mother-in-law
Skill14 starsChanged 55 days agoMITView on GitHub
Test a changed user interaction for realistic sequence failures such as double submission, stale responses, navigation, and recovery; use for interaction QA rather than general code review.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- benchmarks/AGENTS.mdAGENTS.md
- con-artistSkill
- exorcistSkill
- fridaySkill
- hostage-negotiatorSkill
- landlordSkill
- necromancerSkill
- receiptSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Read supplied requirements, interaction code, native tests, existing test support and applicable project instructions together when …
- Distinctive: line 13
Use controlled responses/clocks, isolated cases, bounded waits, and owned-operation cleanup—never sleeps or production actions.
- Distinctive: line 21
If only final ownership is required, leave unspecified intermediate display as observation.
- Distinctive: line 39
Never change production to fit a helper.
- Distinctive: line 42
Rendered UI: read references/browser.md.
- Distinctive: line 46
Do not add separate evidence files when captured check output already proves them.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Mother-in-law
And what happens if I click it twice?
Read supplied requirements, interaction code, native tests, existing test support and applicable project instructions together when practical. Discover missing paths, not another inventory before known-file reads. Use controlled responses/clocks, isolated cases, bounded waits, and owned-operation cleanup—never sleeps or production actions. Preserve user files and scope.
Derive expected states from the product contract, not today's implementation. Separate final ownership from interval requirements. “Retain while loading” or “until the latest completes” applies throughout that interval: assert the retained value after relevant intervening completions while the latest remains pending, not only at request entry. Printing an observation is not a regression assertion. If only final ownership is required, leave unspecified intermediate display as observation; seeing an older response does not require a valid fix to display it. A regression must reject the fault without rejecting another permitted path.
Choose the requested deliverable; load only its relevant support:
- Project regression: extend and run the native test directly, not a disposable probe first. Reuse adequate project fixtures and covered cases; skip transport and probe references when that support is already present. Only when additional Python request-control support is needed, read the native-test interface and copiable transport together. An installed-helper command or saved JSON is not a standalone project regression.
- Captured observations without a project-test deliverable: the optional
component probe fits a zero-argument constructor,
async
run(query, fetch)and direct payload state. An opt-in mode checks required display retention through normal/reversed overlap; repeated identical overlapping queries still require project checks. Existing adequate runners take precedence. Never change production to fit a helper. Native-project delivery does not need this reference. - Rendered UI: read references/browser.md.
Return the tested sequence, expected/observed state, tested layer, and complete bounded command. Stop after the nearest normal and targeted adversarial cases. Do not add separate evidence files when captured check output already proves them. Browser unavailability leaves browser QA incomplete. QA does not authorize a fix.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.