skills/forget/SKILL.md
Use when you need to delete specific outdated or incorrect memories.
npx skillsauth add seokan-jeong/team-shinchan team-shinchan:forgetInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Remove outdated or incorrect learnings from memory.
/team-shinchan:forget # Interactive mode
/team-shinchan:forget "Redux" # Remove learnings containing "Redux"
/team-shinchan:forget --all # Clear all learnings (with confirmation)
/forget)🗑️ [Forget] Current learnings:
1. [preference] Use Zustand over Redux
2. [pattern] Early returns for validation
3. [convention] Use pnpm, not npm
4. [mistake] Always null-check before .map()
Which learning to remove? (Enter number or keyword)
/forget "Redux")🗑️ [Forget] Searching for: "Redux"
Found 1 matching learning:
• [preference] Use Zustand over Redux
Remove this learning? (y/n)
If confirmed:
✅ Removed: "Use Zustand over Redux"
📁 Updated: .shinchan-docs/learnings.md
/forget --all)⚠️ [Forget] WARNING: This will delete ALL learnings!
Current count: 15 learnings
Are you sure? Type "DELETE ALL" to confirm:
If confirmed:
✅ Cleared all learnings.
📁 Reset: .shinchan-docs/learnings.md
💡 Start fresh with /team-shinchan:learn or just work!
| Situation | Action |
|-----------|--------|
| Learning is outdated | /forget "old pattern" |
| Learning was wrong | /forget "incorrect thing" |
| Project changed direction | /forget --all (careful!) |
| Too many irrelevant learnings | Selective /forget |
--alltesting
Default-on interview option-quality panel — N diverse generators produce structure-free options, a SelfCheckGPT majority-vote consensus filters hallucinations, a SteerConf cautious-confidence judge scores survivors, and a deterministic top-K is returned. Workflow tier; the single fierce-* skill that is ON by default.
development
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, completeness + interaction critics, and a deterministic 3-lens rubric judge panel. Opt-in main-loop Workflow tier.
data-ai
Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.
testing
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.