Schema Sync Structured
Fix an agentic NL2SQL system after a database schema change. Inspect the schema contract, agent prompts, and vector database chunks for stale field references and update them.
Install
$ agentstack add skill-dsmmartin-skills-talk-agent-camp-2026-01-structured ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-dsmmartin-skills-talk-agent-camp-2026-01-structured) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Schema Sync — Structured
After a database schema migration, the following files and systems may contain stale field references.
Files to inspect
agentic_system/schema/github_events.yaml— machine-readable schema contractagentic_system/agents_core/nl2sql/prompts/system.md— NL2SQL agent system promptagentic_system/agents_core/rag/prompts/system.md— RAG agent system prompt- ChromaDB collections:
schema_docs,qa_examples— vector RAG chunks
What to look for
- Read the live ClickHouse schema:
SELECT name, type FROM system.columns WHERE table = 'github_events' ORDER BY position - Find references to old field names and SQL predicates in the files above.
- Update each file to use the new field names, types, and predicate syntax.
- For ChromaDB: find chunks with
stale: Truein their metadata and update their content.
Validation
Run python scripts/validate_schema.py to check whether the YAML contract matches the live schema.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: DSmmartin
- Source: DSmmartin/skillstalkagentcamp_2026
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.