| name | digest |
| description | Use when the user wants a ranked daily briefing for a configured topic, asks what matters today for that topic, or wants a chat-friendly digest without inline source lists. Trigger for Chinese requests like "今天有什么重要", "给我今日简报", "跑一次日报", or "看看这个主题今天发生了什么". |
Digest
Generate a topic-level digest for a resolved Skrya topic.
Always resolve an explicit internal topic-id before reading files, but do not ask nontechnical users for raw ids when a natural topic name can be mapped.
Before reading or writing topic files, resolve the Skrya data root. Topic configuration and generated artifacts live under <skrya-data-root>/, not necessarily under the skill repository.
Read First
Read these files before drafting the digest:
<skrya-data-root>/topics/<topic-id>/topic.json<skrya-data-root>/topics/<topic-id>/brief.json<skrya-data-root>/topics/<topic-id>/sources.json<skrya-data-root>/topics/<topic-id>/digest.md- topic-specific digest template file when configured; otherwise
digest/templates/default-digest.md
If available, also read the latest event candidates or prior digest artifacts for that topic.
When runtime retrieval was used, consume only normalized skrya.ingest.v1 artifacts under <skrya-data-root>/runs/<topic-id>/ingest/. Do not consume raw provider output directly.
When thread seeds exist, use them to surface continuing thread updates and preserve durable topic memory.
Also inherit any applicable workspace defaults from AGENTS.md, CLAUDE.md, or the equivalent repository instruction file.
Delivery Context
Digest generation and digest delivery are separate steps.
- Before scheduled delivery, manual resend, or "why was today's digest empty" diagnosis, resolve the topic. In channel-aware hosts, also resolve the channel/conversation binding for the current request.
- In channel-aware hosts, only send the digest bound to the current channel/conversation unless the user explicitly names another target and the host supports cross-channel delivery.
- In channel-aware hosts, treat the current channel/conversation as the default visibility boundary. Resolve against
delivery-bindings.json first; do not scan all topics or all generated digests from the current channel.
- If no topic is bound to the current channel/conversation, ask which topic the user means or explain that no binding was found. Do not resend, combine, or repair every topic.
- In hosts without channel/conversation concepts, fall back to the resolved topic, user intent, and available automation context.
- If multiple same-channel topics are plausible in a channel-aware host, ask the user which digest they mean instead of sending all generated digests.
- Do not bundle unrelated topic digests from other channels into a resend response, even when they share a scheduled run time.
- If generated content exists but the delivered message was empty, resend via the explicit message tool when available and verify that the sent body is non-empty.
Output Rules
Required Behavior
- Load topic configuration, topic-specific digest guidance, and the digest template file.
- Consume the available normalized
skrya.ingest.v1 items or event candidates.
- Remove obvious duplicates and low-value fragments.
- Rank events using the topic brief and digest standard.
- Write every event as a compact line box with stable visible numbers in the first line and source references after a blank separator line.
- Keep the format uniform from the first item to the last.
- Save the digest markdown file under
<skrya-data-root>/runs/<topic-id>/ with an absolute execution-time filename only for scheduled or user-requested real digests; then update latest-digest.md as a symlink or pointer to that file. Do not save test-run previews by default.
- Preserve enough traceability so that if the user later asks for the source of an item, you can return the complete corresponding sources.
- If a seeded thread matches today’s items, write a concise line-box thread update before the normal numbered items. Do not include a "today matched digest items" line in the thread update.
- End the digest body, insert
---, and write a ## 系统提示 section with execution metadata, dig: / track: options, and a plain-language preference feedback option.
- For a test run, still use the same digest template and
## 系统提示 format, mark execution status as test/preview, explain dig: <编号>, track: <编号> <名称/意图>, and plain-language preference feedback, and do not mention saved artifacts.
Feedback Handling
dig: <numbers> routes the selected digest items to deep analysis.track: <numbers> <name/intent> means the user wants a continuing thread; propose a stable thread seed before writing it.- Plain-language preference feedback means the user is adjusting durable topic memory; route to request curation instead of answering only in chat.
- If the user asks "为什么没有 X", do not regenerate blindly; start missed-item diagnosis through request curation.
- If the user says "这个很重要", treat it as a durable ranking or watchpoint update, not a compliment to the current answer.
Ranking Heuristics
Prefer events that:
- strongly match the topic brief
- have multiple independent supporting sources
- are clearly heating up
- have real event shape rather than isolated chatter
Down-rank events that:
- are obvious rehashes with no new movement
- rely mostly on weak or unverifiable sources
- are noisy fragments without clear event value
Source Display
Default digest output should show compact source references on a separate source line inside each line box. Use human-readable source labels when available, or the domain name for URL-only sources. If the user asks where a digest item came from, answer with the complete relevant sources for that item.
