Skip to content

arbiterForge/codeArbiter / plugins/ca-codex/skills/ca-conflict

ca-conflict

Unverified

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

$ca-conflict — conflict protocol

Orchestrator protocol, not a skill route. When a rule conflict surfaces — the persona, a .codearbiter/ document, and code contradict each other, or two docs contradict each other — all other work STOPs and the conflict is presented for the user to resolve. The orchestrator never picks a side.

Flow

  1. Halt — suspend the in-progress task. No partial progress.
  2. Identify the conflicting sources (A and B): which document, file, or rule each is.
  3. Quote the exact passages side by side.
  4. Classify the conflict against the §2 conflict-resolution hierarchy and name the level the tension sits at. Note which source was more recently updated — informational, not determinative.
  5. Present and wait. Work resumes only after the user explicitly resolves.

Output

## Conflict detected — work halted

### Source A
File: <path> · Last updated: <date>
> <exact quoted text>

### Source B
File: <path> · Last updated: <date>
> <exact quoted text>

### Nature of conflict
<what the two sources disagree about>

### Conflict-hierarchy level
Level N — <why the tension sits here>

### To resolve
<options — update A, update B, or supersede one via an ADR>

---
Work is halted. Resolve before the orchestrator proceeds.

When routed automatically

The orchestrator surfaces a conflict on its own when the persona and a .codearbiter/ doc contradict each other, two docs contradict, code contradicts an accepted ADR, a new ADR contradicts an accepted one, or a task instruction contradicts a hard gate.

After resolution

The orchestrator records the resolution; if the user authorized a doc update, it makes that update (the one sanctioned side effect) and resumes from the suspension point.

Hard gate

MUST stop ALL other work. MUST NOT pick a side without explicit user instruction. MUST NOT decide by recency alone. MUST NOT silently continue past a detected conflict. If the conflict involves a guessed or auto-resolved [CONFIRM-NN], flag that as a separate critical finding.

rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 195kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 195kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 195kUpdated Claude CodeCodexVerifiedInstall