refactor: update skill paths to use .agents/skills/ for consistency and remove obsolete skill references

.agents/skills/index.md

@@ -27,4 +27,4 @@ Skills available through the shared `.agents/` surface for Antigravity-compatibl
 ## Compatibility Notes
 
 - `.agents/skills/` is the shared skill source intended for Antigravity-compatible and cross-tool discovery.
-- `.opencode/skills/` mirrors the installed skills for OpenCode runtime discovery.
+- OpenCode CLI also discovers `.agents/skills/`; do not mirror these skills into `.opencode/skills/`, because duplicate skill names create warnings and ambiguous discovery.

.agents/workflows/promote-project-context.md

@@ -49,7 +49,7 @@ Instructions:
   - `.opencode/commands/*.md` when command behavior needs to change
   - `prompts/*.md` when a reusable output template needs to change
   - `.opencode/agents/*.md` or `AGENTS.md` when default agent behavior needs to change
-  - `.opencode/skills/*/SKILL.md` when a specialized workflow needs to change
+  - `.agents/skills/*/SKILL.md` when a specialized workflow needs to change
   - `project-knowledge/00-start/*.md` when durable project onboarding guidance needs to change
   - `agent-memory/**/*.md` when agent learning, promotion, verification, or self-maintenance behavior needs to change
 - Prefer concrete project updates over broad summaries

.opencode/agents/fidelity.md

@@ -35,7 +35,7 @@ Behavior rules:
 - If the user corrects or teaches the agent during a learning session, update the smallest correct canonical file or behavior surface so future sessions benefit.
 - For any meaningful prompt, decide whether the interaction adds, corrects, or sharpens project memory.
 - When the user provides new durable information, update the right workspace files during the same turn when the destination is clear, but do not delay a straightforward answer just to create or reorganize memory.
-- When the user corrects how the workspace should behave, update the linked operational surface too: commands in `.opencode/commands/`, prompt templates in `prompts/`, agent rules in `AGENTS.md` or `.opencode/agents/`, skills in `.opencode/skills/`, and agent operating rules in `agent-memory/` when those files control the behavior.
+- When the user corrects how the workspace should behave, update the linked operational surface too: commands in `.opencode/commands/`, prompt templates in `prompts/`, agent rules in `AGENTS.md` or `.opencode/agents/`, skills in `.agents/skills/`, and agent operating rules in `agent-memory/` when those files control the behavior.
 - If existing context is stale, correct it directly instead of leaving conflicting versions.
 - Promote information carefully:
   - daily facts go to `project-knowledge/06-daily/YYYY-MM-DD.md`

.opencode/agents/workspace.md

@@ -45,4 +45,4 @@ Memory destinations:
 - durable project knowledge -> `project-knowledge/03-context/`
 - people and roles -> `project-knowledge/04-people/`
 - confirmed decisions -> `project-knowledge/05-decisions/`
-- reusable behavior -> `.opencode/commands/`, `prompts/`, `.opencode/agents/`, `.opencode/skills/`, `agent-memory/`, `core/`, or `scripts/`
+- reusable behavior -> `.opencode/commands/`, `prompts/`, `.opencode/agents/`, `.agents/skills/`, `agent-memory/`, `core/`, or `scripts/`

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

@@ -1 +0,0 @@
-../../../.agents/rules/ai-prompt-engineering.md

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

@@ -1 +0,0 @@
-../../../.agents/rules/copilot-prompt-engineering.md

.opencode/skills/index.md

@@ -1,31 +1,12 @@
-# OpenCode Skills Index
+# OpenCode Skills Compatibility
 
-Skills available to the workspace agent.
+OpenCode CLI discovers the shared skills from `.agents/skills/`.
 
----
+Do not mirror skills into `.opencode/skills/`; duplicate skill names create warnings and ambiguous discovery.
 
