Agent skill

Compile Human

by Gerstep in Gerstep/HumanCompiler

Deep interview a human and compile them into an installable AI agent plugin.

No licenceAuto-check: notesAgent Workflows

Install Compile Human

skills CLI
$ npx skills add Gerstep/HumanCompiler --skill compile-human -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Gerstep/HumanCompiler compile-human --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Gerstep/HumanCompiler.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/compile-human .claude/skills/compile-human && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
compile-human
GitHub stars
154
Token cost
~1.3k tokens
SKILL.md length
506 words
Files
10
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Deep interview a human and compile them into an installable AI agent plugin.

  • Works in 4 steps: Ask: "Welcome to HumanCompiler. I'm… → Wait for their name → Run bun run… → …
  • Tasks that involve Hooks and plugins
  • SKILL.md covers Command Routing, Interview Flow, After All Phases Complete and Important Guidelines
  • Calls bun and claude

What it does

Compile Human is an agent skill from Gerstep/HumanCompiler. Deep interview a human and compile them into an installable AI agent plugin. Conducts comprehensive behavioral interviews, analyzes work artifacts via MCP tools, and generates a Claude Code plugin that embodies the person.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files (for example `interview-guide.md`, `phase-instructions/01-identity.md` and `phase-instructions/02-communication.md`).

It sits in Agent Workflows, covering Hooks and plugins, Interview preparation and MCP servers. The repository describes itself as: Compile humans into AI agents — a Claude Code plugin that conducts deep behavioral interviews and generates installable agent plugins.

When your agent uses it

  • Tasks that involve Hooks and plugins
  • Tasks that involve Interview preparation
  • Tasks that involve MCP servers

Example prompts

  • “/compile-human”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep, Bash, AskUserQuestion, Task

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Ask: "Welcome to HumanCompiler. I'm going to interview you deeply to create an AI agent that thinks, communicates, and decides like you…
  2. Wait for their name
  3. Run bun run scripts/profile-manager-cli.ts init "" to create the profile
  4. Begin Phase 1 (see interview flow below)

What it can do on your machine

Read from SKILL.md and the folder at commit 88b5ca0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Glob
    • Grep
    • Bash
    • AskUserQuestion
    • Task

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bun
    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Compile Human loads about 1.3k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 506 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Glob, Grep, Bash, AskUserQuestion, Task

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 506 words (~1,323 tokens).

“You are the HumanCompiler orchestrator. Your job is to conduct a deep interview with a human, build a comprehensive behavioral profile, and generate a Claude Code plugin that embodies them as an AI agent.”

— opening of SKILL.md by Gerstep
name
compile-human
allowed-tools
Read, Write, Edit, Glob, Grep, Bash, AskUserQuestion, Task
argument-hint
resume|status|generate
disable-model-invocation
true
model
opus

Read the full SKILL.md on GitHub

Files

SKILL.md and 9 other files in skills/compile-human of Gerstep/HumanCompiler.

  • SKILL.md
  • interview-guide.md
  • phase-instructions/01-identity.md
  • phase-instructions/02-communication.md
  • phase-instructions/03-decision-making.md
  • phase-instructions/04-domain-expertise.md
  • phase-instructions/05-work-patterns.md
  • phase-instructions/06-edge-cases.md
  • phase-instructions/07-artifact-analysis.md
  • phase-instructions/08-calibration.md

Open the folder on GitHubat commit 88b5ca0

Compare with similar skills

Compile Human next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Compile Human compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Compile Human this skillGerstep/HumanCompiler154—~1.3kAutomated safety check: NotesNone
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
OpenpetsOpenPetsHQ/openpets1.3k—~2.1kAutomated safety check: PassMIT
Claude Automation Recommenderanthropics/claude-plugins-official37k3 repos~2.7kAutomated safety check: NotesApache-2.0
Mistral Vibe Plugin Creatormistralai/mistral-vibe5.1k—~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Openpets

    OpenPetsHQ/openpets

    A skill your agent uses whenever the user wants to build, extend, debug, test, validate, locally load, package, or publish an OpenPets plugin; work with the OpenPets Plugin SDK v3, plugin manifest…

    1.3k GitHub stars~2.1k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Claude Automation Recommender

    anthropics/claude-plugins-official

    Official

    Scans a codebase and suggests which Claude Code hooks, subagents, skills, plugins and MCP servers fit its stack, without changing any files.

    37k GitHub starsUsed in 3 repos~2.7k tokens
    Agent WorkflowsAuto-check: notes
  • Mistral Vibe Plugin Creator

    mistralai/mistral-vibe

    Official

    Shows how to build a Vibe plugin package in the Agent Plugins 1.0 format, with a plugin.json manifest and optional skills, MCP servers, hooks and other components.

    5.1k GitHub stars~3.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.

    7.2k GitHub stars~5.2k tokensUpdated today
    Agent WorkflowsAuto-check: notes

Questions about Compile Human

What does Compile Human do?

Deep interview a human and compile them into an installable AI agent plugin. Compile Human is an agent skill from Gerstep/HumanCompiler. Deep interview a human and compile them into an installable AI agent plugin.

When should I use Compile Human?

Compile Human fits situations like: tasks that involve Hooks and plugins; tasks that involve Interview preparation; tasks that involve MCP servers.

How do I install Compile Human in Claude Code?

Run `npx skills add Gerstep/HumanCompiler --skill compile-human -a claude-code`. Or copy the skill folder (skills/compile-human in Gerstep/HumanCompiler) into .claude/skills/compile-human in your project. Claude Code loads it when a task matches its description.

How do I install Compile Human in Codex?

Run `npx skills add Gerstep/HumanCompiler --skill compile-human -a codex`. Or copy the skill folder (skills/compile-human in Gerstep/HumanCompiler) into .agents/skills/compile-human in your project. Codex loads it when a task matches its description.

Can I use Compile Human in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Gerstep/HumanCompiler --skill compile-human -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compile-human, .gemini/skills/compile-human, .github/skills/compile-human and .opencode/skills/compile-human in your project.

What does Compile Human need to run?

Going by SKILL.md and its folder, Compile Human needs the command-line tools its instructions call (bun and claude). Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, Bash, AskUserQuestion, Task.

Does Compile Human access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Compile Human safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Compile Human use?

No licence was found for Compile Human or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Compile Human use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Compile Human?

Skills that share tags, products or a category with Compile Human: MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars), Crush Configuration (charmbracelet/crush, 29k stars), Openpets (OpenPetsHQ/openpets, 1.3k stars) and Claude Automation Recommender (anthropics/claude-plugins-official, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Compile Human?

Gerstep (a GitHub user) maintains it in Gerstep/HumanCompiler, which has 154 GitHub stars. The repository was last updated on February 17, 2026.

Source: Gerstep/HumanCompiler on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.