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.
templates/GOAL.md
View on GitHub# GOAL - <topic>
Single source of "done". Only the verifier ticks a box; unticking needs regression evidence.
Never delete or reword an unmet criterion - append. Mid-run discovered musts are APPENDED as new
unchecked criteria tagged `(surfaced: ...)`. Ambiguous/product-changing candidates go to
`## Decision Gates` as `ask-user`, not into criteria.
## Original Request
> <user prompt, verbatim>
## Spec
<refined detailed spec: behavior, scope, data, constraints, non-goals>
## Success Criteria
Each item is falsifiable and names its verification method. Prefer Given/When/Then for behavior
criteria (spec-out: `reference/interview.md`).
- [ ] Given <precondition>, when <action>, then <observable result> - verify: `<command | API call | browser step | diff check>`
- [ ] <behavior, falsifiable> - verify: `<command | API call | browser step | diff check>`
- [ ] <surfaced behavior> - verify: `<test file::test name>` (surfaced: implied by <reason it is
required though the prompt never stated it>)
## QA Cases (web apps only)
Browser scenarios the QA agent drives via agent-browser (playwright-cli fallback); evidence under `qa/`.
- [ ] <route + steps + expected> - evidence: `qa/<file>`
## Decision Gates
| ID | Action | Status | Finding | Decision | Recheck |
|---|---|---|---|---|---|
| d1 | auto-fix / no-op / ask-user | open / resolved | | | |
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 |