More screenshots
Works with the AI Agents you already use
AI Tool Integration QA Evidence Pack
Turn an AI integration action catalog and test log into a coverage matrix, blocking gaps, retest queue and hash-bound handoff packet—locally.
$7
AI Tool Integration QA Evidence Pack
Example session with this skill installed
Using the included example actions.json and results.jsonl, build a local QA evidence packet. Show which catalog actions block the handoff and which need retesting. Do not call any live integration.
- Read your context and instructions
- Compiled the ai tool integration
- Generated the data export
Example: included local sample
The supplied four-action catalog produced status
BLOCK. The packet is an evidence summary of the provided files; it did not execute any integration or certify deployment.
| Metric | Result |
|---|---|
| Catalog actions | 4 |
| Passed | 2 |
| Failed | 1 |
| Skipped | 1 |
| Untested | 0 |
| Retest candidates | 1 |
The blocking action is contacts.create, reported as FAIL with error code HTTP_422 and incomplete evidence at screens/create-422.png. contacts.list and contacts.update passed in the supplied result log. Optional contacts.archive was skipped; it appears as a review note rather than a passed action.
The generated action-matrix.csv contains a row for each catalog action, retest.jsonl isolates the failed action, and TEST_EVIDENCE.md provides the handoff summary. result.json is the first file to read for status; evidence-receipt.json binds the packet inputs and outputs by SHA-256.
Next steps: inspect the supplied failure evidence for contacts.create, fix the underlying integration outside this package, rerun the authorized test, then rebuild the packet into a new empty directory. Use the local verify command when transferring the packet.
create-422.png
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
This downloadable local package turns authorized JSON or JSONL evidence into a reproducible review packet. It includes an installable Python CLI, a local stdio MCP adapter and a companion Agent Skill. One run creates result.json, action-matrix.csv, retest.jsonl, TEST_EVIDENCE.md and evidence-receipt.json with SHA-256 bindings.
The fixed core rejects unsafe paths and malformed JSON, never overwrites an existing packet, and escapes formula-active CSV cells. Processing stays local: no API key, login, upload, telemetry or live provider action is included.
Best for connector teams and contractors preparing client handoff evidence or release owners identifying untested and conflicting actions. Requires Windows 11, Python 3.11–3.14 and local files in the documented schemas. The optional MCP adapter uses mcp==2.2.0.
Limitations: this package does not call or test integrations. It records evidence references but does not open or copy them. READY means the supplied packet is complete under the fixed rules, not production certification.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
Requires local tool-integration-qa CLI access. Cannot perform live service calls or production certification. Needs valid JSON/JSONL input files.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
- Software
Python
Permissions
Runs a local Python CLI. Reads only user-selected action catalog and result files, then writes a new evidence packet directory. No network access is required.