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/domain-agent/freshness.md
View on GitHub# Freshness Policy
Goal: keep domain context useful without making every run spend tokens on stale-document auditing.
## Policy
- Light refresh threshold: 5 days after `config.json.lastUpdated`.
- Full review threshold: 30 days after `config.json.lastUpdated`.
- Triggered refresh: selected knowledge conflicts with current code, terminology conflicts with the
glossary, or a run proves a stable new fact that improves future routing.
## Every Run
1. Read `config.json` and `index.md`.
2. Select at most five domain files.
3. Verify load-bearing facts against current code/docs.
4. Write only a compact Domain Brief to the run vault, including terminology conflicts.
## Light Refresh
Use when the pack is older than 5 days or a selected flow feels suspicious.
1. Run CodeGraph status for only affected repos.
2. Check changed docs/source since `lastUpdated` when git history is usable.
3. Re-read only selected domain files and their cited source files.
4. Patch stale entries surgically.
## Full Review
Use monthly, after major repo changes, or after repeated stale-context misses. Review `index.md`,
`code-map.md`, `test-map.md`, `invariants.md`, and high-traffic flows. Split broad files instead of
appending more detail.
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 |