Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/constraint-identification-sop
Identify constraints for a candidate using TOC, TRIZ, and Pre-mortem methods.
Passed 22 of 22 test cases with the skill, and 12 of 22 without it.
and 17 more in the full report
10 fixed12 passed either way0 still failing0 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.
We are evaluating a proposal to switch our main customer dashboard from server-side rendered HTML to a webassembly canvas architecture. We need a constraint identification pass on this setup. Should this run in the main conversation thread, or spawn a dedicated subagent?
| Checked | Without skill | With skill |
|---|---|---|
| The response explicitly delegates the discovery execution to a subagent. | Missed | Passed |
| The response cites preserving creative divergent thinking across frameworks as the reason for subagent execution. | Missed | Passed |
The instructions your model reads when the skill loads.
Systematically discover all constraints that could prevent a candidate from being implemented. Applies three complementary methods: Theory of Constraints (find the bottleneck), TRIZ contradiction analysis (surface technical/physical contradictions), and Pre-mortem (imagine failure and trace causes).
Spawns a subagent that:
Constraint discovery requires creative, divergent thinking across multiple frameworks. Running as a subagent prevents premature filtering and ensures all three methods are fully applied.
Output MUST include: at least 3 constraints identified, method attribution for each, and initial severity estimate. Reject if fewer than 3 constraints found.
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 12 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.