chore: rename opencode skills

.github/workflows/test-flow-next.yml

@@ -41,12 +41,12 @@ jobs:
 
       - name: Check ralph.sh syntax (Unix)
         if: runner.os != 'Windows'
-        run: bash -n .opencode/skill/flow-next-ralph-init/templates/ralph.sh
+        run: bash -n .opencode/skill/flow-next-opencode-ralph-init/templates/ralph.sh
 
       - name: Check ralph.sh syntax (Windows Git Bash)
         if: runner.os == 'Windows'
         shell: bash
-        run: bash -n .opencode/skill/flow-next-ralph-init/templates/ralph.sh
+        run: bash -n .opencode/skill/flow-next-opencode-ralph-init/templates/ralph.sh
 
       - name: Smoke check flowctl (Unix)
         if: runner.os != 'Windows'

.opencode/command/flow-next/export-context.md

@@ -2,9 +2,9 @@
 description: Export RepoPrompt context for external LLM review
 ---
 
-# IMPORTANT: This command MUST invoke the skill `flow-next-export-context`
+# IMPORTANT: This command MUST invoke the skill `flow-next-opencode-export-context`
 
-The ONLY purpose of this command is to call the `flow-next-export-context` skill. You MUST use that skill now.
+The ONLY purpose of this command is to call the `flow-next-opencode-export-context` skill. You MUST use that skill now.
 
 **Arguments:** $ARGUMENTS
 

.opencode/command/flow-next/impl-review.md

@@ -2,9 +2,9 @@
 description: John Carmack-level implementation review via RepoPrompt or OpenCode
 ---
 
-# IMPORTANT: This command MUST invoke the skill `flow-next-impl-review`
+# IMPORTANT: This command MUST invoke the skill `flow-next-opencode-impl-review`
 
-The ONLY purpose of this command is to call the `flow-next-impl-review` skill. You MUST use that skill now.
+The ONLY purpose of this command is to call the `flow-next-opencode-impl-review` skill. You MUST use that skill now.
 
 **Arguments:** $ARGUMENTS
 

.opencode/command/flow-next/interview.md

@@ -2,9 +2,9 @@
 description: Interview & refine an epic, task, or spec file in-depth
 ---
 
-# IMPORTANT: This command MUST invoke the skill `flow-next-interview`
+# IMPORTANT: This command MUST invoke the skill `flow-next-opencode-interview`
 
-The ONLY purpose of this command is to call the `flow-next-interview` skill. You MUST use that skill now.
+The ONLY purpose of this command is to call the `flow-next-opencode-interview` skill. You MUST use that skill now.
 
 **User input:** $ARGUMENTS
 

.opencode/command/flow-next/plan-review.md

@@ -2,9 +2,9 @@
 description: Carmack-level plan review via RepoPrompt or OpenCode
 ---
 
-# IMPORTANT: This command MUST invoke the skill `flow-next-plan-review`
+# IMPORTANT: This command MUST invoke the skill `flow-next-opencode-plan-review`
 
-The ONLY purpose of this command is to call the `flow-next-plan-review` skill. You MUST use that skill now.
+The ONLY purpose of this command is to call the `flow-next-opencode-plan-review` skill. You MUST use that skill now.
 
 **Arguments:** $ARGUMENTS
 

.opencode/command/flow-next/plan.md

@@ -2,9 +2,9 @@
 description: Draft a clear build plan from a short request
 ---
 
-# IMPORTANT: This command MUST invoke the skill `flow-next-plan`
+# IMPORTANT: This command MUST invoke the skill `flow-next-opencode-plan`
 
-The ONLY purpose of this command is to call the `flow-next-plan` skill. You MUST use that skill now.
+The ONLY purpose of this command is to call the `flow-next-opencode-plan` skill. You MUST use that skill now.
 
 **User request:** $ARGUMENTS
 

.opencode/command/flow-next/ralph-init.md

@@ -2,8 +2,8 @@
 description: Scaffold repo-local Ralph autonomous harness (scripts/ralph/)
 ---
 
-# IMPORTANT: This command MUST invoke the skill `flow-next-ralph-init`
+# IMPORTANT: This command MUST invoke the skill `flow-next-opencode-ralph-init`
 
-The ONLY purpose of this command is to call the `flow-next-ralph-init` skill. You MUST use that skill now.
+The ONLY purpose of this command is to call the `flow-next-opencode-ralph-init` skill. You MUST use that skill now.
 
 Creates `scripts/ralph/` in the current repo.

