AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Layerkit Discover Data Layer

skill-hariharapanigrahy-layerkit-layerkit-discover-data-layer · by hariharapanigrahy

Read customer code for domain events/fields; deny secrets; emit domain_spec proposal with source:code.

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-hariharapanigrahy-layerkit-layerkit-discover-data-layer

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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 Used
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets Used
  • 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-hariharapanigrahy-layerkit-layerkit-discover-data-layer)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Layerkit Discover Data Layer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

layerkit-discover-data-layer

Analyze the customer data layer (not vendor docs). Output is a domain_spec proposal that seeds Q3–Q4.

Protocol

  1. List candidate files with narrow deterministic tools (rg --files, exact symbol search), then read source yourself. Do not use deterministic heuristics to infer business domains.
  2. Scan TS/JS/Java (and similar) as the AI agent:
  • event / intent type names
  • analytics or vendor emit call sites
  • DTOs / domain models for user, cart, purchase
  1. Deny-paths (never open or paste):
  • .env, .env.*
  • **/*secret*, **/*credential*
  • **/id_rsa*, **/*.pem, **/keystore*, **/*.p12
  1. Prefer in-repo OpenAPI, JSON Schema, or redacted curl for field hints (source: openapi|curl|code).
  2. Draft domain_spec proposal shape:
{
  "schemaVersion": 2,
  "kind": "domain_spec",
  "id": "domain-spec--v1",
  "summary": "Customer domain intents/fields from code",
  "authoredBy": "agent",
  "status": "draft",
  "createdAt": "",
  "sources": [
    { "title": "", "url": "file://", "excerpt": "" }
  ],
  "payload": {
    "id": "",
    "version": "0.1.0",
    "description": "...",
    "intents": [{ "id": "purchase", "description": "..." }],
    "fields": [
      { "path": "user.email", "type": "string", "description": "...", "required": false }
    ]
  },
  "maker": { "type": "agent", "id": "" }
}
  1. Bootstrap questionnaire Q3 (intents) / Q4 (fields) only when code supports them; residual gaps stay unanswered (source: unanswered).
  2. Persist:
layerkit proposal validate ./domain-spec.json
layerkit memory append --type research --title "domain discovery" --vendor general --body-file ./discovery-note.md
  1. Next: layerkit-research-vendor (per target vendor).

Multi-vendor packages

When the client package already integrates multiple vendors (adapters, mappers, gateways, destinations):

  1. Inventory sibling vendor paths with file:// evidence: adapters, mappers, registry/router wire-up, privacy hooks, and sibling tests.
  2. Name the existing path a new vendor should follow (module root, registry entry, test layout) — do not invent a parallel package tree.
  3. Prefer extending the same module root and registry pattern used by siblings; residual only when no sibling path exists.
  4. Record which vendors already ship so research/design can clone the proven structure for the next vendor.

Example note shape:

# multi-vendor inventory
- vendors_present: [acme, beacon]
- adapter_root: src/vendors/*
- registry: src/registry.ts
- sibling_reference: file://src/vendors/acme/adapter.ts
- test_sibling: file://tests/vendors/acme.test.ts
- new_vendor_path: follow sibling under src/vendors// + registry wire + clone tests

Forbidden

  • Inventing domain fields not present in code or customer-accepted docs
  • Reading secret/credential files
  • Writing vendor_map / processor payloads here
  • Inventing a parallel facade/module tree when sibling vendor adapters already exist

Success criteria

  • [ ] Every sources[] entry is file:// or customer-accepted URL with real excerpt
  • [ ] No deny-path content in proposal or memory
  • [ ] layerkit proposal validate has zero errors (warnings OK)
  • [ ] Residual gaps listed explicitly; none silently filled
  • [ ] Multi-vendor packages list sibling vendor paths and the path a new integration must follow

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.