How do I choose plan vs impl?

Use plan to export a plan review context; use impl to export the implementation review context for the current branch.

Can I use this with external LLMs?

Yes. The export is intended for external models like ChatGPT Pro or Claude web to review code or plans, then you can implement feedback back in your repo.

flow-next-export-context

npx machina-cli add skill gmickel/gmickel-claude-marketplace/flow-next-export-context --openclaw

Files (1)

SKILL.md

2.9 KB

Export Context Mode

Build RepoPrompt context and export to a markdown file for use with external LLMs (ChatGPT Pro, Claude web, etc.).

Use case: When you want Carmack-level review but prefer to use an external model.

CRITICAL: flowctl is BUNDLED — NOT installed globally. which flowctl will fail (expected). Always use:

FLOWCTL="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl"
$FLOWCTL <command>

Input

Arguments: $ARGUMENTS Format: <type> <target> [focus areas]

Types:

plan <epic-id> - Export plan review context
impl - Export implementation review context (current branch)

Examples:

/flow-next:export-context plan fn-1 focus on security
/flow-next:export-context impl focus on the auth changes

Setup

FLOWCTL="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl"
REPO_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"

Workflow

Step 1: Determine Type

Parse arguments to determine if this is a plan or impl export.

Step 2: Gather Content

For plan export:

$FLOWCTL show <epic-id> --json
$FLOWCTL cat <epic-id>

For impl export:

git branch --show-current
git log main..HEAD --oneline 2>/dev/null || git log master..HEAD --oneline
git diff main..HEAD --name-only 2>/dev/null || git diff master..HEAD --name-only

Step 3: Setup RepoPrompt

eval "$($FLOWCTL rp setup-review --repo-root "$REPO_ROOT" --summary "<summary based on type>" --create)"

Step 4: Augment Selection

$FLOWCTL rp select-get --window "$W" --tab "$T"

# Add relevant files
$FLOWCTL rp select-add --window "$W" --tab "$T" <files>

Step 5: Build Review Prompt

Get builder's handoff:

$FLOWCTL rp prompt-get --window "$W" --tab "$T"

Build combined prompt with review criteria (same as plan-review or impl-review).

Set the prompt:

cat > /tmp/export-prompt.md << 'EOF'
[COMBINED PROMPT WITH REVIEW CRITERIA]
EOF

$FLOWCTL rp prompt-set --window "$W" --tab "$T" --message-file /tmp/export-prompt.md

Step 6: Export

OUTPUT_FILE=~/Desktop/review-export-$(date +%Y%m%d-%H%M%S).md
$FLOWCTL rp prompt-export --window "$W" --tab "$T" --out "$OUTPUT_FILE"
open "$OUTPUT_FILE"

Step 7: Inform User

Exported review context to: $OUTPUT_FILE

The file contains:
- Full file tree with selected files marked
- Code maps (signatures/structure)
- Complete file contents
- Review prompt with Carmack-level criteria

Paste into ChatGPT Pro, Claude web, or your preferred LLM.
After receiving feedback, return here to implement fixes.

Note

This skill is for manual external review only. It does not work with Ralph autonomous mode (no receipts, no status updates).

Source

git clone https://github.com/gmickel/gmickel-claude-marketplace/blob/main/plugins/flow-next/skills/flow-next-export-context/SKILL.md

View on GitHub

Overview

Exports a complete RepoPrompt context to a markdown file for external LLM review (ChatGPT Pro, Claude web, etc.). Supports plan exports and implementation exports, guiding you through gathering content, building the review prompt, and exporting for external critique.

How This Skill Works

You trigger an export by choosing plan or impl. The skill gathers content using FlowCTL and git commands, then configures a RepoPrompt with rp setup-review. You augment the selection, build the review prompt, set it, and finally export it to a markdown file for external review.

When to Use It

You want Carmack-level critique but prefer an external model (ChatGPT Pro, Claude web) to review your work.
You need to export a plan review context for an epic (plan <epic-id>).
You need to export an implementation review context for the current branch (impl).
You want a complete, shareable markdown export that includes file tree, code maps, and full file contents.
You will paste the export into an external LLM and implement fixes based on the feedback.

Quick Start

Step 1: Set FLOWCTL to the plugin script path and determine REPO_ROOT as described in the SKILL.
Step 2: Run /flow-next:export-context plan <epic-id> or /flow-next:export-context impl with optional focus.
Step 3: Open the exported Markdown file on your machine and apply external feedback.

Best Practices

Use the /flow-next:export-context trigger to start the flow.
Verify FLOWCTL path and the repo root setup as shown in the Skill instructions.
Choose the correct type (plan or impl) and provide any focus areas.
Before exporting, augment the selection with rp select-get and rp select-add to include relevant files.
Open and review the generated Markdown file, then paste into your external LLM and iterate with feedback.

Example Use Cases

Export a plan review context: /flow-next:export-context plan fn-1 focus on security
Export an implementation review for the current branch: /flow-next:export-context impl focus on the auth changes
Save the export to Desktop as review-export-YYYYMMDD-HHMMSS.md
Paste into ChatGPT Pro or Claude web for Carmack-level critique
Use the feedback to implement fixes in the repository

Frequently Asked Questions

Add this skill to your agents