Use when the reflex is to add a feature, layer, or process. Prefer removing harmful or nonessential elements first, with an irreversibility guard before deletion.
SkillScore82Maintained
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Product Management pack
Last verified 8/14/2026
What it changes
Passed 18 of 22 test cases with the skill, and 9 of 22 without it.
Without skill41%
With skill82%
Checks it passed that the model alone missed
The response keeps essential base dependencies on the do-not-touch list
The response lists core user-initiated location services under do-not-touch
The response keeps core safety and unit test suites on the do-not-touch list
and 7 more in the full report
10 fixed8 passed either way3 still failing1 broke
Pass-rate lift
+41 pp
Tokens
-20%
Agent turns
0%
Response time
-50%
Model gemini-3.6-flashMeasured 8/14/2026v118 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
CI runs take 45 minutes. The team proposes buying extra compute nodes. Analysis shows 20 minutes are spent running a redundant duplicate end-to-end suite that mirrors unit coverage. Format the resolution plan.
What was checked, without and with the skill
Checked
Without skill
With skill
The response prioritizes eliminating redundant test suite executions over adding compute hardware
Passed
Passed
The response keeps core safety and unit test suites on the do-not-touch list
Missed
Passed
case-09 · gemini-3.6-flash · 8/14/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md46 linessingle file
Via Negativa
Improve by subtraction before addition. Prefer removing harm, waste, and nonessential complexity; add only when a demonstrated need remains after removal candidates are exhausted.
When to Use
About to add a feature, abstraction, dependency, process, or control to fix a problem.
Simplifying a system or workflow where complexity is the tax.
Prioritizing by deciding what not to keep, build, or maintain.
Performance or reliability work where eliminating a bad path beats bolting on mitigation.
A demonstrated requirement that cannot be met by removal or simplification.
Aesthetic minimalism without evidence of non-use or net harm.
Irreversible deletion without a rollback path when impact is unknown.
Procedure
Pause the add reflex. State the goal and the proposed addition in one line.
Ask the subtraction question first. List what could be removed or stopped to achieve the same goal with less surface area.
Catalog candidates with evidence. Prefer unused, redundant, high-cost/low-value, or harmful elements. Require usage, call-graph, metrics, or experiment evidence — not taste.
Apply the irreversibility guard. Classify reversible vs hard-to-restore; identify dependents; refuse deleting unproven mystery guards. Plan staged removal or flag when risk is non-trivial.
Remove the safest high-value candidate first. Subtract, monitor, and verify absence of needed behavior before the next removal.
Add only if the goal still fails. If subtraction cannot meet the need, add the minimum change and record why removal was insufficient.
Stop when the goal is met by absence, or remaining candidates fail the irreversibility/evidence bar and a minimal addition is justified.
Stop condition: Goal achieved via removal, or residual need documented after evidence-backed subtraction failed.