all publishers

birdiebir

@birdiebir source repo

2 published skills

  1. ▌
    Social Export Analysis · birdiebir bundle
    Methodology and reusable scaffolding for turning a large, unstructured personal-data export into categorized, analyzable data — validated on a 10GB+ Facebook export (tens of thousands of message files, about 15 raw top-level categories, tens of thousands of photos). The architecture is platform-agnostic; only the connector (the code that parses one platform's raw file format into records) is platform-specific.
    0 installs
  2. ▌
    Social Export Insights · birdiebir bundle
    Use when the user asks a natural-language question about a specific person/relationship, group, or PR-risk concern derived from an already-organized personal social-data export (Facebook Messenger today) — e.g. "這個人最近是不是變冷淡了", "我最近的人脈狀況", "有沒有PR風險", "這個群組在幹嘛" — or wants to add a new deep-analysis capability on top of one. Also use whenever the user asks for a specific analysis depth on a conversation/group — "輕量分析"/"中量分析"/"深度分析" or "light/medium/heavy analysis", "幫我對這幾個對話做中量分析" — this skill owns the light/medium/deep tier system (see 分析/分層.md) and its verbatim-quote/coverage verification scripts; don't hand-roll a one-off analysis pass without checking here first. Requires analysis/output/messages/data/thread_index.json to already exist (see social-export-analysis skill first if not).
    0 installs