Merge pull request #39 from first-fluke/chore/update-oh-my-agent

chore(deps): update oh-my-agent skills

Author: gracefullight

.agents/agents/backend-engineer.md

@@ -10,7 +10,7 @@ You are a Backend Specialist. Detect the project's language and framework from p
 ## Execution Protocol
 
 Follow the vendor-specific execution protocol:
-- Write results to `.agents/results/result-backend.md`
+- Write results to project root `.agents/results/result-backend.md` (orchestrated: `result-backend-{sessionId}.md`)
 - Include: status, summary, files changed, acceptance criteria checklist
 
 ## Charter Preflight (MANDATORY)

.agents/agents/db-engineer.md

@@ -10,7 +10,7 @@ You are a Database Specialist.
 ## Execution Protocol
 
 Follow the vendor-specific execution protocol:
-- Write results to `.agents/results/result-db.md`
+- Write results to project root `.agents/results/result-db.md` (orchestrated: `result-db-{sessionId}.md`)
 - Include: status, summary, files changed, acceptance criteria checklist
 
 ## Charter Preflight (MANDATORY)

.agents/agents/debug-investigator.md

@@ -10,7 +10,7 @@ You are a Debug Specialist.
 ## Execution Protocol
 
 Follow the vendor-specific execution protocol:
-- Write results to `.agents/results/result-debug.md`
+- Write results to project root `.agents/results/result-debug.md` (orchestrated: `result-debug-{sessionId}.md`)
 - Include: status, summary, files changed, acceptance criteria checklist
 
 ## Charter Preflight (MANDATORY)

.agents/agents/frontend-engineer.md

@@ -10,7 +10,7 @@ You are a Frontend Specialist.
 ## Execution Protocol
 
 Follow the vendor-specific execution protocol:
-- Write results to `.agents/results/result-frontend.md`
+- Write results to project root `.agents/results/result-frontend.md` (orchestrated: `result-frontend-{sessionId}.md`)
 - Include: status, summary, files changed, acceptance criteria checklist
 
 ## Charter Preflight (MANDATORY)

.agents/agents/mobile-engineer.md

@@ -10,7 +10,7 @@ You are a Mobile Specialist.
 ## Execution Protocol
 
 Follow the vendor-specific execution protocol:
-- Write results to `.agents/results/result-mobile.md`
+- Write results to project root `.agents/results/result-mobile.md` (orchestrated: `result-mobile-{sessionId}.md`)
 - Include: status, summary, files changed, acceptance criteria checklist
 
 ## Charter Preflight (MANDATORY)

.agents/agents/pm-planner.md

@@ -10,7 +10,7 @@ You are a Product Manager.
 ## Execution Protocol
 
 Follow the vendor-specific execution protocol:
-- Write results to `.agents/results/result-pm.md`
+- Write results to project root `.agents/results/result-pm.md` (orchestrated: `result-pm-{sessionId}.md`)
 - Include: status, summary, files changed, acceptance criteria checklist
 
 ## Charter Preflight (MANDATORY)

.agents/agents/qa-reviewer.md

@@ -10,7 +10,7 @@ You are a QA Specialist. Review code changes for quality and security.
 ## Execution Protocol
 
 Follow the vendor-specific execution protocol:
-- Write results to `.agents/results/result-qa.md`
+- Write results to project root `.agents/results/result-qa.md` (orchestrated: `result-qa-{sessionId}.md`)
 - Include: status, summary, files changed, acceptance criteria checklist
 
 ## Charter Preflight (MANDATORY)

.agents/config/user-preferences.yaml .agents/oma-config.yaml.agents/config/user-preferences.yaml renamed to .agents/oma-config.yaml

@@ -1,17 +1,22 @@
+---
+trigger: always_on
+description: Response language rules for agents and workflows
+---
+
 # i18n Guide — Response Language Rules
 
-Single source of truth for agent/workflow response language handling.
+Rules for determining and applying response language across agents and workflows.
 
 ## Language Resolution
 
 Response language is determined by the following priority:
 
 1. **User prompt language** — if the user writes in a specific language, respond in that language
-2. **`user-preferences.yaml`** — `language` field in `.agents/config/user-preferences.yaml`
+2. **`oma-config.yaml`** — `language` field in `.agents/oma-config.yaml`
 3. **Fallback** — English (en) if neither of the above is set
 
 ```yaml
-# .agents/config/user-preferences.yaml
+# .agents/oma-config.yaml
 language: ko  # ko, en, ja, zh, ...
 ```
 
@@ -46,13 +51,14 @@ language: ko  # ko, en, ja, zh, ...
 3. **Inline code (`backtick`) is never translated**
 4. **Parenthetical supplement allowed** — for unfamiliar terms, use `translated(original)` format once
 5. **Register consistency** — match the target language's appropriate register for the context
+6. **Translation tasks** — for translating UI strings, docs, or marketing copy, use the `/oma-translator` skill
 
 ## Workflow Integration
 
 All workflows follow these rules. The following line in existing workflows references this guide:
 
 ```
-- **Response language follows `language` setting in `.agents/config/user-preferences.yaml` if configured.**
+- **Response language follows `language` setting in `.agents/oma-config.yaml` if configured.**
 ```
 
 ## Subagent Behavior

.agents/rules/i18n-guide.md

@@ -8,25 +8,35 @@ Use file-based I/O for coordination. Write results to `.agents/results/`.
 
 If Serena MCP is available, you may also use `read_memory`/`write_memory`/`edit_memory`.
 
+### Path Resolution (CRITICAL)
+
+All result, progress, and state files MUST be written to the **project root** `.agents/` directory — never to a subdirectory's `.agents/`.
+
+- **Project root** = the git repository root (where `.git` exists)
+- **Session-scoped naming**: when running under an orchestration session, append session ID as suffix:
+  - `result-{agent-id}-{sessionId}.md` (e.g., `result-frontend-session-20260405-100835.md`)
+  - `progress-{agent-id}-{sessionId}.md`
+- **Manual (non-orchestrated) runs**: no suffix — `result-{agent-id}.md`
+
 ## On Start
 
 1. Read `.agents/results/task-board.md` (or `read_memory("task-board.md")`) to confirm your assigned task
-2. Create `.agents/results/progress-{agent-id}.md` with initial status
+2. Create `.agents/results/progress-{agent-id}[-{sessionId}].md` with initial status
 
 ## During Execution
 
-- Periodically update `progress-{agent-id}.md` with current state
+- Periodically update `progress-{agent-id}[-{sessionId}].md` with current state
 - Include: action taken, current status, files created/modified
 
 ## On Completion
 
-- Create `.agents/results/result-{agent-id}.md` with final result including:
+- Create `.agents/results/result-{agent-id}[-{sessionId}].md` with final result including:
   - Status: `completed` or `failed`
   - Summary of work done
   - Files created/modified
   - Acceptance criteria checklist
 
 ## On Failure
 
-- Still create `result-{agent-id}.md` with Status: `failed`
+- Still create `result-{agent-id}[-{sessionId}].md` with Status: `failed`
 - Include detailed error description and what remains incomplete