skill-openqa-cn-codexqa-catalog · by Install
$ agentstack add skill-openqa-cn-codexqa-catalog ✓ 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-openqa-cn-codexqa-catalog) 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
Catalog data-build slot
Vendor-neutral catalog-domain slot. Drop-in under pack slots/ (already discovered; no extra slot_roots / marketplace path). slot.yaml is the scene config. More specific entities (limited / credit) are listed before generic product. Executors talk to DATA_BUILD_API_BASE (default local mock on port 8765). The case pipeline binds these executors from slot.yaml without an LLM when the match is unique.
Single-step routing
| User intent | Executor | |---|---| | Standard catalog product | scripts/executors/create_product.ts | | Limited catalog product | scripts/executors/create_limited_product.ts | | Catalog order | scripts/executors/create_order.ts | | Account credit on a product / user | scripts/executors/setup_account_credit.ts |
Do not invent productId / userId when the user already supplied them. Optional fields use executor defaults.
node scripts/executors/create_product.ts --json '{"name":"Northwind Standard","city":"demo-city"}'Scene orchestration
credit-ready-product
- Create catalog product (or reuse
productId) - Enroll the product and user in account credit
- Return
productId, enrollment result,creditBalance
bookable-order
- Ensure a product exists
- Create an order for
userId+productId - Return
productId,orderId,status
Pass upstream data fields into the next executor. Do not skip a later scene step.
Guardrails
- Start
node ../mock_server.tsif no enterprise gateway is configured - Do not invent
productId/userId/orderId - Defaults:
city=demo-city,validHours=4,fulfillOn=today+2days,quantity=1,credits=1000 - See [references/tools-guide.md](references/tools-guide.md) and [../SLOTSPEC.md](../SLOTSPEC.md)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: openqa-cn
- Source: openqa-cn/codexqa
- License: Apache-2.0
- Homepage: https://openqa.cn
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.