메뉴
Triggers on process mistakes and steering corrections; run steering-correction-promotion for artifact choice, context optimization, and JRN receipt. Journal alone is incomplete.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Runs StepCOVNet GPU training and MERT extraction on Windows via WSL with TensorFlow CUDA libraries. Use for train_onset, overfit scripts, extract_mert_features with cuda, or when TensorFlow sees zero GPUs in WSL.
One-prompt agent autoresearch loop for StepCOVNet: goal + time budget → orient, hypothesize, run, log, repeat until success or deadline. Use when the user says "run autoresearch", gives a research goal with a budget, or names a profile (e.g. ar-tide-overfit). Not for unattended Python planners (--hours / lattice).
Deprecated alias — use autoresearch skill with profile ar-tide-overfit.
Starts a research session and logs EXP and NOTE entries with timestamps. Use when beginning research work, logging experiments, or writing discussion notes. Promote findings to PAPER_OUTLINE only when drafting the paper.
Audit and sync agent brain — read all rules from disk, reconcile skills/catalogs/routing. Triggers on refresh agent brain, refresh all rules, audit rules, or after steering promotion. Read-only audit script; agent writes doc updates.
On user steering corrections or remember-this, pick the smallest durable artifact (skill section, scoped rule, or rare always-apply rule), slim AGENTS.md, optimize agent-brain context, then prepend JRN. Use instead of creating new alwaysApply rules by default.
| name | agent-self-improvement |
| description | Triggers on process mistakes and steering corrections; run steering-correction-promotion for artifact choice, context optimization, and JRN receipt. Journal alone is incomplete. |
| disable-model-invocation | true |
On user steering, remember this, or a process mistake worth preserving:
| Step | Action |
|---|---|
| 1 | Artifact per promotion skill |
| 2 | Prepend JRN with Artifact path |
| 3 | Confirm artifact + journal id in chat |
Journal-only entries are incomplete (except explicit user deferral).
Immediately: steering correction, remember this, costly mistake, durable fix.
Periodically: after discrete tasks with process lessons; before switching task areas.
Session end: catch missed artifact + JRN pairs; run agent-brain-refresh if brain files changed.
See steering-correction-promotion § JRN receipt and self-journal.md.
~/.cursor/skills-cursor/ (Cursor internal)