cskwork/supergoal-skill / skills/supergoal
supergoal
UnverifiedRoute objective-driven development, verification, planning, "teach/explain", codebase learning, and skill evaluation through the Supergoal workflow. Use when Supergoal is requested or an autonomous delivery workflow is needed.
reference/market-research.md
View on GitHub# Market research - GREENFIELD Validate
Validate asks whether to build before Build opens. It seeks directional demand evidence and a bounded
MVP, not market sizing or pricing forecasts. State that limitation. Position `/supergoal` as a
supervised, gated delivery loop for bounded objectives, not a hands-off engineer.
## `brief.md` `## Validation` must include
1. **Problem & target user.** One Jobs-To-Be-Done sentence: "When [situation], I want [motivation], so
I can [outcome]." If you cannot write it, ask the user.
2. **Demand evidence** via fan-out:
- Competitors/substitutes: who solves this, pricing, user complaints.
- Search/keyword signal: are people looking?
- Existing-solution check: build vs adopt.
3. **Riskiest assumption.** Name the belief that sinks the product if false.
4. **MVP scope.** Smallest thing that tests the riskiest assumption and serves the JTBD. Everything
else is a non-goal.
5. **Decision line.** End with exactly one line:
- `Decision: GO` when demand is real, no adequate existing solution exists, and MVP is bounded.
- `Decision: NO-GO` when an existing tool suffices, no demand signal appears, or the objective stays
vague after one question. Stop; do not build on spec.
## Dispatch
Validate is wide-and-shallow. Fan out one subagent per evidence stream. The Analyst persona
(`agents/analyst.md`) writes JTBD, riskiest assumption, MVP scope, and Decision into `brief.md`.
Use the session's web/search tools. If the environment uses `ctx_*` / context-mode tools, use those;
do not force blocked `curl`/`wget`.
## Why gated
Autonomous coding capacity is scarce. A short evidence pass that prevents one wrong build pays for
itself.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |