFORE implementing UI changes to capture "before" state while implementation proceeds
|
|
916
916
|
20. **Capture after screenshots + post to Linear**: After implementation, launch `screenshot-reporter` agent to capture "after" screenshots, generate comparison report, post to Linear, and cleanup
|
|
917
917
|
21. **Document translations changes**: If `apps/web/public/translations.json` was modified, include a table with added/changed translation keys and their PL/EN values in the Implementation Report
|
|
918
|
-
21a. **⚠️ MANDATORY: Translation completeness before completion**: No hardcoded UI strings — every static label, heading, button, aria-label, meta/SEO text goes through a translation key. Before marking a subtask complete,
|
|
918
|
+
21a. **⚠️ MANDATORY: Translation completeness before completion**: No hardcoded UI strings — every static label, heading, button, aria-label, meta/SEO text goes through a translation key. Before marking a subtask complete, RUN the repo's translation check rather than eyeballing it — reading a diff does not prove a key resolves, and a raw `GROUP.key` rendered in the UI is one of the most visible defects a user can hit. Use `npm run check:translations` when the project defines it (museum projects wire it to `mobilems-check-translations`), otherwise fall back to whatever check the repo provides. Fix everything it reports: keys referenced in code but undefined, `pl`/`en` parity gaps, and — when a reference project is configured — groups that are incomplete against it. Only then mark the subtask done
|
|
919
919
|
22. **Capture screenshots in both modes**: Agent captures screenshots in BOTH normal mode and dark mode (high contrast) for complete visual documentation
|
|
920
920
|
23. **Ask before collecting feedback for agent evolution**: When user provides corrections or suggestions during implementation, **explicitly ask** if they want to create a Linear issue for the improvement. Only user-confirmed feedback (answered "Yes") should be processed at evolution checkpoints (Step 3g-evolve, Step 4a) via `shared-agent-evolver` agent.
|
|
921
921
|
24. **Never modify agent files directly during implementation**: The `shared-agent-evolver` agent files all proposals as Linear issues for manual review — it does NOT modify agent, command, or skill files directly.
|