Skip to content
Skills Library
AI & agents · Building & coding

init

/init

Set up agnostic-ai in a project by scaffolding the spec directories, picking target AI CLIs, and producing the first generated config. Use when a project has no .agnostic-ai/ directory yet.

Repository
agnostic-ai ↗
Licence
MIT
Last repository change
27.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Set up agnostic-ai in a project by scaffolding the spec directories, picking target AI CLIs, and producing the first generated config. Use when a project has no .agnostic-ai/ directory yet.

Original author description

Set up agnostic-ai in a project by scaffolding the spec directories, picking target AI CLIs, and producing the first generated config. Use when a project has no .agnostic-ai/ directory yet.

How it works

  1. Steps
  2. Notes
Original SKILL.md headings · 27 lines, 267 words
SKILL.md preview
---
name: init
description: Set up agnostic-ai in a project by scaffolding the spec directories, picking target AI CLIs, and producing the first generated config. Use when a project has no .agnostic-ai/ directory yet.
---

# init

Turns a project with no shared AI config into one where a single set of specs drives every tool.

## Steps

1. Confirm the CLI is present: `agnostic-ai --version`. If missing, run the `install` skill first.
2. Check whether the project already has AI config worth keeping: `CLAUDE.md`, `AGENTS.md`, `GEMINI.md`, `.cursor/rules/`, `.github/copilot-instructions.md`. If any exist, stop and use the `import` skill instead; it captures them as specs rather than overwriting them.
3. Scaffold:

   ```bash
   agnostic-ai init --all      # every target, no prompt
   agnostic-ai init --demo     # plus example specs to start from
   ```

   `init` alone opens a target picker when stdin is a TTY. In a non-interactive session, pass `--all` or pipe a list: `echo "claude,codex" | agnostic-ai init`.
4. Ask which AI tools the team actually uses, then narrow `targets:` in `agnostic-ai.yaml` to those. Fewer targets means fewer generated files to review.
5. Write the project's real conventions as rules under `.agnostic-ai/rules/`, one file per rule. Keep each rule to a single concern with a `description` that says when it applies.
6. Run `agnostic-ai sync`, then show the user what appeared with `git status --short`.

## Notes

- `init` writes `gitignore.enabled: true` by default: generated files stay out of git and each contributor runs `sync`. Pass `--gitignore=false` to commit them instead, which suits a team where not everyone has the CLI.
- One spec per file. `agnostic-ai new rule <name>` (also `agent`, `skill`, `hook`, `mcp`) scaffolds the right frontmatter for the kind.
- Never hand-edit a generated file such as `CLAUDE.md` or `.cursor/rules/*.mdc`. The next `sync` overwrites it. Edit the spec under `.agnostic-ai/` instead.

Versions

RepositoryScoreLicence
This page · chemaclass/agnostic-ai100MIT
CodaColaLight/nightmill100Apache-2.0
userKael/rastro100MIT
elalfner/relevo100MIT
abatyuk/okf100MIT
duronext/jig100MIT
sh5623/e2e-rail100MIT
Calvin-LLC/skills100MIT
arxdsilva/ai-loops100MIT

Database snapshot: 13.11.2026 · package version 7192a70aaf99 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100import
    Adopt a project's existing AI config (CLAUDE.md, AGENTS.md, .cursor/rules, and friends) into agnostic-ai specs, then fan it out to every other tool. Use when the project already has config for one AI CLI and should feed the rest.
  • 100init-pipeline
    This skill should be used when the user asks to set up or initialize the subagent-system pipeline for a project ('init pipeline', 'set up the pipeline', 'khoi tao pipeline'). Creates PIPELINE_CONFIG.md and checkpoint scaffolding.
  • 100init-project
    当用户明确要求初始化项目、创建项目指令文件、生成 AGENTS.md,或为已有项目补齐 AI 协作规范时使用。该 Skill 会分析项目结构,并生成或更新适用于当前项目的标准化协作文档与基础目录。
  • 100project-init
    [Utilities] Use when setting up or re-evaluating portable project context end to end: project-config, reference docs, CLAUDE.md, AGENTS.md. One piece only: project-config, docs-manager --mode=init or ai-context-refresh.
  • 100project-init
    [Utilities] Use when setting up or re-evaluating portable project context end to end: project-config, reference docs, CLAUDE.md, AGENTS.md. One piece only: project-config, docs-manager --mode=init or ai-context-refresh.
  • 90Project Scaffolding
    This skill should be used when the user wants to set up Claude for a project, create a CLAUDE.md file, scaffold the .claude directory, initialize an AI workflow, configure a project for Claude, set up dev intelligence, initialize a new project, or do a new project setup.…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.