xano-dashboard

Browser-driven Xano admin operations.

Ported from kernel snappy-xano-dashboard in Phase 0.5. See state/lib/xano-dashboard.ts for the full API surface.

Steps

• openDashboard() - see state/lib/xano-dashboard.ts
• snapshotDashboard() - see state/lib/xano-dashboard.ts
• navigateTo() - see state/lib/xano-dashboard.ts
• runApiTest() - see state/lib/xano-dashboard.ts
• getRequestLogs() - see state/lib/xano-dashboard.ts
• closeDashboard() - see state/lib/xano-dashboard.ts

Eval

Actor: the exported functions in state/lib/xano-dashboard.ts. Auditor: none wired yet - eval is manual (Robert review). File a state/log/pending-eval.ndjson row on each run.

Score convention:

Gotchas

via the Phase 0.5 driver. Only these rewrites were applied: already in state/lib/)

1. realpathSync(process.argv[1]) CLI guard wrapped in try/catch

• See the kernel SKILL.md for the original long-form guidance if you need it

(read-only reference at the kernel path above).

Graduation

This skill is prose. Graduate by defining a deterministic auditor and flipping eval: auto.

Rubric

criteria:
  - name: dashboard_opened_successfully
    kind: judge
    check: "The `openDashboard()` function should successfully open the Xano dashboard in the browser without errors."
  - name: correct_navigation
    kind: judge
    check: "The `navigateTo()` function should correctly navigate to the specified Xano dashboard section or page."
  - name: api_test_execution_status
    kind: judge
    check: "The `runApiTest()` function should execute the API test and return a clear indication of its success or failure."
  - name: request_logs_content
    kind: judge
    check: "The `getRequestLogs()` function should retrieve and present relevant request logs from Xano, reflecting recent activity."

xano-dashboard - loader

Per-turn rules for the xano-dashboard skill. Full reference: state/skills/xano-dashboard/SKILL.md. Do not skip these.

Critical Rules

• ALWAYS prefer the Xano METADATA API (state/lib/xano.ts) over browser automation when the operation is available there - browser-driven is the fallback for things only the dashboard exposes
• Serialize browser calls - no parallel automation against a single dashboard session (memory: no_parallel_browser_writes)
• ALWAYS pair openDashboard() with closeDashboard() - leaked sessions accumulate and break subsequent runs
• For schema mutations, ROUTE to the typed state/lib/xano.ts (createTable, addField, createApi, etc.) - clicking through the dashboard for ops the metadata API supports is wasted budget and harder to verify
• Eval is manual (Robert review) - every run files to state/log/pending-eval.ndjson

Commands

| ui dashboard | state/skills/xano-dashboard/resources/ui.openui | |library: state/lib/xano-dashboard.ts - openDashboard(), snapshotDashboard(), navigateTo(), runApiTest(), getRequestLogs(), closeDashboard() |metadata API: state/lib/xano.ts (preferred for schema/API ops) |eval log: state/log/pending-eval.ndjson (manual)

OpenUI Resource

• Skill-owned OpenUI Lang resource: state/skills/xano-dashboard/resources/ui.openui. Read it before rendering or editing this skill's generated component surface.
• Treat this resource as a first-class artifact of the skill, not a generic chat response. Improve it when the skill's user-facing output needs to become richer.
• System resources compose OpenUI primitives and inherit SnappyChat tokens. Use ui_contract: branded in SKILL.md only for deliberate platform or client visuals.

Known Pitfalls

• Reaching for the dashboard for a schema change that state/lib/xano.ts already supports duplicates infra and slows the run
• Forgetting closeDashboard() leaves the session resident and the next run collides

Self-Test

An agent reading this should correctly:

1. [ ] Check state/lib/xano.ts for a metadata-API path before opening the dashboard?
2. [ ] Serialize all browser calls against a single dashboard session?
3. [ ] Always close the dashboard at the end of the run?

Self-report

If this loader fell short, append a line:

echo "[$(date -u +%FT%TZ)] xano-dashboard: <what was missing>" >> state/log/loader-feedback.log

<!-- kernel-ok: historical attribution for the PID-loader pattern. -->

Self-correcting loader (PID feedback)

This is the rule that makes loaders learn. Ported from snappy-kernel, where it demonstrably worked: the snappy-dom-cartographer skill mapped Skool admin UI once, every later ship-agent inherited the full map for free.

Before you finish, do two things:

1. Fix gaps (P - proportional). MANDATORY. If this loader didn't cover your case - if you had to read another file, run an undocumented command, work around a wrong selector, or discover a quirk - you MUST attempt an Edit to this AGENTS.md before you log.

• Default action: edit this file. Surgical. Add the missing line, table

row, or code example where it belongs. No restructuring.

• Only LOGGED is allowed when: the fix needs >10 lines, spans multiple

files, or requires a structural rewrite. In that case the state/regen/drain.sh queue picks it up asynchronously.

• "I didn't have time" / "it's minor" / "the next agent will figure it out"

are NOT valid reasons. Minor gaps compound - that's the whole point of this loop.

• Concrete example of a valid P-fix: discover agent-browser screenshot

takes path positionally not as --output <path>. One line in a table. Edit it in. Do not just log it.

• The goal: the next agent never has to leave the loader.

2. Log the result.

echo "[$(date -u +%FT%TZ)] xano-dashboard: <what was missing or fixed> [FIXED|LOGGED]" >> state/log/loader-feedback.log

• FIXED = you patched this loader inline (P-fix).
• LOGGED = too large for inline; the PostToolUse enqueue + Stop-hook drain

will rewrite the loader from scratch on next session-end.

Do not skip this. Every agent run must leave the system better than it found it. The loader is the setpoint; you are the sensor; the gap is the error signal; closing the gap is the correction.