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.

AGENTS.md

@@ -22,6 +22,7 @@ The detailed operating rules live in:
 - `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`
@@ -57,6 +58,7 @@ These are also loaded through `opencode.json`.
 - Keep changes concise and auditable.
 - When the topic is architectural or historical, prefer updating the relevant file under `ai/context/systems/`, `ai/context/workstreams/`, or `ai/context/process/` instead of overloading `ai/context/project.md`.
 - When the user asks Swift, SwiftUI, iOS architecture, testing, or debugging questions, use `ai/context/ios/` and the local OpenCode iOS skills before answering.
+- When the user asks for a prompt for another AI, GitHub Copilot, or the Fidelity development machine, use `ai/context/process/ai-to-ai-prompting.md` and generate a self-contained prompt.
 - If a Swift/iOS recommendation depends on current Apple APIs, Xcode behavior, or framework migration guidance, verify against official Apple or Swift documentation before making strong claims.
 
 ## Communication

README.md

@@ -11,6 +11,7 @@ This repository is not the product codebase. It is the operational context layer
 - Keep Fidelity context current outside the main development machine
 - Turn fragmented daily work into reusable AI-ready context
 - Support standups, manager updates, Jira notes, and debugging summaries
+- Generate high-quality prompts for GitHub Copilot or another AI on the Fidelity development machine
 - Improve communication quality without losing technical accuracy
 
 ---
@@ -26,6 +27,7 @@ This workspace is used to:
 - preserve current project context between sessions
 - draft messages for the current manager or stakeholder with the right tone and scope
 - translate rough notes into concise native-sounding English
+- generate self-contained prompts for another AI that does have access to the product codebase
 
 Core principle:
 
@@ -165,6 +167,7 @@ Project commands live under `.opencode/commands/` and are intended to:
 - sync Mattermost context into the workspace inbox
 - draft standups
 - draft manager updates
+- draft Copilot prompts for coding work on the Fidelity machine
 - convert rough notes into daily log updates
 
 This keeps AI output tied to the latest workspace state instead of relying on chat memory alone.

ai/AGENTS.md

@@ -64,6 +64,7 @@ When drafting messages for a manager or stakeholder:
 - Before answering prompts about current work, verify `ai/state/current.md` and the latest relevant log in `ai/logs/`
 - Before answering architecture, process, or historical questions, check the relevant file under `ai/context/systems/`, `ai/context/workstreams/`, or `ai/context/process/`
 - Before answering Swift, SwiftUI, iOS architecture, testing, or debugging questions, check `ai/context/ios/` and use the project-local iOS skills when available
+- Before generating a prompt for another AI or GitHub Copilot, check `ai/context/process/ai-to-ai-prompting.md` and make the prompt self-contained
 - If `ai/inbox/mattermost-latest.md` exists, check it before answering prompts about current status, standups, or supervisor communication
 - Treat all meaningful user prompts as potential memory updates, not only explicit sync commands
 - If a Mattermost sync or other context-ingestion step fails, do not update `ai/logs/`, `ai/state/`, or stable context files based on that failure
@@ -80,6 +81,7 @@ When drafting messages for a manager or stakeholder:
 - Prefer updating stable project context over appending generic operational summaries
 - Do not create daily log entries for tooling activity, sync status, or generic chat noise
 - For Swift/iOS best-practice answers, distinguish current Apple guidance from project-safe recommendations when Fidelity constraints may change the answer
+- For Copilot prompts, include only relevant context, tell Copilot what to inspect, and state constraints, non-goals, expected output, and validation
 - Do not ask the user what should be promoted after a successful sync unless multiple conflicting interpretations are equally plausible
 - When the user shares relevant new information, update today's log if the information belongs to the daily record
 - When the user corrects or changes stable context, update the canonical file directly:

ai/context/process/ai-to-ai-prompting.md

@@ -0,0 +1,69 @@
+# AI-To-AI Prompting
+
+## Goal
+
+Generate prompts that can be sent to another AI assistant on the Fidelity development machine, especially GitHub Copilot.
+
+---
+
+## Operating Assumption
+
+This workspace does not contain the product codebase. The target AI has access to the Fidelity codebase on another machine.
+
+Therefore prompts must:
+
+- include only the relevant project context from this workspace
+- tell the target AI what files/modules to inspect
+- ask for a concrete output
+- specify constraints and non-goals
+- avoid pretending the target AI already has this workspace memory
+
+---
+
+## Prompt Structure
+
+Use this structure by default:
+
+1. Role
+2. Project context
+3. Current task
+4. Relevant ticket/context
+5. Files/modules to inspect
+6. Constraints
+7. Expected output
+8. Validation requirements
+
+---
+
+## Prompt Quality Rules
+
+- Prefer precise task framing over long background dumps.
+- Include Jira ID and title when the work maps to a ticket.
+- Include current constraints such as REST feature flag, GraphQL fallback, auth state, backend-driven behavior, and consumer validation when relevant.
+- Ask the target AI to inspect code before proposing changes.
+- Ask for a plan first when the implementation scope is uncertain.
+- Ask for code changes only when the desired write scope is clear.
+- Include "Do not assume REST is active by default" for REST migration tasks.
+- Include "Separate external issue from regression" for AO/Discourse issues.
+- Include "Validate against Fid4/consumer path when needed" for XFlow integration tasks.
+
+---
+
+## Bad Prompt Pattern
+
+"Fix this issue in XFlow."
+
+Why bad:
+
+- no entry point
+- no auth state
+- no expected behavior
+- no ticket context
+- no validation path
+- no scope boundary
+
+---
+
+## Good Prompt Pattern
+
+"You are working in the Fidelity iOS codebase. Inspect the XFlowSDK and XFlowViewMaker integration path for `PDIAP-14859 - Spike - Research strategy to remove final UIKit wrapping from XFlowSDK and XFlowViewMaker without disrupting consumer implementation`. First identify where XFlow currently exposes SwiftUI through `UIHostingController`, where XFlowViewMaker consumes it, and what feature flag protects the migration path. Do not change code yet. Return a concise plan with affected files, risks, consumer validation needs in Fid4/FTTransfer, and any questions that block implementation."

ai/context/process/index.md

@@ -5,6 +5,9 @@
 - [communication.md](./communication.md)
   How to frame technical updates and external communication.
 
+- [ai-to-ai-prompting.md](./ai-to-ai-prompting.md)
+  How to generate prompts for GitHub Copilot or another AI on the Fidelity development machine.
+
 - [jira-story-rules.md](./jira-story-rules.md)
   How to create or reference stories with the right scope and precision.
 

opencode.json

@@ -49,6 +49,7 @@
     "./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",

prompts/copilot-prompt.md

@@ -0,0 +1,43 @@
+# Copilot Prompt Template
+
+Generate a prompt to send to GitHub Copilot on the Fidelity development machine.
+
+The prompt should be self-contained because Copilot will not have this workspace's memory unless the prompt includes it.
+
+Requirements:
+
+- Use precise senior-engineer language
+- Include only relevant context
+- Include Jira ID and approved title when available
+- Tell Copilot what to inspect before changing code
+- Make constraints explicit
+- Specify whether the desired result is:
+  - investigation
+  - implementation plan
+  - code change
+  - review
+  - test strategy
+  - PR/story text
+- Include expected output format
+- Include validation requirements
+- Avoid overloading the prompt with unrelated workspace history
+
+Default output format:
+
+```text
+Role:
+
+Project context:
+
+Task:
+
+Relevant ticket/context:
+
+Inspect:
+
+Constraints:
+
+Expected output:
+
+Validation:
+```