Frozen, deterministic decision (no LLM): maps zone_type, day, hour, is_public_holiday, has_resident_permit to one of prohibited, no_parking_street_cleaning, pay_and_display_2h, free, permit_required.
SkillScore78Maintained
Automatic
◆Personal Assistant pack
Last verified 8/4/2026
What it changes
Passed 16 of 21 test cases with the skill, and 5 of 21 without it.
Without skill26%
With skill78%
Checks it passed that the model alone missed
Passes None for the day parameter.
Passes None for the zone_type feature.
Passes None for the has_resident_permit feature.
and 10 more in the full report
12 fixed6 passed either way5 still failing0 broke
Pass-rate lift
+52 pp
Tokens
-29%
Agent turns
0%
Response time
-58%
Model gemini-3.6-flashMeasured 8/4/2026v118 of 23 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
What exact key names must be present in the dictionary passed to the parking decision function?
What was checked, without and with the skill
Checked
Without skill
With skill
Lists zone_type, day, hour, is_public_holiday, and has_resident_permit as key names.
Missed
Passed
case-17 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md30 lines6 filesincludes scripts
can_i_park — skill (tempered by temper-skills)
You are an assistant.
The decision is frozen. Do not re-derive it from prose or your own judgment — the routing logic now lives in a deterministic decision tree (can_i_park.can_i_park, zero LLM calls, reviewed and version-controlled). Your job is the part the tree cannot do: turn the request into structured features, call the tree, and phrase its verdict.
How to answer
Extract these structured features from the request:
zone_type
day
hour
is_public_holiday
has_resident_permit
Call the decision tree and treat its result as authoritative (bundled at scripts/can_i_park.py):
Relay verdict to the user. Do not override it. If a feature can't be extracted, pass it as None — the tree is built to fall through safely.
Gray zones to surface
The tree flags these as underdetermined — mention the caveat when the answer touches them:
(n2) Suspended on public holidays (is_public_holiday true falls through). Window is the clock hours 11 and 12 (>=11 and <13).
(n3) The 2-hour cap can't be enforced by the tree alone; a downstream system must track elapsed duration.
Generated by temper-skills from the original skill · 2026-07-01T12:45:19Z · model: claude-sonnet-4-6 via temper-skills. The decision logic is now testable (temper-skills validate) and evolvable (temper-skills incremental) — regenerate this skill when the tree changes.