Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
SkillScore95Maintained
Automatic
◆QA & Test Engineering pack
Last verified 9/29/2026
What it changes
Passed 21 of 22 test cases with the skill, and 18 of 22 without it.
Without skill82%
With skill95%
Checks it passed that the model alone missed
Uses t.Run within a table-driven test structure.
Reports scenarios covered in the response summary.
Reports test files changed in the response summary.
and 3 more in the full report
4 fixed17 passed either way0 still failing1 broke
Pass-rate lift
+14 pp
Tokens
-12%
Agent turns
0%
Response time
-25%
Model gemini-3.6-flashMeasured 9/29/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
I'm building an interactive terminal app in Go using Bubbletea and need test coverage for key press state updates and full view rendering. Could you add the appropriate unit and snapshot tests? When you're done, provide a structured summary listing the test files altered, scenario cases addressed, CLI execution commands run, golden files revised, and any external integration scope skipped.
What was checked, without and with the skill
Checked
Without skill
With skill
Calls Update() directly on the Bubbletea model for state transition unit tests.
Passed
Passed
Uses t.Run within a table-driven test structure.
Missed
Passed
Reports skipped integration scope in the final output summary.
Passed
Passed
case-01 · gemini-3.6-flash · 9/29/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md42 lines2 files
Activation Contract
Load this skill when writing or reviewing Go tests, adding coverage, testing Bubbletea/TUI flows, using teatest, or updating golden files.
Hard Rules
Prefer table-driven tests for multiple cases; use t.Run(tt.name, ...).
Test behavior and state transitions, not implementation trivia.
Use t.TempDir() for filesystem tests; never rely on a real home directory.
Keep integration tests skippable with testing.Short() when they run external commands or slow flows.
For Bubbletea, test Model.Update() directly for state changes; use teatest only for interactive flows.
Golden files must be deterministic; update only through the repo's -update path and rerun tests without -update.
Use small mocks/interfaces around system or command execution boundaries.
Decision Gates
Target
Test pattern
Pure function or parser
Table-driven unit test.
Error behavior
Explicit success and failure cases.
File operations
t.TempDir() plus focused assertions.
TUI state transition
Direct Model.Update() call with tea.Msg.
Full TUI interaction
teatest.NewTestModel().
Rendered output
Golden file test.
Real external command
Integration test; skip in -short.
Execution Steps
Identify behavior under test and the smallest public boundary that proves it.
Choose the test pattern from the decision gate.
Name cases by scenario, not input mechanics.
Assert outputs, errors, state, and side effects explicitly.
Run the narrow package test first, then the relevant broader suite.
For golden updates: run with -update, inspect diff, then rerun without -update.
Output Contract
Report test files changed, scenarios covered, commands executed, golden files updated, and any skipped integration scope.