メニュー
Generate a local research digest from arXiv and OpenAlex using a local Python script. Also manages tracked research topics.
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
| name | research_digest_wrapper |
| description | Generate a local research digest from arXiv and OpenAlex using a local Python script. Also manages tracked research topics. |
| user-invocable | true |
| disable-model-invocation | false |
| metadata | {"openclaw":{"emoji":"🧠","requires":{"bins":["bash"]}}} |
Use this skill when the user wants a research digest from tracked topics or wants to manage the tracked topic list.
If the user provides an action inline (e.g. /research_digest_wrapper run), execute it immediately. Otherwise ask what they want to do and wait for their reply.
For every research digest or topic-management task, use:
When the digest seeds deeper research, preserve identifiers and hand off items to digest_bridge, zotero, paper-lookup, or deep-research-workflow instead of treating digest text as final evidence.
Run digest: run (options: --tag TAG, --min-priority N, --use-llm-summary, --use-llm-scoring)
List topics: list-topics
Add topic: add-topic "name" --tag TAG --priority N
Doctor: doctor
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh <COMMAND AND ARGS>
After running, read the digest file and summarize the top findings.
Validation before summarizing:
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh edit-topic "<NAME>" --tag <TAG> --priority <N>
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh disable-topic "<NAME>"
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh enable-topic "<NAME>"
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh remove-topic "<NAME>"
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh backup-topics --reason "<REASON>"
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh list-topic-backups
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh restore-topic-backup
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh export-topics --output /tmp/topics.tsv
exec: /workspace/skills/research-digest-wrapper/run_research_digest.sh import-topics /tmp/topics.tsv
{{ PRIVATE_DATA_DIR }}/research/alerts/topics.tsv{{ PRIVATE_DATA_DIR }}/research/alerts/digests/latest-digest.mdSend email over SMTP using only the Python standard library, with plain-text and HTML bodies, file attachments, cc/bcc, reply-to, a dry-run preview, connection verification, and redacted config inspection.
ALWAYS use this skill when the user asks to send, get, retrieve, find, share, add, or search for a paper. This skill manages the user's Zotero library with 10,000+ papers and can retrieve PDFs, create share links, add new papers, and search. Prefer this over getscipapers for any request involving sending/getting/finding papers.
Use before delivering work that incorporated content the agent did not author — fetched web pages, PDFs, retrieved or library documents, tool or subagent output — or that performs an outward-facing or irreversible action. Maps trust boundaries and runs an abuse-case and prompt-injection check, delegating to a fresh-context security reviewer.
Run bounded autonomous research iterations with evidence gates, recovery ledgers, and optional cross-agent handoffs. Use when the user asks to continue research autonomously, run a research loop, integrate autonomous agent loops, or keep improving a research workflow without repeated prompts.
Use for a clarity-only pass that must not change behavior — simplifying, renaming, de-duplicating, or restructuring code, configs, research scripts, or prose. Gates on understanding the target before touching it and re-verifies after each change so behavior stays fixed.
Use in-flight, the moment you are about to let a non-trivial decision stand — a branching or control-flow change, crossing a module/service/agent boundary, an assertion the type system or proof checker cannot see, a high-stakes or irreversible action, or an analytical step a conclusion rests on. Materializes a fresh-context reviewer biased to disprove, while course-correction is still cheap.