Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/appreciative-reframing
Find positive deviants and reframe the problem from deficit-based to asset-based using Appreciative Inquiry.
Passed 14 of 23 test cases with the skill, and 10 of 23 without it.
and 13 more in the full report
11 fixed4 passed either way3 still failing7 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
What target count and acceptable range are allocated for paper-research tasks in the research budget ledger?
| Checked | Without skill | With skill |
|---|---|---|
| Specify target 5 | Missed | Passed |
| Specify range 4 to 6 | Missed | Passed |
The instructions your model reads when the skill loads.
Instead of "what's wrong?", ask "what's already working and why?"
| Base SOP | Target | ±10% Range |
|---|---|---|
| web-search | 25 | 22–28 |
| web-research | 10 | 9–11 |
| paper-overview | 25 | 22–28 |
| paper-search | 15 | 13–17 |
| paper-research | 5 | 4–6 |
<HARD-GATE>
| SOP | Done | Target | % |
|-----|------|--------|---|
| web-search | ? | 25 | ? |
| web-research | ? | 10 | ? |
| paper-overview | ? | 25 | ? |
| paper-search | ? | 15 | ? |
| paper-research | ? | 5 | ? |
Budget Gate: OPEN/CLOSED (>=80% required to exit)
</HARD-GATE>
Import: web-search, web-research, paper-overview, paper-search, paper-research Subagent: appreciative-discovery, reformulation-synthesis
Find positive deviants (cases that succeed despite the general problem), identify their enabling conditions, reframe the problem as "how to create more of what already works."
test cases passed, vs 10 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.