-## Generic Skills
+Use:
-
-- [Workspace Memory Curation](workspace-memory-curation/SKILL.md)
-- [Professional Communication](professional-communication/SKILL.md)
-- [Status Reporting](status-reporting/SKILL.md)
-- [AI Prompt Engineering](ai-prompt-engineering/SKILL.md)
-
----
-
-## Fidelity / iOS Skills
-
-- [Copilot Prompt Engineering](copilot-prompt-engineering/SKILL.md)
-- [iOS Swift Answering](ios-swift-answering/SKILL.md)
-- [iOS Testing Strategy](ios-testing-strategy/SKILL.md)
-- [SwiftUI Expert Skill](swiftui-expert-skill/SKILL.md)
-- [SwiftUI XFlow Review](swiftui-xflow-review/SKILL.md)
-- [Update SwiftUI APIs](update-swiftui-apis/SKILL.md)
-
----
-
-## Related
 
+- [Shared Skills Index](../../.agents/skills/index.md)
 - [Tooling Map](../../agent-memory/maps/tooling.md)
 - [Commands Index](../commands/index.md)
 - [Prompts Index](../../prompts/index.md)

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

@@ -1 +0,0 @@
-../../../.agents/rules/ios-swift-answering.md

.opencode/skills/ios-testing-strategy/SKILL.md

@@ -1 +0,0 @@
-../../../.agents/rules/ios-testing-strategy.md

.opencode/skills/professional-communication/SKILL.md

@@ -1 +0,0 @@
-../../../.agents/rules/professional-communication.md

.opencode/skills/status-reporting/SKILL.md

@@ -1 +0,0 @@
-../../../.agents/rules/status-reporting.md

.opencode/skills/swiftui-expert-skill

@@ -1 +0,0 @@
-../../.agents/skills/swiftui-expert-skill

.opencode/skills/swiftui-xflow-review/SKILL.md

@@ -1 +0,0 @@
-../../../.agents/rules/swiftui-xflow-review.md

.opencode/skills/update-swiftui-apis

@@ -1 +0,0 @@
-../../.agents/skills/update-swiftui-apis

.opencode/skills/workspace-memory-curation/SKILL.md

@@ -1 +0,0 @@
-../../../.agents/rules/workspace-memory-curation.md

agent-memory/behavior/self-maintenance.md

@@ -19,7 +19,7 @@ The agent must keep the workspace behavior aligned with recurring user correctio
 - Update `.opencode/commands/` for slash-command behavior.
 - Update `prompts/` for reusable drafting shape.
 - Update `.opencode/agents/` and `AGENTS.md` for default agent behavior.
-- Update `.opencode/skills/` for specialized workflows.
+- Update `.agents/skills/` for specialized workflows.
 - Update `agent-memory/` for reusable agent operating rules.
 - Update `project-knowledge/` only when the correction changes project knowledge or project-facing process documentation.
 
@@ -32,4 +32,3 @@ The agent must keep the workspace behavior aligned with recurring user correctio
 - Agent implementation chatter.
 - Generic preference notes that only affect agent behavior.
 - Duplicate summaries of already-correct project facts.
-

agent-memory/maps/tooling.md

@@ -51,11 +51,11 @@ Commands, prompts, skills, workflows, and automation surfaces that make the work
 ## Skills
 
 - Shared skills source: `.agents/skills/`
-- Skills index: `.opencode/skills/index.md`
+- Skills index: `.agents/skills/index.md`
-- Workspace memory curation: `.opencode/skills/workspace-memory-curation/SKILL.md`
+- Workspace memory curation: `.agents/skills/workspace-memory-curation/SKILL.md`
-- Professional communication: `.opencode/skills/professional-communication/SKILL.md`
+- Professional communication: `.agents/skills/professional-communication/SKILL.md`
-- Status reporting: `.opencode/skills/status-reporting/SKILL.md`
+- Status reporting: `.agents/skills/status-reporting/SKILL.md`
-- AI prompt engineering: `.opencode/skills/ai-prompt-engineering/SKILL.md`
+- AI prompt engineering: `.agents/skills/ai-prompt-engineering/SKILL.md`
 