.opencode/command/flow-next/setup.md

@@ -2,8 +2,8 @@
 description: Optional local install of flowctl CLI and project docs
 ---
 
-# IMPORTANT: This command MUST invoke the skill `flow-next-setup`
+# IMPORTANT: This command MUST invoke the skill `flow-next-opencode-setup`
 
-The ONLY purpose of this command is to call the `flow-next-setup` skill. You MUST use that skill now.
+The ONLY purpose of this command is to call the `flow-next-opencode-setup` skill. You MUST use that skill now.
 
 This is an **optional** setup for power users. Flow-next works without it.

.opencode/command/flow-next/work.md

@@ -2,9 +2,9 @@
 description: Execute a plan end-to-end with checks
 ---
 
-# IMPORTANT: This command MUST invoke the skill `flow-next-work`
+# IMPORTANT: This command MUST invoke the skill `flow-next-opencode-work`
 
-The ONLY purpose of this command is to call the `flow-next-work` skill. You MUST use that skill now.
+The ONLY purpose of this command is to call the `flow-next-opencode-work` skill. You MUST use that skill now.
 
 **User input:** $ARGUMENTS
 

.opencode/plugin/flow-next-ralph-guard.ts

@@ -187,7 +187,7 @@ export default async function (_input: PluginInput): Promise<Hooks> {
         if (subagent !== allowedReviewer) {
           block(
             `BLOCKED: Ralph mode only allows task tool for reviewer '${allowedReviewer}'. ` +
-              "Use the skill tool (flow-next-plan-review / flow-next-work) and do NOT spawn generic tasks.",
+              "Use the skill tool (flow-next-opencode-plan-review / flow-next-opencode-work) and do NOT spawn generic tasks.",
           )
         }
       }

.opencode/skill/flow-next-export-context/SKILL.md → .opencode/skill/flow-next-opencode-export-context/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-export-context
+name: flow-next-opencode-export-context
 description: Export RepoPrompt context for external LLM review (ChatGPT, Claude web, etc.). Use when you want to review code or plans with an external model. Triggers on /flow-next:export-context.
 ---
 

.opencode/skill/flow-next-impl-review/SKILL.md → .opencode/skill/flow-next-opencode-impl-review/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-impl-review
+name: flow-next-opencode-impl-review
 description: John Carmack-level implementation review via RepoPrompt or OpenCode. Use when reviewing code changes, PRs, or implementations. Triggers on /flow-next:impl-review.
 ---
 

.opencode/skill/flow-next-interview/SKILL.md → .opencode/skill/flow-next-opencode-interview/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-interview
+name: flow-next-opencode-interview
 description: Interview user in-depth about an epic, task, or spec file to extract complete implementation details. Use when user wants to flesh out a spec, refine requirements, or clarify a feature before building. Triggers on /flow-next:interview with Flow IDs (fn-1, fn-1.2) or file paths.
 ---
 

.opencode/skill/flow-next-plan-review/SKILL.md → .opencode/skill/flow-next-opencode-plan-review/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-plan-review
+name: flow-next-opencode-plan-review
 description: Carmack-level plan review via RepoPrompt or OpenCode. Use when reviewing Flow epic specs or design docs. Triggers on /flow-next:plan-review.
 ---
 

.opencode/skill/flow-next-plan/SKILL.md → .opencode/skill/flow-next-opencode-plan/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-plan
+name: flow-next-opencode-plan
 description: Create structured build plans from feature requests or Flow IDs. Use when planning features or designing implementation. Triggers on /flow-next:plan with text descriptions or Flow IDs (fn-1, fn-1.2).
 ---
 

.opencode/skill/flow-next-ralph-init/SKILL.md → .opencode/skill/flow-next-opencode-ralph-init/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-ralph-init
+name: flow-next-opencode-ralph-init
 description: Scaffold repo-local Ralph autonomous harness under scripts/ralph/. Use when user runs /flow-next:ralph-init.
 ---
 
@@ -11,7 +11,7 @@ Scaffold repo-local Ralph harness. Opt-in only.
 
 - Only create `scripts/ralph/` in the current repo.
 - If `scripts/ralph/` already exists, stop and ask the user to remove it first.
-- Copy templates from `.opencode/skill/flow-next-ralph-init/templates/` into `scripts/ralph/`.
+- Copy templates from `.opencode/skill/flow-next-opencode-ralph-init/templates/` into `scripts/ralph/`.
 - Copy `flowctl` and `flowctl.py` from `$OPENCODE_DIR/bin/` into `scripts/ralph/`.
 - Set executable bit on `scripts/ralph/ralph.sh`, `scripts/ralph/ralph_once.sh`, and `scripts/ralph/flowctl`.
 
