Config Export
Export CLAUDE.md and ai-context/ into Copilot, Gemini, and Cursor instruction files with dry-run preview and explicit write confirmation.
Overview
config-export is an agent skill most often used in Build agent-tooling (also Validate scope and Ship review handoffs) that exports CLAUDE.md and ai-context/ to Copilot, Gemini, and Cursor formats.
Install
npx skills add https://github.com/fearovex/claude-config --skill config-exportWhat is this skill?
- Reads CLAUDE.md plus any present `ai-context/` into an in-context bundle—never modifies source files
- User selects one or more targets: GitHub Copilot, Google Gemini, Cursor rules
- LLM transformation with dry-run preview; writes only after explicit user confirmation
- Guard when no CLAUDE.md: offers `/project-setup` (recommended) or minimal SDD Copilot bootstrap
- Triggers: `/config-export`, export config, copilot instructions, gemini config, cursor rules
- 3 target assistant families: GitHub Copilot, Google Gemini, Cursor
Adoption & trust: 1 installs on skills.sh; 1 GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You maintain rich Claude project rules but Copilot, Gemini, and Cursor each expect different instruction file shapes and locations.
Who is it for?
Solo builders standardizing on CLAUDE.md who also ship with Copilot, Cursor, or Gemini and want one export ritual.
Skip if: Projects with no CLAUDE.md and no intent to run project-setup or SDD bootstrap, or teams that forbid generated editor config files.
When should I use this skill?
User runs `/config-export`, asks to export config, or wants copilot instructions, gemini config, or cursor rules from CLAUDE.md.
What do I get? / Deliverables
You preview tool-specific instruction files and, after confirmation, write them to canonical paths without changing CLAUDE.md or ai-context/ sources.
- Dry-run preview of generated instruction files
- Confirmed writes to canonical Copilot/Gemini/Cursor paths
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Agent-tooling shelf fits transforming one canonical Claude config into multi-tool instruction surfaces without editing sources. config-export is tooling that keeps assistants aligned after you have CLAUDE.md—primary home is build-time agent setup, not marketing or ops monitoring.
Where it fits
Export constraints so Cursor-assisted prototyping matches the scoped CLAUDE.md decisions.
Regenerate Copilot and Cursor files after expanding ai-context/ architecture notes.
Mirror coding standards into Gemini instructions for documentation passes.
Refresh Copilot instructions before external review so suggestions follow project gates.
How it compares
Skill-side exporter from Claude canonical config—not an MCP server and not manual copy-paste into three formats.
Common Questions / FAQ
Who is config-export for?
Developers who already use or plan CLAUDE.md plus ai-context/ and need equivalent rules for Copilot, Gemini, or Cursor.
When should I use config-export?
After scaffolding CLAUDE.md during Build agent-tooling, when onboarding a teammate on Cursor during Validate scope, or before Ship when you want review tools to share the same constraints.
Is config-export safe to install?
It only writes after your confirmation and does not edit CLAUDE.md; review the Security Audits panel on this page and inspect dry-run output before approving writes.
SKILL.md
READMESKILL.md - Config Export
# config-export > Exports CLAUDE.md and ai-context/ to tool-native instruction files for GitHub Copilot, Google Gemini, and Cursor. **Triggers**: `/config-export`, export config, copilot instructions, gemini config, cursor rules --- ## Purpose `config-export` reads the project's Claude configuration (`CLAUDE.md` and any present `ai-context/` files) into an in-context bundle, lets the user select one or more target AI assistants, generates tool-specific instruction files via LLM transformation, shows a dry-run preview, and writes the confirmed files to their canonical locations. It never modifies source files and never writes without explicit user confirmation. --- ## Process ### Step 1 — Source collection **Guard — no CLAUDE.md:** If no `CLAUDE.md` exists in the current working directory, present the user with two paths: ``` No CLAUDE.md found in the current directory. Choose an option: 1. project-setup first — run /project-setup to scaffold CLAUDE.md + ai-context/ in this project, then re-run /config-export (recommended for new projects with SDD workflow) 2. SDD bootstrap — generate a minimal .github/copilot-instructions.md from the global SDD template only (no project-specific stack or conventions) Enter 1 or 2 (or press Enter to cancel): ``` - If the user selects **1**: emit `Run /project-setup, then re-run /config-export` and stop. No files are written. - If the user selects **2**: proceed using the global SDD methodology as the sole source bundle (skip ai-context/ collection; note "No project CLAUDE.md — bootstrap mode" in transformation context). - If the user cancels: emit `Export cancelled — no files written` and stop. **Guard — no ai-context/:** If no `ai-context/` directory is present, emit: ``` WARNING: ai-context/ not found — export quality will be lower; only CLAUDE.md will be used as source ``` Continue; `CLAUDE.md` alone is sufficient. **Read and bundle source files in priority order:** | # | File | Required? | Behavior when absent | | --- | ---------------------------- | --------- | -------------------------------------------------------------------- | | 1 | `CLAUDE.md` | Yes | Halt (see guard above) | | 2 | `ai-context/stack.md` | No | Skip; note "stack.md not available" in transformation context | | 3 | `ai-context/architecture.md` | No | Skip; note "architecture.md not available" in transformation context | | 4 | `ai-context/conventions.md` | No | Skip; note "conventions.md not available" in transformation context | | 5 | `ai-context/known-issues.md` | No | Skip silently if absent | All present files are read into the in-context bundle before any transformation begins. --- ### Step 2 — Target selection **If the user provided a target as a CLI argument** (e.g., `/config-export copilot`), skip the interactive menu and proceed directly to Step 3 with that target. **Otherwise, present the target menu:** ``` Available export targets: 1. copilot → .github/copilot-instructions.md 2. gemini → GEMINI.md 3. cursor → .cursor/rules/conventions.mdc → .cursor/rules/stack.mdc → .cursor/rules/architecture.mdc Enter targets (comma-separated numbers or names, or "all"): ``` **Claude target rejection:** If the user requests target `claude` or `CLAUDE.md`, respond with: ``` The Claude target is not supported in V1 — use /project-update to refres