菜单
Dev: wipe the six category datasets (incident tables) for a clean test run; keeps config, vocab, and the message store. Usage: /vipe
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Dev: check a target (spec / plan / working diff / code) for architectural drift from the rulebook docs/ARCHITECTURE.md — report qualitative deviations citing rule ids, and triage new ones into docs/Debt.md. Usage: /drift <target>
Push enriched vocab to Anki Desktop as flashcards and pull review progress back. Usage: /anki-sync
Add words/terms you're learning, enriched (translation, alternative translations, examples, synonyms, definition) into your native/learning languages. Comma-separated for several at once. Usage: /loot <word>[, <word2>, ...]
Review your buffered writing into per-category frequency docs (grammar / rephrasings / idioms / verbs). Usage: /debrief
Use whenever you read, query, or mutate shadowling's sqlite database (shadowling.db) — any SELECT/INSERT/UPDATE/DELETE, ad-hoc SQL, dropping/clearing/resetting rows, inspecting data, or checking a migration's result. All DB access goes through a skill entrypoint, a repository method (`models/*`), or `sql.py` — never raw sqlite3. Schema/data-layer changes are NOT made here — they go through an appended migration in appdb.py; this skill only documents that rule and verifies the outcome.
Explain an expression in the language you're learning that you can't read literally — get a verdict (memorize vs learnable rule) + how to read it, saved to the decode dataset. Usage: /aha <phrase> [+ your hunch]
| name | vipe |
| description | Dev: wipe the six category datasets (incident tables) for a clean test run; keeps config, vocab, and the message store. Usage: /vipe |
| disable-model-invocation | true |
| allowed-tools | Bash(python3 */sql.py*) |
Dev utility — empties the six category incident tables so you can re-test from
a clean slate. Keeps config.json, the vocab table, and the messages
store. The wipe goes through sql.py --write, which snapshots the database
into backups/ before each delete — so a mistaken run is always recoverable.
Run EXACTLY these six commands and print their combined output, then STOP:
python3 "${CLAUDE_PLUGIN_ROOT}/sql.py" --write "DELETE FROM grammar"
python3 "${CLAUDE_PLUGIN_ROOT}/sql.py" --write "DELETE FROM rephrasing"
python3 "${CLAUDE_PLUGIN_ROOT}/sql.py" --write "DELETE FROM idioms"
python3 "${CLAUDE_PLUGIN_ROOT}/sql.py" --write "DELETE FROM verbs"
python3 "${CLAUDE_PLUGIN_ROOT}/sql.py" --write "DELETE FROM decode"
python3 "${CLAUDE_PLUGIN_ROOT}/sql.py" --write "DELETE FROM friction"