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/domain-rules.md
View on GitHub# Domain rules - priority digest
For domain-specific work, carry <=10 abstract priority rules for the task's domain(s). They guide
Frame/Build/Verify quality only. They are advisory and never replace hard gates: the project's REAL
tests, the QA gates, and the read-only DB rule still decide.
## Produce at Frame
1. **Route.** Name the domain(s) the objective touches (e.g. web-design, payments, data pipeline).
Multiple domains may stack.
2. **Distill.** Write <=10 one-line principle rules total - from the project's own docs/code first,
then general domain knowledge. Keep them abstract, not task steps.
3. **Record once.** Add `## Priority Rules` to the run vault `PLAN.md`; keep them in the
conductor's context.
## Apply per role
Inject only the role-relevant subset into each role prompt. Do not widen vault read scope.
- Build: honor the rules while implementing; derive edge-case tests from them.
- Reviewer (plan attack / REVIEW-ONLY): flag violations as findings.
- Verify: derive a concrete coverage checklist from the same domain routing - UI means
a11y/responsive/error states; data pipeline means idempotency/schema/PII; API means error paths and
auth ordering; security-sensitive input means bypass families. Report each item as
verified-with-evidence, or list it under `Not covered:` with justification.
## Conservative updates
Refine only when the objective or plan materially changes. Keep rules abstract and log the reason in
the run `PLAN.md` as `RULES-UPDATE:`.
## Format
```md
## Priority Rules
Domain(s): <e.g. web-design + ecommerce-retail>
1. <abstract one-line rule>
...
10. <abstract one-line rule>
```
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: 471k | 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 |