Works with the AI Agents you already use
Flaky Check
The top flaky tests from your repo's recent pipeline runs. Free taste of the Pipeline Doctor suite.
Free
About this skill
One question, answered: which tests in this repo flip between pass and fail. This is the free taste of the Pipeline Doctor suite: the same machinery, one function.
-
The flaky list: test name, flip count over the window, and the runs where it flipped, worst first
-
The broken list, separated: tests failing almost every run are labeled broken, not flaky
-
Nothing else: no queue analysis, no cache audit, no cost estimates, no fix diffs. That is the paid Pipeline Doctor suite
-
No changes of any kind: no diffs, no commits
-
No queue, cache, artifact or cost analysis
-
No scheduled monitoring
- Ask which repo and which window (default: last 30 days, minimum 5 runs per test); the connection must already exist.
- Analyze outcomes per test across the window's runs.
- Deliver the two lists, counts first, one line per test with its flip runs.
- A repo with no history gets the explicit "no runs in this window" line, never a guessed list.
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 any payment.
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
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
Requires
Permissions
Allowed Hosts
Read-only analysis of recent pipeline run outcomes. Never changes anything.