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/QA.md
View on GitHub# QA - <topic>
All testing results as succinct plain-language checklist sentences. Evidence lives in `qa/`.
- Verdict: PASS | FAIL | PARTIAL
## Before
- [x] <observed pre-change behavior / reproduced symptom / preserve-baseline> - evidence: `qa/<file>` or command output
## Results
- [x] <one sentence: what was exercised and what happened> - `<command>` (frozen_repo)
- [x] <neighbor baseline re-run, no unnamed drift> - `<command>` (evaluator_owned)
Backward-trace: clean | <orphan file:line list>
## Commands
| Command | Source | Proves |
|---|---|---|
| | frozen_repo / evaluator_owned / agent_detected | |
## QA
Tool: agent-browser | playwright-cli
Fallback: <required only for playwright-cli; why agent-browser could not QA properly>
UI-tier: <Expressive|Functional, UI runs only>
DB: <dialect, read-only, when used>
- as-is: `qa/as-is-<view>.png` to-be: `qa/to-be-<view>.png`
- <per-scenario pass/fail + repro details for failures>
## Reproduction Fidelity
- Fidelity level: exact | prod-snapshot | synthetic-representative | synthetic-minimal | not-reproduced
- Residual risk from data gap:
- Post-deploy confirmation plan:
## Residual Risk
- Not proven:
- Follow-up:
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 |