How do I install the Are Generate skill?

Run npx skillmds@latest add tomevault-io/are-generate in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Are Generate safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Are Generate?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Are Generate free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Are Generate?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Are Generate by tomevault-io — Agent Skill

Name: Are Generate
Author: tomevault-io

File contents

Generate comprehensive documentation for this codebase using agents-reverse-engineer.

Steps

Read version: Read .claude/ARE-VERSION → store as $VERSION. Show the user: agents-reverse-engineer v$VERSION

Run the generate command in the background using run_in_background: true:

npx agents-reverse-engineer@$VERSION generate --backend claude $ARGUMENTS

Monitor progress by polling the latest progress log:
- Wait ~15 seconds (use sleep 15 in Bash), then use Glob to find the latest .agents-reverse-engineer/progress-*.log file, and Read it (use the offset parameter to read only the last ~20 lines for long files)
- Show the user a brief progress update (e.g. "32/96 files analyzed, ~12m remaining")
- Check whether the background task has completed using TaskOutput with block: false
- Repeat until the background task finishes
- Important: Keep polling even if no progress log exists yet (the command takes a few seconds to start writing)
On completion, read the full background task output and summarize:
- Number of files analyzed and any failures
- Number of directories documented
- Any inconsistency warnings from the quality report

This executes a two-phase pipeline:

File Analysis (concurrent): Discovers files, applies filters, then analyzes each source file via AI and writes .sum summary files with YAML frontmatter (content_hash, file_type, purpose, public_interface, dependencies, patterns).
Directory Aggregation (sequential): Generates AGENTS.md per directory in post-order traversal (deepest first, so child summaries feed into parents), and writes CLAUDE.md pointers.

Options:

--dry-run: Preview the plan without making AI calls
--eval: Namespace output by backend.model for side-by-side comparison (e.g., file.ts.claude.haiku.sum, AGENTS.claude.haiku.md)
--concurrency N: Control number of parallel AI calls (default: auto)
--fail-fast: Stop on first file analysis failure
--debug: Show AI prompts and backend details
--trace: Enable concurrency tracing to .agents-reverse-engineer/traces/

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: are-generatedescription: Generate AI-friendly documentation for the entire codebase Use when this capability is needed.---Generate comprehensive documentation for this codebase using agents-reverse-engineer.<execution>Run the generate command in the background and monitor progress in real time.## Steps1. **Read version**: Read `.claude/ARE-VERSION` → store as `$VERSION`. Show the user: `agents-reverse-engineer v$VERSION`2. **Run the generate command in the background** using `run_in_background: true`: ```bash npx agents-reverse-engineer@$VERSION generate --backend claude $ARGUMENTS ```3. **Monitor progress** by polling the latest progress log: - Wait ~15 seconds (use `sleep 15` in Bash), then use **Glob** to find the latest `.agents-reverse-engineer/progress-*.log` file, and **Read** it (use the `offset` parameter to read only the last ~20 lines for long files) - Show the user a brief progress update (e.g. "32/96 files analyzed, ~12m remaining") - Check whether the background task has completed using `TaskOutput` with `block: false` - Repeat until the background task finishes - **Important**: Keep polling even if no progress log exists yet (the command takes a few seconds to start writing)4. **On completion**, read the full background task output and summarize: - Number of files analyzed and any failures - Number of directories documented - Any inconsistency warnings from the quality reportThis executes a two-phase pipeline:1. **File Analysis** (concurrent): Discovers files, applies filters, then analyzes each source file via AI and writes `.sum` summary files with YAML frontmatter (`content_hash`, `file_type`, `purpose`, `public_interface`, `dependencies`, `patterns`).2. **Directory Aggregation** (sequential): Generates `AGENTS.md` per directory in post-order traversal (deepest first, so child summaries feed into parents), and writes `CLAUDE.md` pointers.**Options:**- `--dry-run`: Preview the plan without making AI calls- `--eval`: Namespace output by backend.model for side-by-side comparison (e.g., `file.ts.claude.haiku.sum`, `AGENTS.claude.haiku.md`)- `--concurrency N`: Control number of parallel AI calls (default: auto)- `--fail-fast`: Stop on first file analysis failure- `--debug`: Show AI prompts and backend details- `--trace`: Enable concurrency tracing to `.agents-reverse-engineer/traces/`</execution>---> Converted and distributed by [TomeVault](https://tomevault.io/claim/geoloeg-ist) — claim your Tome and manage your conversions.

Frequently asked questions

Are Generate