feat: Enhance AI prompting capabilities with new guidelines and templates for GitHub Copilot

.opencode/agents/fidelity.md

@@ -33,4 +33,5 @@ Behavior rules:
 - Do not over-promote uncertain information. Keep uncertain items in the daily log.
 - When drafting communication, preserve technical meaning and improve clarity in natural US English.
 - When answering Swift/iOS programming questions, use the project-local iOS skills and `ai/context/ios/`.
+- When generating prompts for GitHub Copilot or another AI, use `ai/context/process/ai-to-ai-prompting.md` and the `copilot-prompt-engineering` skill.
 - If the answer depends on current Apple APIs or Xcode/iOS behavior, verify with official Apple or Swift documentation before presenting it as current best practice.

.opencode/commands/copilot-prompt.md

@@ -0,0 +1,41 @@
+---
+description: Generate a high-quality prompt for GitHub Copilot on the Fidelity development machine
+---
+
+Generate a prompt that the user can send to GitHub Copilot or another AI assistant on the Fidelity development machine.
+
+Read:
+
+@prompts/copilot-prompt.md
+@ai/AGENTS.md
+@ai/context/process/ai-to-ai-prompting.md
+@ai/context/index.md
+@ai/context/project.md
+@ai/context/ios/index.md
+@ai/context/ios/project-swift-guidance.md
+@ai/context/systems/index.md
+@ai/context/workstreams/index.md
+@ai/work-items/index.md
+@ai/state/current.md
+@ai/state/work-items.md
+
+Detailed active work item files, if available:
+
+!`if [ -d ai/work-items ]; then for f in ai/work-items/*.md; do case "$f" in *README.md|*index.md) continue;; esac; echo "\n### $f"; cat "$f"; done; else echo "No work item files available."; fi`
+
+User request:
+
+$ARGUMENTS
+
+Instructions:
+
+- Use the `copilot-prompt-engineering` skill if available.
+- Generate a self-contained prompt for the target AI.
+- Include only context relevant to the request.
+- Include Jira ID/title when the task maps to an active work item.
+- Tell Copilot what to inspect before making assumptions.
+- Include constraints, non-goals, expected output, and validation.
+- If the user asks for implementation help but the write scope is unclear, generate an investigation/plan prompt rather than a code-change prompt.
+- Do not mention this workspace unless explaining that the target AI will not have access to it.
+
+Return only the final prompt unless the user explicitly asks for commentary.

.opencode/commands/fidelity-context.md

@@ -16,6 +16,7 @@ Use these files as the baseline context:
 @ai/context/systems/index.md
 @ai/context/workstreams/index.md
 @ai/context/process/communication.md
+@ai/context/process/ai-to-ai-prompting.md
 @ai/context/process/jira-story-rules.md
 @ai/context/people/manager.md
 @ai/context/people/index.md

.opencode/plugins/fidelity-compaction.js

@@ -22,6 +22,7 @@ export const FidelityCompaction = async ({ directory }) => {
         "ai/context/systems/index.md",
         "ai/context/workstreams/index.md",
         "ai/context/process/communication.md",
+        "ai/context/process/ai-to-ai-prompting.md",
         "ai/context/people/manager.md",
         "ai/context/people/index.md",
         "ai/work-items/index.md",

.opencode/skills/copilot-prompt-engineering/SKILL.md

@@ -0,0 +1,43 @@
+---
+name: copilot-prompt-engineering
+description: Create high-quality prompts for GitHub Copilot or another AI running on the Fidelity development machine, using this workspace's context without assuming the target AI has access to it.
+compatibility: opencode
+---
+
+## When To Use
+
+Use this skill when the user wants a prompt for another AI assistant, GitHub Copilot, or the Fidelity development machine.
+
+## Workflow
+
+1. Identify the target task type:
+   - investigation
+   - implementation plan
+   - code change
+   - review
+   - test strategy
+   - story/PR drafting
+2. Pull only the relevant context:
+   - `ai/work-items/` for ticket-specific context
+   - `ai/context/systems/` for component context
+   - `ai/context/workstreams/` for recurring constraints
+   - `ai/context/ios/` for Swift/iOS guidance
+3. Make the prompt self-contained.
+4. Tell the target AI what to inspect before acting.
+5. State constraints, non-goals, and validation expectations.
+
+## Fidelity Prompting Rules
+
+- Include Jira ID and approved title when available.
+- For REST work, say REST is behind a feature flag and GraphQL is fallback unless confirmed otherwise.
+- For XFlow work, say behavior may depend on entry point, auth state, backend config, and consumer integration.
+- For AO/Discourse issues, say external report vs regression must be separated.
+- For SwiftUI/XFlow work, mention lifecycle, modal presentation, UIKit bridge, feature flag, and Fid4 validation if relevant.
+
+## Output Rules
+
+- Return only the prompt unless the user asks for explanation.
+- Keep the prompt concise but complete.
+- Prefer sections over paragraphs.
+- Do not invent file paths unless the workspace context explicitly names them.
+- If exact files are unknown, ask Copilot to locate them first.