@@ -21,7 +21,7 @@ Scaffold repo-local Ralph harness. Opt-in only.
    ```bash
    ROOT="$(git rev-parse --show-toplevel)"
    OPENCODE_DIR="$ROOT/.opencode"
-   TEMPLATE_DIR="$ROOT/.opencode/skill/flow-next-ralph-init/templates"
+   TEMPLATE_DIR="$ROOT/.opencode/skill/flow-next-opencode-ralph-init/templates"
    ```
 2. Check `scripts/ralph/` does not exist.
 3. Detect available review backends:

.opencode/skill/flow-next-ralph-init/templates/prompt_plan.md → .opencode/skill/flow-next-opencode-ralph-init/templates/prompt_plan.md

@@ -5,7 +5,7 @@ Inputs:
 - PLAN_REVIEW={{PLAN_REVIEW}}
 - REQUIRE_PLAN_REVIEW={{REQUIRE_PLAN_REVIEW}}
 
-Treat the following as the user's exact input to flow-next-plan-review:
+Treat the following as the user's exact input to flow-next-opencode-plan-review:
 `{{EPIC_ID}} --review={{PLAN_REVIEW}}`
 
 Steps:
@@ -23,7 +23,7 @@ Ralph mode rules (must follow):
 - If any rule is violated, output `<promise>RETRY</promise>` and stop.
 
 2) Plan review gate:
-   - Call the skill tool: flow-next-plan-review.
+   - Call the skill tool: flow-next-opencode-plan-review.
    - Follow the workflow in the skill using the exact arguments above.
    - Do NOT stop after loading the skill.
    - For opencode: run reviewer via task tool and require `<verdict>` tag.

.opencode/skill/flow-next-ralph-init/templates/prompt_work.md → .opencode/skill/flow-next-opencode-ralph-init/templates/prompt_work.md

@@ -5,13 +5,13 @@ Inputs:
 - BRANCH_MODE={{BRANCH_MODE_EFFECTIVE}}
 - WORK_REVIEW={{WORK_REVIEW}}
 
-Treat the following as the user's exact input to flow-next-work:
+Treat the following as the user's exact input to flow-next-opencode-work:
 `{{TASK_ID}} --branch={{BRANCH_MODE_EFFECTIVE}} --review={{WORK_REVIEW}}`
 
 ## Steps (execute ALL in order)
 
 **Step 1: Execute task**
-- Call the skill tool: flow-next-work.
+- Call the skill tool: flow-next-opencode-work.
 - Follow the workflow in the skill using the exact arguments above.
 - Do NOT run /flow-next:* as shell commands.
 - Do NOT improvise review prompts; use the skill's review flow.

.opencode/skill/flow-next-rp-explorer/SKILL.md → .opencode/skill/flow-next-opencode-rp-explorer/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-rp-explorer
+name: flow-next-opencode-rp-explorer
 description: Token-efficient codebase exploration using RepoPrompt CLI. Use when user says "use rp to..." or "use repoprompt to..." followed by explore, find, understand, search, or similar actions.
 ---
 

.opencode/skill/flow-next-setup/SKILL.md → .opencode/skill/flow-next-opencode-setup/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-setup
+name: flow-next-opencode-setup
 description: Local install of flowctl CLI and CLAUDE.md/AGENTS.md instructions. Use when user runs /flow-next:setup.
 ---
 

.opencode/skill/flow-next-setup/workflow.md → .opencode/skill/flow-next-opencode-setup/workflow.md

@@ -147,7 +147,7 @@ Notes:
 ## Step 8: Ask about starring
 
 Ask with the **question** tool:
-- **Header**: `Support Flow-Next`
+- **Header**: `Support`
 - **Question**: `Flow-Next is free and open source. Would you like to ⭐ star the repo on GitHub to support the project?`
 - **Options**:
   1. `Yes, star the repo`

.opencode/skill/flow-next-work/SKILL.md → .opencode/skill/flow-next-opencode-work/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-work
+name: flow-next-opencode-work
 description: Execute a Flow epic or task systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan or working through a spec. Triggers on /flow-next:work with Flow IDs (fn-1, fn-1.2).
 ---
 
@@ -154,7 +154,7 @@ Wait for response. Parse naturally — user may reply terse or ramble via voice.
 
