instinct-status
Shows learned instincts from dqiii8.db, grouped by project and confidence. Internal diagnostic tool — not for user invocation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Shows learned instincts from dqiii8.db, grouped by project and confidence. Internal diagnostic tool — not for user invocation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Skill para despachar tareas a agentes NIM/Groq/GitHub desde esta sesión CC. Habilita el Hermes Work Loop — CC orquesta, agentes B/B+ ejecutan.
Upload DOCX files from intl-reports to Google Drive Carpeta 3 using rclone. Zero reasoning — action only.
Defensive security — reads red-team findings and systematically patches every vulnerability. Hardens code, adds input validation, fixes permissions, and verifies each fix. Works from the latest red-team report.
Launch an efficiency audit on modified Python files using Aider + Gemini 2.0 Flash. Analyzes bugs, efficiency, readability, and security. Saves report to database/audit_reports/.
Genera y entrega informes de internacionalización (Diagnóstico + Plan) para pymes españolas. Batch pipeline via Orchestrator v4 (core.cli) desde tmux externo. NUNCA empresa-a-empresa con Agent Haiku manual.
Adversarial security testing — attempts to break the codebase using real hacker techniques. Tests OWASP Top 10, prompt injection, MCP poisoning, dependency attacks, auth bypass, and vibe-coding-specific patterns. Generates exploit report. NEVER auto-invoked — user must explicitly request.
| name | instinct-status |
| description | Shows learned instincts from dqiii8.db, grouped by project and confidence. Internal diagnostic tool — not for user invocation. |
| command | /instinct-status |
| allowed-tools | ["Bash"] |
| user-invocable | false |
Shows continuous learning instincts stored in dqiii8.db.
/instinct-status
/instinct-status --project dqiii8-core
/instinct-status --top 10
instincts table from database/dqiii8.dbpython3 -c "
import sqlite3, os, sys
DB = 'database/dqiii8.db'
project_filter = None
top_n = 20
# Parse args (passed as ARGS env or argv)
args = sys.argv[1:]
for i, a in enumerate(args):
if a == '--project' and i+1 < len(args):
project_filter = args[i+1]
if a == '--top' and i+1 < len(args):
top_n = int(args[i+1])
conn = sqlite3.connect(DB)
if project_filter:
rows = conn.execute(
'SELECT keyword, pattern, confidence, times_applied, times_successful, project, created_at '
'FROM instincts WHERE project=? ORDER BY confidence DESC LIMIT ?',
(project_filter, top_n)
).fetchall()
else:
rows = conn.execute(
'SELECT keyword, pattern, confidence, times_applied, times_successful, project, created_at '
'FROM instincts ORDER BY project, confidence DESC LIMIT ?',
(top_n,)
).fetchall()
conn.close()
if not rows:
print('No instincts registered yet.')
print('They will be generated automatically at the end of sessions with corrections in tasks/lessons.md')
exit(0)
def conf_bar(c):
filled = int(c * 10)
return 'X' * filled + '.' * (10 - filled) + f' {int(c*100)}%'
print('=' * 60)
print(f' INSTINCT STATUS -- {len(rows)} total')
print('=' * 60)
current_proj = '__none__'
for kw, pattern, conf, applied, successful, proj, created in rows:
if proj != current_proj:
current_proj = proj
label = proj if proj else 'GLOBAL'
print(f'\n## {label.upper()}')
bar = conf_bar(conf or 0)
success_pct = int((successful or 0) / max(applied or 1, 1) * 100)
tag = ' consolidated' if (conf or 0) >= 0.7 else ''
print(f' {bar} [{kw}]{tag}')
print(f' applied: {applied or 0}x successful: {success_pct}% since: {(created or \"\")[:10]}')
if pattern:
preview = pattern[:80] + ('...' if len(pattern) > 80 else '')
print(f' {preview}')
"
database/dqiii8.db table instinctstasks/lessons.md[YYYY-MM-DD] [KEYWORD] cause → fixpython3 -c "import sqlite3; ..."