flow-next-export-context
Exports repository context to markdown for review by external LLMs.
Install
mkdir -p .claude/skills/flow-next-export-context && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7324" && unzip -o skill.zip -d .claude/skills/flow-next-export-context && rm skill.zipInstalls to .claude/skills/flow-next-export-context
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Export RepoPrompt context to a markdown file for review with an external LLM (ChatGPT, Claude web, etc.). Use when you want Carmack-level review but prefer an external model. Triggers on "export context", "export for external review", "export plan for ChatGPT", "export impl review context", "review with an external model", "export review context".Key capabilities
- →Bundle implementation context from Git
- →Parse project structure into reviewable markdown
- →Generate structured prompts for external LLMs
- →Filter context by specific focus areas
How it works
Collects project state, branch logs, and implementation plans using local scripts and compiles them into a formatted Markdown document suitable for external model input.
Inputs & outputs
When to use flow-next-export-context
- →Export current implementation for external review
- →Create a markdown file of the current plan
- →Review branch changes with an external model
About this skill
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.
Preamble
CRITICAL: flowctl is BUNDLED — NOT installed globally. which flowctl will fail (expected). Define once; subsequent blocks use $FLOWCTL:
FLOWCTL="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl"
[ -x "$FLOWCTL" ] || FLOWCTL=".flow/bin/flowctl"
Input
Arguments: $ARGUMENTS
Format: <type> <target> [focus areas]
Types:
plan <spec-id>- Export plan review contextimpl- Export implementation review context (current branch)
This skill is phrase-triggered (no slash command) — invoke it by asking in natural language; the host agent parses <type> <target> [focus areas] from the request.
Examples:
- "export context for plan fn-1, focus on security"
- "export impl review context, focus on the auth changes"
Setup
REPO_ROOT="$(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 <spec-id> --json
$FLOWCTL cat <spec-id>
For impl export:
git branch --show-current
git log main..HEAD --oneline 2>/dev/null || git log master..HEAD --oneline
git diff main..HEAD --name-only 2>/dev/null || git diff master..HEAD --name-only
Step 3: Setup RepoPrompt
eval "$($FLOWCTL rp setup-review --repo-root "$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 (file composition — no content re-typing)
Path-persistence rule: bash vars do not survive across tool calls. The prompt path is composed once as a literal and typed verbatim in every block that touches it — ${TMPDIR:-/tmp}/flow-export-prompt-<target>-<agent-chosen 4-char suffix>.md. A run that carries the path in a shell variable across tool calls has broken this: the later block writes to an empty path.
Build the prompt by deterministic composition — the handoff is captured via redirection, never pasted into a heredoc; only the static review criteria (same criteria as plan-review or impl-review) are typed, once, in the quoted heredoc:
PROMPT_FILE="${TMPDIR:-/tmp}/flow-export-prompt-<target>-<suffix>.md" # literal path
# 1. Builder handoff — captured via redirection, never re-typed
$FLOWCTL rp prompt-get --window "$W" --tab "$T" > "$PROMPT_FILE"
# 2. Review criteria (static, quoted heredoc — same criteria block as
# plan-review or impl-review, per the export type)
cat >> "$PROMPT_FILE" << 'EOF'
<review criteria — static block>
EOF
$FLOWCTL rp prompt-set --window "$W" --tab "$T" --message-file "$PROMPT_FILE"
Done when
$PROMPT_FILEnames the same literal path in all three commands above.- The builder handoff reached the file by redirection from
flowctl rp prompt-get. A run that reconstructs that content inside a heredoc has broken this. - The only typed content is the static review criteria block for this export type, appended once via the quoted heredoc.
Step 6: Export
OUTPUT_FILE=~/Desktop/review-export-$(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 manual-only. It produces no receipts and no status updates, so an autonomous Ralph invocation is declined rather than served — a run that reports success to a Ralph caller has broken this.
Done when
- The run ended with
flowctl rp prompt-exportto a timestamped output file, and told the user that exact path plus what the file contains.
When not to use it
- →When security policies forbid sharing code with third-party LLMs
- →If the repository is too large to fit into an external LLM's context window
Prerequisites
Limitations
- →Requires flowctl environment
- →Manual review of exported content required for privacy
How it compares
It produces a structured, context-rich summary specifically tailored for external model review rather than raw code dumps.
Compared to similar skills
flow-next-export-context side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| flow-next-export-context (this skill) | 1 | 2mo | Review | Intermediate |
| docs-review | 10 | 7mo | No flags | Beginner |
| claude-md-improver | 21 | 6mo | Review | Beginner |
| backend-to-frontend-handoff-docs | 3 | 6mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by gmickel
View all by gmickel →You might also like
docs-review
metabase
Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.
claude-md-improver
anthropics
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
backend-to-frontend-handoff-docs
davila7
Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.
readme
sickn33
When the user wants to create or update a README.md file for a project. Also use when the user says 'write readme,' 'create readme,' 'document this project,' 'project documentation,' or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
doc-gen
phodal
Generate comprehensive documentation from code
generate-verified-docs
quran
Generates audit-grade, hallucination-free documentation from codebase features with full traceability. Use when documenting features, creating technical specs, or generating verified documentation with code references.