When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.
SkillScore73Maintained
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆DevOps & SRE pack
Last verified 8/14/2026
What it changes
Passed 16 of 22 test cases with the skill, and 12 of 22 without it.
Without skill55%
With skill73%
Checks it passed that the model alone missed
Explicitly states the base estimate with confidence rating.
Applies a buffer multiplier between 1.5x and 2x to accommodate replication log bursts.
Determines the ruin check status as pass or redesign needed based on irreversible state loss.
and 5 more in the full report
6 fixed10 passed either way4 still failing2 broke
Pass-rate lift
+18 pp
Tokens
-22%
Agent turns
0%
Response time
-42%
Model gemini-3.6-flashMeasured 8/14/2026v116 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
We are sizing backhaul capacity for a rural cell tower array covering seasonal tourist events. Baseline bandwidth is 2 Gbps (high confidence), and temporary load spikes are bounded by tower radio capacity. Over-provisioning fiber carries high monthly lease fees while brief congestion lowers streaming quality without permanent data loss. Evaluate capacity allocation and format the output with base demand, uncertainty drivers, breach impact, buffer multiplier, final allocation, ruin check, cost comparison, and monitoring rules.
What was checked, without and with the skill
Checked
Without skill
With skill
Applies a conservative buffer multiplier between 1.2x and 1.5x due to high base confidence and recoverable non-ruinous breach consequences.
Missed
Passed
case-06 · 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.md50 linessingle file
Margin of Safety
Core rule: commit a buffered number when residual uncertainty plus breach cost can cause ruin or costly failure. Margin covers estimation error; it is not free slack for laziness.
When to Use
Capacity, timeouts, pool sizes, queue depths, storage, or SLA numbers under load uncertainty
Timeline or budget commitments where underestimation is costly
Architecture headroom when scaling or recovery is slow
Any public or production commitment where being wrong has asymmetric downside
When NOT to Use
Breach is detected immediately and fixed near-zero cost (fast auto-scale, live-tunable limit)—static fat buffers waste resources
cost(buffer) > P(breach) × cost(breach)—right-size or measure instead of maxing out
Uncertainty is eliminable by measurement or lookup—get the real number first
Stopping-criterion / search budget problems—use bounded rationality, not padding
Fully known parameters and low stakes where edge optimization is the goal
Procedure
Point estimate without padding. State the base requirement in explicit units (RPS, weeks, GB, ms) and confidence (high / medium / low).
Uncertainty and breach cost. List drivers (spike, growth, unknowns, dependency variance). State what fails if undershot: outage, missed launch, data loss, reputation—and whether failure is recoverable or ruinous.
Size the buffer. Multiply or add margin to residual uncertainty and stakes—not to vanity. Typical bands (adjust with evidence):
Well-known, low consequence: ~1.2–1.5×
Familiar with unknowns / reversible: ~1.5–2×
New domain, external deps, SLA, irreversible: ~2–3×
Cap or cut when buffer cost exceeds expected breach cost.
Ruin constraint. If a breach can cause irreversible harm, size so the worst plausible miss still stays above the failure threshold; if that buffer is unaffordable, change the design (shed load, degrade, stage) rather than pretend precision.
Strongest countercase. Challenge both under-buffering ("we will scale later") and over-buffering (idle cost, complexity). Prefer measure-then-trim when history exists.
Commit and monitor. Publish the buffered commitment, the failure threshold, and the metric that would prove margin excessive or thin. Stop when the number is set and monitorable.
Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.