 ## Workflow
 
-After setup questions answered, read `.opencode/skill/flow-next-work/phases.md` and execute each phase in order.
+After setup questions answered, read `.opencode/skill/flow-next-opencode-work/phases.md` and execute each phase in order.
 If user chose review:
 - Option 2a: run `/flow-next:impl-review` after Phase 6, fix issues until it passes
 - Option 2b: run `/flow-next:impl-review` with export mode after Phase 6

.opencode/skill/flow-next-work/phases.md → .opencode/skill/flow-next-opencode-work/phases.md

@@ -61,7 +61,7 @@ Detect input type in this order (first match wins):
 
 Based on user's answer from setup questions:
 
-- **Worktree**: use `skill: flow-next-worktree-kit`
+- **Worktree**: use `skill: flow-next-opencode-worktree-kit`
 - **New branch**:
   ```bash
   git checkout main && git pull origin main

.opencode/skill/flow-next-worktree-kit/SKILL.md → .opencode/skill/flow-next-opencode-worktree-kit/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next-worktree-kit
+name: flow-next-opencode-worktree-kit
 description: Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
 ---
 
@@ -10,7 +10,7 @@ Use the manager script for all worktree actions.
 ```bash
 ROOT="$(git rev-parse --show-toplevel)"
 PLUGIN_ROOT="$ROOT/.opencode/skill"
-bash "$PLUGIN_ROOT/flow-next-worktree-kit/scripts/worktree.sh" <command> [args]
+bash "$PLUGIN_ROOT/flow-next-opencode-worktree-kit/scripts/worktree.sh" <command> [args]
 ```
 
 Commands:

.opencode/skill/flow-next/SKILL.md → .opencode/skill/flow-next-opencode/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: flow-next
+name: flow-next-opencode
 description: "Manage .flow/ tasks and epics. Triggers: 'show me my tasks', 'list epics', 'what tasks are there', 'add a task', 'create task', 'what's ready', 'task status', 'show fn-1'. NOT for /flow-next:plan or /flow-next:work."
 ---
 

AGENTS.md

@@ -2,4 +2,4 @@
 
 - OpenCode logs: `~/.local/share/opencode/log/` (tail for live run status)
 - Porting guidance: `sync/PORTING.md` (manual, .opencode is canonical)
-- Ralph template source of truth: `.opencode/skill/flow-next-ralph-init/templates/ralph.sh`
+- Ralph template source of truth: `.opencode/skill/flow-next-opencode-ralph-init/templates/ralph.sh`

CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+## Unreleased
+
+- Rename OpenCode skills to `flow-next-opencode-*` to avoid Claude skill collisions
+- Thanks @gmickel for the contribution
+
 ## 0.2.3
 
 - Canonicalize `.opencode/` (remove legacy plugin/sync paths)

plans/opencode-canonical-switch.md

@@ -13,7 +13,7 @@
 ## Proposed Canonical Layout
 - `.opencode/` contains **everything runtime** needs:
   - `.opencode/bin/flowctl` + `.opencode/bin/flowctl.py` (new)
-  - `.opencode/skill/flow-next-ralph-init/templates/*` (already present)
+- `.opencode/skill/flow-next-opencode-ralph-init/templates/*` (already present)
   - `.opencode/skill/**` (existing)
   - Docs move to repo-level `docs/` (flowctl + ralph docs)
 - `plugins/flow-next/` will be **removed** from installer output and repo after switch. Upstream porting will be manual (no dev copy).
@@ -49,7 +49,7 @@
 ## Required File Changes (checklist)
 - [ ] `.opencode/bin/flowctl` + `.opencode/bin/flowctl.py` added
 - [ ] `.opencode/skill/*` references updated (flowctl path)
-- [ ] `.opencode/skill/flow-next-ralph-init/templates/*` updated
+- [ ] `.opencode/skill/flow-next-opencode-ralph-init/templates/*` updated
 - [ ] `install.sh` updated (copy `.opencode` only)
 - [ ] `README.md` + `docs/` updated for new pathing
 - [ ] `sync/PORTING.md` updated with new canonical rule

sync/PORTING.md

@@ -16,7 +16,7 @@ Goal: keep this OpenCode port aligned with upstream with **manual, minimal edits
    - `.opencode/bin/flowctl`
    - `.opencode/bin/flowctl.py`
 4) If ralph templates change upstream, update:
-   - `.opencode/skill/flow-next-ralph-init/templates/*`
+   - `.opencode/skill/flow-next-opencode-ralph-init/templates/*`
 5) If docs change upstream, update:
    - `docs/*`