Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →borghei/extended-thinking-architect
This skill should be used when the user asks to "decide reasoning effort", "set a thinking budget", "when to use extended thinking", "tune reasoning vs cost", or "should this task use a reasoning model".
Passed 17 of 22 test cases with the skill, and 16 of 22 without it.
1 fixed16 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Just draft it. Since our automated refactoring pipeline works on production repos where failures are costly, we plan to set the initial reasoning effort to maximum (high) for all initial task attempts. Is this the recommended strategy?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends starting at lower reasoning effort and escalating only upon failure. | Missed | Passed |
The instructions your model reads when the skill loads.
Category: Engineering Domain: AI Engineering
The Extended Thinking Architect skill helps you decide when an LLM task should spend a reasoning/thinking budget, how much (no-thinking / low / medium / high), and when the better move is a cheaper model with a sharper prompt instead. It turns task signals — error cost, ambiguity, step count, latency budget — into a deterministic recommendation with a rough cost multiplier, and allocates effort across the phases of an agent loop so you front-load reasoning where it pays and avoid runaway budgets.
Before recommending an effort level, confirm these inputs. If any is unknown or vague, ASK — do not assume:
--task-type and --verifiable)--error-cost and --latency-budget)--steps and --ambiguity)Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
# Recommend a reasoning effort level for a single task
python scripts/reasoning_budget_advisor.py --task-type code-debug \
--error-cost high --steps 4 --ambiguity low --latency-budget interactive
# A cheap, high-volume classification task — expect "cheaper model + better prompt"
python scripts/reasoning_budget_advisor.py --task-type classification \
--error-cost low --latency-budget realtime --json
# Allocate reasoning effort across the phases of an agent loop
python scripts/reasoning_loop_allocator.py --difficulty high --steps 8 \
--max-budget-multiplier 30
# Tight-latency loop — see effort capped per phase
python scripts/reasoning_loop_allocator.py --difficulty medium --steps 5 --realtime --json
test cases passed, vs 16 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.