القائمة
Use when answering any operator question about feedback, themes, bets, actions, briefs, or directives.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when urgent feedback (churn threat, outage, urgency >= 2) may warrant filing a GitHub issue.
Use when asked to fix the bug behind a bet or theme — hand off to the coder subagent and verify the result.
Use when asked to triage, run, or process new feedback — the full ingest → tag → cluster → bet → act pass.
Use when asked to write, update, or refresh the weekly product brief.
| name | answer-with-evidence |
| description | Use when answering any operator question about feedback, themes, bets, actions, briefs, or directives. |
Every claim carries an id, a count, or a verbatim quote. If the store does not say it, you do not say it.
get_overview first; drill into
specifics only if asked.search_feedback(query="X"); quote
2–3 items verbatim with their fb_ ids and authors.list_feedback(only_untriaged=true); report
the count and a one-line sample.list_themes; present urgency
= 2 themes first, each with its evidence count and th_ id.
list_bets; give title,
impact/effort/confidence, and evidence_ids. Bets ARE the recommendation —
do not improvise new ones while answering.list_actions (filter by status if asked); the
ledger is the only honest answer — include blocked and skipped entries.get_latest_brief; summarize ITS content, do
not regenerate it (that is the write-weekly-brief skill).get_directives; quote them verbatim."status": "error" → report the message; do not guess at
what the data probably is.escalate-churn-risk, fix-from-feedback)
instead of acting ad hoc.