a554b554/Reactant / skills/resolve
resolve
VerifiedReactant tag-only chain resolution. Use only when execute or execute-one dispatches an exact <@resolve> tag attached to a complete chat chain; never activate from ordinary chat or another skill.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.7 KB |
SKILL.md
View on GitHub---
name: resolve
description: Reactant tag-only chain resolution. Use only when execute or execute-one dispatches an exact <@resolve> tag attached to a complete chat chain; never activate from ordinary chat or another skill.
---
# 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.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |