Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Chief Init

ASecurity

Bootstrap `.chief/project.md` for a Chief-installed project by interviewing the user about their tech stack, dev commands, architecture, and key rules. Use after `/chief-install` (or any time the user wants to set up project-wide context). This is the lazy entry point for `.chief/` — it creates only `project.md`; milestones and rules are created later, on demand.

65 stars
0 votes
0 copies
0 views
Added 9/20/2026
documentationgotestingdatabase

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add thaitype/chief --skill chief-init --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Chief Init?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Chief Init
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thaitype-chief-init/badge)](https://www.skillsdirectory.com/skills/thaitype-chief-init)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: chief-init
description: Bootstrap `.chief/project.md` for a Chief-installed project by interviewing the user about their tech stack, dev commands, architecture, and key rules. Use after `/chief-install` (or any time the user wants to set up project-wide context). This is the lazy entry point for `.chief/` — it creates only `project.md`; milestones and rules are created later, on demand.
---

You are bootstrapping the project's `.chief/project.md`. This is the only thing this skill creates. Milestones, rules, and other `.chief/` content are created later by chief-agent on first need.

## Steps

### 1. Pre-flight checks

1. Verify the framework is installed: `.agents/agents/chief-agent.md` must exist. If missing, tell the user to run `/chief-install` first and stop.
2. Check if `.chief/project.md` already exists.
   - If yes → ask the user: "`.chief/project.md` already exists. Update it / overwrite / cancel?"
   - If overwrite, back up the current file to `.chief/project.md.bak` before proceeding.
   - If update, read the current content first and treat the interview as a refinement pass.
   - If cancel, stop.
3. Create `.chief/` if it does not exist.

### 2. Interview the user

Walk through these topics, one short question at a time. Keep questions focused. Wait for the answer before moving on. Skip a topic if the user says "skip" or "n/a".

- **Project name and one-line summary.**
- **Tech stack** — primary languages, frameworks, runtimes, databases, key libraries.
- **Dev commands** — how to install deps, run dev, run tests, lint, typecheck, build.
- **Architecture overview** — main patterns (e.g. Repository Pattern, Service Layer, hexagonal, monorepo, etc.).
- **Directory structure** — top-level folders and what they hold.
- **Important development rules** — conventions developers must follow (commit style, branch policy, formatting, testing requirements, etc.).

If the user is unsure about a topic, suggest reasonable defaults derived from files you can see in the repo (`package.json`, `pyproject.toml`, `Cargo.toml`, `Makefile`, `README.md`, etc.) and confirm.

### 3. Show a draft and confirm

Print the proposed `.chief/project.md` content as formatted markdown. Then ask once: "Write this to `.chief/project.md`?"

If the user requests changes, apply them and re-confirm. Do not loop more than three rounds — if alignment is hard, write the current draft and tell the user they can edit manually.

### 4. Write the file

Write to `.chief/project.md`. Use this structure (omit empty sections rather than leaving placeholder prose):

```markdown
# Project Configuration

## Project
{name and one-line summary}

## Development Commands
{commands as a list or table}

## Architecture Overview

### Tech Stack
{...}

### Key Architectural Patterns
{...}

### Directory Structure
{...}

### Important Development Rules
{...}
```

### 5. Next steps

Tell the user:

- `.chief/project.md` is now set. chief-agent will read it for project context.
- To start a milestone: `/chief-plan` (creates `.chief/milestone-N/` lazily).
- To run autonomously once a milestone is planned: `/chief-autopilot`.
- Rules can be added later under `.chief/_rules/_standard/`, `_contract/`, `_goal/`, `_verification/` — chief-agent creates the appropriate subfolder on first rule.

## Important rules

- This skill creates **only** `.chief/` (if missing) and `.chief/project.md`. Do not scaffold milestones, rule subfolders, or `_template/`.
- Never overwrite an existing `project.md` without explicit user confirmation; always back up to `.bak` first.
- If `.agents/agents/chief-agent.md` is missing, do not proceed — direct the user to `/chief-install`.
- Keep the interview short. One focused question at a time, no compound questions.
- Reference: a canonical layout example lives at `docs/example-chief/` in the chief repo.

Attribution

thaitypethaitype
View sourceMore from thaitype →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Context Fundamentals

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

179001 votes

release-notes

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.

1301 votes

docs-style-guide

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

11 votes

Caveman Help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

1023330 votes

How It Works

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

929660 votes
View all in documentation →