Deep Analysis

Analyze one specific event 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 the current topic or natural topic name is clear. Before reading topic files or stored digest artifacts, 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 starting:

• <skrya-data-root>/topics/<topic-id>/topic.json
• <skrya-data-root>/topics/<topic-id>/brief.json
• <skrya-data-root>/topics/<topic-id>/deep-analysis.md

If available, also read the latest digest output and the stored event context for the referenced event.

Also inherit any applicable workspace defaults from AGENTS.md, CLAUDE.md, or the equivalent repository instruction file.

Accepted Inputs

Accept either:

• dig: N-xx for one news item, resolved from the received card or explicit digest artifact.
• dig: T-xx for the complete Thread archive, not only displayed milestones.
• write: T-xx for a sourced article draft based on the complete Thread history. Do not automatically publish.
• a specific event description that is sufficient to locate the event.

In channel-aware hosts, resolve the topic and current binding first. Use skrya resolve-reference --topic <topic-id> --binding <binding-id> --reference <N-xx-or-T-xx> --message-id <replied-message-id>. Omit message ID only when using that binding's latest complete successful delivery. Never use an unrelated channel's snapshot or the latest generated digest. For local non-channel conversations, use skrya resolve-reference --topic <topic-id> --artifact <digest-file> --reference <N-xx-or-T-xx>. If the user only replies with a number, interpret it as the news number in the same received digest. If no snapshot or topic can be resolved, ask a short clarification instead of guessing.

For write: T-xx, read the resolved entity's full timeline, sources, topic brief and deep-analysis guidance. Write an article with a clear argument, chronological context, source citations and explicit uncertainty. Save the completed draft under <skrya-data-root>/runs/<topic-id>/articles/ using a timestamped Markdown filename. This is an agent writing workflow, not a publishing command.

Output Rules

• Do not show source lists in the normal analysis output.
• Keep traceability so that if the user asks for sources afterward, you can return them.
• Focus on event understanding, not article summarization.
• Keep the tone analytical and natural, not templated.
• Be explicit about uncertainty.
• File names are internal execution details; do not show file names in normal user-facing replies unless the user asks for implementation details.

Required Behavior

1. Resolve the target event.
2. Gather the relevant items and supporting context for that event.
3. Supplement with more retrieval only if the current evidence is too thin.
4. Reconstruct the event timeline.
5. Separate agreed facts from disputed claims.
6. Judge current credibility and uncertainty.
7. End with what is worth watching next.

Default Structure

Use this shape by default:

1. Brief conclusion
2. Event overview
3. Timeline or development arc
4. Cross-source synthesis
5. Credibility judgment
6. What to watch next

Do not mechanically print these as stiff report labels if a smoother structure reads better, but make sure all six jobs are covered.

Source Follow-up

If the user asks for the sources behind the analysis, return the relevant source list for the analyzed event.