feat: Enhance technical verification processes and documentation for improved accuracy in engineering advice

.opencode/agents/fidelity.md

@@ -58,5 +58,8 @@ 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 `vault/03-context/ios/`.
+- When answering programming, dependency-management, package-manager, CI/build, testing, or architecture-practice questions, verify with primary/current documentation when the topic may be outdated, disputed, version-sensitive, or project-critical.
+- For CocoaPods, podspecs, private spec repos, trunk/CDN behavior, SPM, Xcode, Swift, and Apple frameworks, do not rely only on model memory before giving strong advice.
 - When generating prompts for GitHub Copilot or another AI, use `vault/03-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.
+- Act as an agent, not only as a chat assistant: when a repeated weakness appears in output quality, proactively suggest or apply a workspace-level improvement.

.opencode/agents/workspace.md

@@ -31,6 +31,8 @@ Behavior rules:
 - If an integration or sync command fails, do not update project memory from that failure.
 - Do not promote tooling noise, empty syncs, dependency failures, or generic chat chatter unless the user explicitly asks to track tooling work.
 - Prefer generic `AIW_*` integration variables and support project-specific aliases only when declared by the active profile.
+- For technical advice about programming concepts, dependency tooling, package managers, CI/build systems, testing frameworks, or changing best practices, verify against primary/current documentation before making strong claims.
+- Treat recurring quality gaps as workspace-maintenance signals and update commands, agents, skills, prompts, or process notes when the improvement should persist.
 - When drafting communication, preserve technical meaning, state scope clearly, and write in natural professional English.
 
 Memory destinations:

.opencode/commands/fidelity-context.md

@@ -21,6 +21,7 @@ Use these files as the baseline context:
 @vault/07-maps/people.md
 @vault/03-context/project.md
 @vault/03-context/process/communication.md
+@vault/03-context/process/technical-verification.md
 @vault/03-context/process/ai-to-ai-prompting.md
 @vault/03-context/process/jira-story-rules.md
 @vault/03-context/process/workspace-model.md

.opencode/commands/swift-help.md

@@ -9,6 +9,7 @@ Read:
 @vault/03-context/ios/index.md
 @vault/03-context/ios/current-practices.md
 @vault/03-context/ios/project-swift-guidance.md
+@vault/03-context/process/technical-verification.md
 @vault/03-context/project.md
 @vault/03-context/systems/index.md
 @vault/03-context/workstreams/index.md
@@ -23,7 +24,7 @@ Instructions:
 - Use the `ios-swift-answering` skill if available.
 - Use `swiftui-xflow-review` if the question touches SwiftUI, XFlow, UIKit bridge removal, modal presentation, lifecycle, or backend-driven UI.
 - Use `ios-testing-strategy` if the question touches tests or validation.
-- If current Apple API behavior matters, verify against official Apple or Swift documentation before making strong claims.
+- If current Apple API, Swift, CocoaPods, SPM, Xcode, CI/build, or testing behavior matters, verify against official/primary documentation before making strong claims.
 - Contextualize the answer to Fidelity only when it materially changes the recommendation.
 - Separate current best practice from project-safe recommendation when they differ.
 

.opencode/commands/workspace-context.md

@@ -25,6 +25,7 @@ Read active workspace memory:
 @vault/07-maps/people.md
 @vault/03-context/project.md
 @vault/03-context/process/communication.md
+@vault/03-context/process/technical-verification.md
 @vault/03-context/process/context-maintenance.md
 @vault/03-context/process/workspace-model.md
 @vault/03-context/process/agent-memory-rules.md

.opencode/skills/ios-swift-answering/SKILL.md

@@ -13,7 +13,7 @@ Use this skill for Swift, SwiftUI, iOS architecture, concurrency, testing, or de
 1. Identify whether the question is general Swift/iOS or Fidelity-specific.
 2. Read `vault/03-context/ios/current-practices.md` for currentness rules.
 3. Read `vault/03-context/ios/project-swift-guidance.md` when the answer may affect XFlow, Fid4, XFlowViewMaker, FTFrameworks, feature flags, or consumer validation.
-4. If the answer depends on current Apple APIs, Xcode versions, or migration guidance, verify with official Apple/Swift documentation before making strong claims.
+4. If the answer depends on current Apple APIs, Xcode versions, dependency tooling, package-manager behavior, testing frameworks, or migration guidance, verify with official/primary documentation before making strong claims.
 5. Separate:
    - current best practice
    - project-safe recommendation
@@ -24,4 +24,5 @@ Use this skill for Swift, SwiftUI, iOS architecture, concurrency, testing, or de
 - Be direct and senior-engineer practical.
 - Avoid generic architecture advice when project constraints matter.
 - Do not assume deployment target, Xcode version, or framework migration status.
+- Do not characterize CocoaPods, SPM, podspec repos, trunk/CDN behavior, CI/build behavior, or testing framework practices as good or bad practice without corroborating current primary docs when the recommendation matters.
 - Mention tradeoffs and validation path when relevant.