菜单
Import or smoke-test Twitter/X network artifacts through the RapidAPI + MOE + LinkedIn resolution pipeline. Use for $import-twitter.
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
The single post-import people-processing workflow and per-person dossier surface. Use for $deep-context, "process/resolve/enrich my contacts", "build deep context", a dossier or identity lookup by name/phone/email, duplicate-person review, LinkedIn self-heal, or the staged people/LinkedIn UI. Builds dossiers for imported people and unresolved Gmail/iMessage/WhatsApp candidates, merges duplicates, asks the user only about uncertain additions, runs one budget-gated lookup for the editable Yes decisions plus eligible wrong-link recovery, verifies found LinkedIns, then realizes the approved network and index.
Add Gmail contacts to your local network. Use for $import-gmail. Sets up msgvault/Gmail (OAuth + authorize), asks which accounts and how many years to sync, syncs mail down, and imports contacts free and locally (shared identity directory only) — unresolved contacts go to a research-candidates pool. No Parallel.ai, no RapidAPI, no index build — identity resolution and indexing happen later in $deep-context. Always reruns the full checklist; overwrites in place.
Add iMessage/WhatsApp contacts to your local network. Use for $import-messages. Sets up access (Full Disk Access + WhatsApp QR), syncs message contacts down, matches them against already-imported LinkedIn/Gmail people (free), and imports matched people plus a research-candidates pool. No LLM calls, no paid research, no index build — identity resolution and indexing happen later in $deep-context. Never uploads to a Powerset set.
Deterministic LinkedIn-only Powerpacks setup. Use for $setup. Steps through update, a supported Powerset workspace or an already-prepared custom Modal workspace, LinkedIn Connections.csv import on Modal, source merge, Modal indexing, and local search-index validation. Always reruns the full checklist; overwrites in place. For Gmail use $import-gmail; for iMessage/WhatsApp use $import-messages.
Bootstrap Powerpacks into this agent from one URL — clone the public repo, install every Powerpacks skill for this harness (Claude Code, Codex, or Pi), initialize the hosted Powerset config when requested, then continue the user's ask in the same session without a restart. Use for "install powerpacks", "download the powerpacks skill", "use powerpacks to set up ...", or "set up my local network search using my Powerset account".
Force-update the canonical Powerpacks checkout to the newest published release and reinstall skills while preserving .powerpacks. Use for $update-powerpacks.
| name | import-twitter |
| description | Import or smoke-test Twitter/X network artifacts through the RapidAPI + MOE + LinkedIn resolution pipeline. Use for $import-twitter. |
Use this skill for $import-twitter or Twitter/X network import testing.
This is an alias/wrapper around discover/twitter/network_import.py. It is
manifest-only: one idempotent run per handle writes the fixed dir
.powerpacks/network-import/discover/twitter/<handle>/ (overwritten in place)
plus a single manifest.json. The RapidAPI-backed crawl and the OpenAI/RapidAPI
resolution steps are spend-bearing and run only with --approve-spend.
Without --approve-spend, run stops at the first spend step and emits a
needs_approval manifest naming the step + estimated calls:
uv run --project . python packs/ingestion/primitives/discover/twitter/network_import.py run \
--handle example_operator \
--max-pages 1 \
--limit 10 \
--min-score 0
Approve the spend by re-running the same command with --approve-spend; it
advances the whole pipeline in one pass and never re-spends steps whose output
is already on disk:
uv run --project . python packs/ingestion/primitives/discover/twitter/network_import.py run \
--handle example_operator \
--max-pages 1 \
--limit 10 \
--min-score 0 \
--approve-spend \
--linkedin-workers 10 \
--aggregator-workers 10
Inspect progress any time from the manifest (no spend):
uv run --project . python packs/ingestion/primitives/discover/twitter/network_import.py status --handle example_operator
twitter241 (RAPIDAPI_TWITTER_KEY or RAPIDAPI_KEY).--approve-spend; do not run deep research for this smoke.RAPIDAPI_LINKEDIN_KEY or RAPIDAPI_KEY and is spend-gated behind --approve-spend.people.csv; summarize as x/10 linkedins plus counts, not raw rows.After Twitter finishes, rebuild the merged network and local index with the
indexing fan-in:
uv run --project . python packs/indexing/primitives/index_contacts_pipeline/index_contacts_pipeline.py run --operator-id <operator-id>.