 ---
 

agent-memory/memory/context-maintenance.md

@@ -20,7 +20,7 @@ Keep this workspace useful as living memory instead of a pile of disconnected no
 - Prefer correcting stale context over appending contradictory notes.
 - Keep `project-knowledge/` human-facing and project-facing: write it as an engineer maintaining shared project notes, not as an AI maintaining its own operating instructions.
 - Do not place agent-only logic, output contracts, prompting tactics, evaluation heuristics, or command-behavior rules in `project-knowledge/` unless a human engineer on the project would reasonably want that exact guidance there.
-- Put agent behavior, prompt logic, formatting contracts, and slash-command rules in `agent-memory/`, `.opencode/commands/`, `prompts/`, `.opencode/agents/`, or `.opencode/skills/` instead of `project-knowledge/`.
+- Put agent behavior, prompt logic, formatting contracts, and slash-command rules in `agent-memory/`, `.opencode/commands/`, `prompts/`, `.opencode/agents/`, or `.agents/skills/` instead of `project-knowledge/`.
 - If a canonical note appears in an Obsidian Base, update its frontmatter properties together with the prose content.
 - When changing frontmatter properties on existing canonical notes, prefer Obsidian CLI property operations through `scripts/obsidian/cli.sh` when available so YAML spacing and property formatting stay clean; fall back to direct Markdown edits only when the CLI is unavailable or the operation is unsupported.
 - Keep templates under `project-knowledge/09-templates/` out of real-note Bases by filtering the template folder.
@@ -34,7 +34,7 @@ Keep this workspace useful as living memory instead of a pile of disconnected no
   - `project-knowledge/01-current/work-items.md` for the compact active-work summary
   - `project-knowledge/03-context/` for durable project knowledge
   - `project-knowledge/04-people/` for named person context
-  - `.opencode/commands/`, `prompts/`, `.opencode/agents/`, `.opencode/skills/`, `agent-memory/`, `core/`, or `scripts/` for reusable behavior rules that control how the workspace responds
+  - `.opencode/commands/`, `prompts/`, `.opencode/agents/`, `.agents/skills/`, `agent-memory/`, `core/`, or `scripts/` for reusable behavior rules that control how the workspace responds
 
 ---
 

agent-memory/workflows/workspace-model.md

@@ -54,7 +54,7 @@ When the user corrects a recurring behavior, the workspace should update the fil
 - `.agents/workflows/` for slash commands (with `.opencode/commands/` for compatibility)
 - `prompts/` for reusable drafting templates
 - `.agents/rules/` and `AGENTS.md` for default agent behavior
-- `.agents/skills/` for specialized workflows (with `.opencode/skills/` for compatibility)
+- `.agents/skills/` for specialized workflows. Do not mirror into `.opencode/skills/`; OpenCode discovers `.agents/skills/` directly.
 - `project-knowledge/00-start/` and `project-knowledge/03-context/process/` for project-facing onboarding and process rules
 - `agent-memory/` for agent-specific behavior, learning, promotion, verification, and self-maintenance rules
 

core/memory/operational-memory.md

@@ -80,7 +80,7 @@ Default path patterns:
 ```text
 .opencode/commands/*.md
 .opencode/agents/*.md
-.opencode/skills/*/SKILL.md
+.agents/skills/*/SKILL.md
 prompts/*.md
 agent-memory/**/*.md
 core/**/*.md
@@ -179,6 +179,6 @@ The agent should also identify recurring quality gaps proactively. If an answer
 For technical topics, recurring gaps often belong in:
 
 - domain-specific guidance under `project-knowledge/03-context/`
-- reusable skills under `.opencode/skills/`
+- reusable skills under `.agents/skills/`
 - agent behavior rules under `.opencode/agents/`, `AGENTS.md`, or `agent-memory/`
 - source anchors for official/current documentation

prompts/index.md

@@ -18,4 +18,4 @@ Reusable drafting templates used by workspace commands and agents.
 
 - [Tooling Map](../agent-memory/maps/tooling.md)
 - [Commands Index](../.opencode/commands/index.md)
-- [Skills Index](../.opencode/skills/index.md)
+- [Skills Index](../.agents/skills/index.md)