ワンクリックで
research-digest-wrapper
Use when the user wants a local research digest from tracked topics or wants to manage 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。
メニュー
Use when the user wants a local research digest from tracked topics or wants to manage 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
Use when the user asks for a multi-agent discussion, panel review, multi-agent review, or multi-agent research session with role selection, round control, and template-based orchestration.
Use when drafting, validating, or normalizing bounded cross-agent task/result packets for parent-controlled handoffs. This is a packet-contract skill, not a runtime delegation broker.
Send 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.
Runtime helper for autonomous-research-loop ledgers. Use to initialize, append, validate, inspect, or smoke-test autonomous research loop state files without network, package installation, provider CLI calls, or live agent spawning.
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 external DOI/ISBN/title resolution, manifest creation from pasted text, and paper retrieval after the local library-first workflow does not satisfy the request or the user explicitly opts out of library use.
| name | research-digest-wrapper |
| description | Use when the user wants a local research digest from tracked topics or wants to manage tracked research topics. |
| metadata | {"short-description":"Local research digest from tracked topics"} |
On native Windows, use the managed Windows runner and the native runtime command target. Set $runtime to the installed runtime root. Multi-agent installs usually use %LOCALAPPDATA%\ai-agents-skills\runtime. Then run:
$runtime = if ($env:AAS_RUNTIME_ROOT) { $env:AAS_RUNTIME_ROOT } else { "$env:LOCALAPPDATA\ai-agents-skills\runtime" }
& "$runtime\run_skill.bat" "skills/research-digest-wrapper/run_research_digest.bat" <args>
POSIX examples below use run_skill.sh and .sh command targets; use the Windows command target above on native Windows.
$AAS_RUNTIME_WORKSPACE/skills/research-digest-wrapper/Use the managed runtime runner rather than invoking the digest script directly.
Shared runner:
bash "$AAS_RUNTIME_ROOT/run_skill.sh"bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/research-digest-wrapper/run_research_digest.sh <COMMAND AND ARGS>
runrun --tag TAG --min-priority Nrun --use-llm-scoring --use-llm-summarylist-topicsadd-topic "<name>" --tag TAG --priority Nedit-topic "<name>" --tag TAG --priority Ndisable-topic "<name>" / enable-topic "<name>"remove-topic "<name>"backup-topics --reason "REASON"list-topic-backupsrestore-topic-backup <backup-name>export-topics --output /tmp/topics.tsvimport-topics /tmp/topics.tsvdoctorrebuild-corpusVerified example shapes:
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/research-digest-wrapper/run_research_digest.sh run --tag graph-theory --min-priority 3
bash "$AAS_RUNTIME_ROOT/run_skill.sh" skills/research-digest-wrapper/run_research_digest.sh add-topic "Token sliding" --tag reconfiguration --priority 5
Read and summarize:
$AAS_RUNTIME_WORKSPACE/data/research/alerts/digests/latest-digest.mdTracked topics live at:
$AAS_RUNTIME_WORKSPACE/data/research/alerts/topics.tsvFor any user-facing digest summary, load writing-style-settings.md before
writing. If the digest item or synthesis is mathematical, TCS, graph-theoretic,
Lean-related, or LaTeX manuscript prose, also load math-manuscript-style.md.
Stored digest summaries should record style_profile_ref, active_overlays,
active_requirement_ids, and style_applied; do not accept a bare
style_applied: true assertion as sufficient evidence.