Resolve

Activation Boundary

This is a tag-only worker skill. Use it only after execute or execute-one selects an exact <@resolve> annotation and supplies its attached document chat chain. Never activate it from a chat-window request, semantic similarity, or any skill other than those two routers. Without that handoff, do not apply conversation content to authored prose.

Consume a complete document-local chat chain: apply its final intent to the authored text, then remove every chain tag so only clean prose remains.

Tag

<@resolve>

Placed as the next annotation after the last element of a chain that contains at least one <@chat-model> response:

original paragraph...
<@chat-user: how can this be improved>
<@chat-model name="some-model">
suggestion text
</@chat-model>
<@resolve>

Input

• File path — the document being processed.
• The chain — all chat-user/chat-model turns in order. The user may have edited any turn, including model responses; the edited text is the authoritative history.
• Preceding authored block — the text the chain discusses and that this skill will revise.

Workflow

1. Read the preceding authored block and the full ordered chain.
2. Determine the final intent: the latest <@chat-model> response (and any later user follow-up) takes precedence; earlier turns resolve ambiguity about goals and constraints.
3. Apply that intent to the authored block's prose.
4. Write the result back: replace the authored block plus the entire chain — every <@chat-user> tag, every <@chat-model> block, and the <@resolve> tag — with the revised prose alone.

Scope Modifiers

• Protect << >> — content must NOT be modified, even if the chain suggests changing it. Keep the content exactly; remove the delimiters in the output.
• Field (( )) — ONLY text inside fields may be modified. Remove the delimiters in the output.
• Neither present: the whole authored block is editable.

Rules

• Follow the chain's final intent faithfully; this step applies decisions that were already made in the conversation.
• Remove the complete chain and consumed modifier delimiters; leave no chat-user, chat-model, or resolve syntax behind. Preserve every unrelated annotation, <@comment: ...> tag, and contextual literal/example byte-for-byte.
• Only this skill moves chain content into authored prose; if the chain is somehow incomplete (no <@chat-model> present), fail cleanly: change nothing and report.