Help us improve
Share bugs, ideas, or general feedback.
From claude-qae
End-to-end validation flows across plugins, integrations, and mobile. Proves the full jadecli ecosystem works with real data.
npx claudepluginhub jadecli/jadecli-kw-plugins --plugin claude-qaeHow this skill is triggered — by the user, by Claude, or both
Slash command
/claude-qae:e2e-validationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```
Runs real end-to-end loops across all nexus-agents feature families — research, synthesize, vote, plan, dev-pipeline, graph workflow, memory, audit — to validate claims against actual tool outputs. Use after releases, weekly, or when several behavior fixes have landed.
Performs Phase 4 quality gate for cli-web Python CLIs: 3-agent implementation review, 75-check checklist, pip package publishing, and read/write smoke tests.
Orchestrates post-implementation validation by delegating to /vibe, /post-mortem, /retro, /forge, and lifecycle skills. Produces a slice-validation roll-up mapping every acceptance criterion to a passing test.
Share bugs, ideas, or general feedback.
Developer runs `cc` in Ghostty
→ Claude Code session starts
→ OTel exports metrics + events
→ Collector forwards to Supabase
→ otel_events table populated
→ Telemetry dashboard shows session
→ Cost card shows real USD value
Assert: TelemetrySummary.totalSessions increments after session.
Developer pushes branch
→ PR created
→ claude-code-review.yml triggers
→ Multi-agent review posts findings
→ Developer addresses findings
→ CI green
→ Squash merge to main
→ Netlify redeploys
Assert: PR has Claude Code Review check run with inline comments.
claude plugin marketplace update jadecli-kw-plugins
→ claude plugin install data-engineering@jadecli-kw-plugins
→ /data-engineering:ast-index
→ ast-index/ populated with L1-L4 JSON
Assert: ast-index/L2-symbols.json has > 0 entries after skill invocation.
@Claude in Slack: "fix the failing test in auth.ts"
→ Claude Code web session created
→ Claude reads repo, identifies issue
→ Creates fix, runs tests
→ Posts status to Slack thread
→ "Create PR" button → PR opened
Assert: Slack thread contains "View Session" and "Create PR" buttons.
iOS Claude app: send task to Desktop
→ Desktop session spawns
→ Task executes against local files
→ Completion notification on phone
→ View results in claude.ai/code
Assert: Session appears in mobile app session list with "complete" status.
Telegram message to bot: "check deploy status"
→ Message arrives in running Claude Code session
→ Claude checks deploy, formats response
→ Reply sent back to Telegram
Assert: Reply appears in Telegram chat within 60 seconds.
Cron fires nightly at 2am
→ AST index rebuilds
→ Package audit runs
→ Results stored in Supabase
→ Dashboard reflects updated data
Assert: ast-index/L1-files.json modified_at within last 24 hours.
Linear sprint has issues with status
→ Monday 9am: WBR cron fires
→ Claude generates weekly business review
→ Report includes per-role metrics from OTel
→ Report posted/stored
Assert: WBR contains non-zero PRs and cost data for current week.
#!/bin/bash
set -euo pipefail
echo "=== E2E Validation ==="
# M1: Foundation
echo -n "M1 OTel pipeline... "
count=$(psql $SUPABASE_DB_URL -t -c "SELECT COUNT(*) FROM otel_events WHERE recorded_at > now() - INTERVAL '1 hour'")
[[ $count -gt 0 ]] && echo "PASS" || echo "FAIL"
# M7: Real data
echo -n "M7 Real sessions... "
sessions=$(psql $SUPABASE_DB_URL -t -c "SELECT COUNT(*) FROM otel_events WHERE event_name = 'claude_code.session.stop'")
[[ $sessions -gt 10 ]] && echo "PASS ($sessions)" || echo "FAIL ($sessions)"
# M8: Frontend
echo -n "M8 jadecli.com... "
status=$(curl -s -o /dev/null -w '%{http_code}' https://jadecli.com)
[[ $status -eq 200 ]] && echo "PASS" || echo "FAIL ($status)"
echo "=== Done ==="