Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/constraint-classification
Classify constraints into hard constraints, soft constraints, and assumptions.
Passed 17 of 21 test cases with the skill, and 8 of 21 without it.
and 11 more in the full report
11 fixed7 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
For Orion Mobile App, categorize these 4 items: 1) iOS App Store guidelines, 2) 100k user launch target, 3) Unverified belief that Firebase handles auth load, 4) Preferred Swift UI framework. Provide just a quick list of category labels next to each item without spending time explaining reasons.
| Checked | Without skill | With skill |
|---|---|---|
| The response includes written justification for each constraint classification. | Missed | Passed |
The instructions your model reads when the skill loads.
Take a list of identified constraints and classify each into one of three categories: hard constraints (immovable, must be accepted), soft constraints (can be worked around or mitigated), and assumptions (unvalidated beliefs that may or may not be real constraints).
Spawns a subagent that:
Classification requires careful judgment about what is truly immovable vs. what merely appears so. A dedicated subagent can focus on this distinction without being biased by prior analysis.
Output MUST include: all input constraints classified, at least one constraint in each category (hard/soft/assumption), and justification for each classification. Reject if any input constraint is missing from output.
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.