- Home
- Skills
- Workflow Automation
- π Automation Acceptance Replay Harness
More screenshots
Works with the AI Agents you already use
π Automation Acceptance Replay Harness
Replay automation traces against explicit rules for required steps, order, retries, approvals, idempotency, external side effects, duration, and terminal success.
$19
π Automation Acceptance Replay Harness
Example session with this skill installed
Contract: required ingest,classify,approve,send,record; email_sent requires idempotency and prior human_review; max retries 2.
Trace: email_sent succeeded twice with side_effect_key email:lead-99; first send had no idempotency key; no approved review event; classification failed; terminal completed.
- Read your context and instructions
- Compiled the automation acceptance replay
Recommendation: REJECT
Critical: duplicate successful email side effect.
Critical: missing idempotency key and human approval.
Critical: terminal completed after required classification failed.
High: required approval and record steps missing; retry limit exceeded.
Connects securely to your tools. The creator never sees your data.
About this skill
Automation Acceptance Replay Harness tests exported workflow or agent execution traces against a declared operational acceptance contract. Define required and ordered steps, allowed external side effects, idempotency requirements, actions that need prior human approval, retry limits, duration limits, and accepted terminal states. The included deterministic local helper then finds missing or out-of-order steps, duplicate successful effects, absent idempotency keys, unapproved actions, missing approval, retry overflow, duration breaches, and false-success executions. It returns findings, per-execution dispositions, a JSON recommendation, and a client-ready review memo without executing the workflow or accessing connectors.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.
The result is limited to events represented in the supplied trace; missing logging can resemble missing execution. A clean fixture does not prove that every input, connector failure, race condition, or replay scenario is covered. External provider state must be checked separately when acceptance depends on whether an email, write, charge, or deletion actually occurred.
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 24 days ago
Permissions
File Scopes
The helper reads one contract and one trace, then writes local findings and summaries. It never executes the automation, calls a connector, or verifies external provider state.