database

Xano database catalog and content engine queries.

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

Steps

• listTables() - see state/lib/database.ts
• describeTable() - see state/lib/database.ts
• query() - see state/lib/database.ts

Eval

Actor: the exported functions in state/lib/database.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: list_tables_correctness
    kind: judge
    check: "The output of listTables() accurately reflects the tables present in the connected Xano database, as if manually verified against the Xano dashboard or direct database inspection."
  - name: describe_table_accuracy
    kind: judge
    check: "The output of describeTable() for a given table name correctly details its schema, including column names, data types, and primary key information, matching Xano's definition."
  - name: query_result_validity
    kind: judge
    check: "Executed queries via query() method return results that are consistent with direct execution against the Xano database or content engine, confirming data integrity and query correctness."
  - name: no_xano_api_errors
    kind: deterministic
    check: "The execution log (e.g., `state/log/pending-eval.ndjson` or application logs) must not contain any Xano API error codes or connection failures during database operations."

database - loader

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

Critical Rules

• content-engine is NOT Xano. It's raw SQL against rb-content-engine.fly.dev (Neon Postgres proxy). Don't confuse the two. The lib was split 2026-04-16 (state/index.md).
• Xano writes go through Metadata API: createTable, addField, deleteField, createApiGroup, createApi, updateApi. Xanoscript push is PUT /api/{id} (no editor).

Commands

| ui dashboard | state/skills/database/resources/ui.openui | |invoke: import from state/lib/database.ts - listTables(), describeTable(), query() |verify: listTables() against the target workspace before describing or querying |eval log: state/log/pending-eval.ndjson (manual eval - skill: "database")

OpenUI Resource

• Skill-owned OpenUI Lang resource: state/skills/database/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

• For raw SQL, use state/lib/content-engine.ts (split out 2026-04-16) - NOT database.ts and NOT xano.ts
• For Xano REST CRUD on records, use state/lib/xano.ts (read+write surface listed in state/index.md)
• Wiki page state/docs/xano/schema.md is the canonical table reference, copied from kernel snappy-database/tables.md

Self-Test

An agent reading this should correctly:

1. [ ] Route a "run this SQL" request to content-engine.ts, not database.ts
2. [ ] Use Metadata API for schema changes, REST for record CRUD
3. [ ] Read state/docs/xano/schema.md for table shapes

Self-report

If this loader fell short, append a line:

echo "[$(date -u +%FT%TZ)] database: <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)] database: <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.