Initializes feature development by creating standardized documentation and directory structures based on project inputs.

Install

mkdir -p .claude/skills/init-minhquan2904 && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13842" && unzip -o skill.zip -d .claude/skills/init-minhquan2904 && rm skill.zip

Installs to .claude/skills/init-minhquan2904

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Initialize a new feature — scaffold change directory, generate metadata.yaml and proposal.md. Use when starting a new feature from user description, Confluence pages, or documentation files.
190 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • →Gather feature information and classify input sources.
  • →Collect context from Confluence pages, documentation files, and codebase references.
  • →Scaffold a change directory using `openspec new change`.
  • →Generate `metadata.yaml` with project ID, name, type, and timestamps.
  • →Load context for proposal generation from `artifact_context_modular.yml`.
  • →Determine Feature Profile including mode, entity base class, and service pattern.

How it works

The skill initializes a new feature by collecting user input, scaffolding a change directory, generating `metadata.yaml` and `proposal.md` based on collected context and a determined Feature Profile.

Inputs & outputs

You give it
User description of a feature, Confluence URL, documentation file paths, or codebase references
You get back
A new change directory with `metadata.yaml` and `proposal.md` artifacts

When to use init

  • →Start a new feature ticket
  • →Document initial requirements for a new module
  • →Scaffold boilerplate files for a feature proposal

About init

Collects user requirements from text, Confluence, or code sources. Generates a kebab-case directory and populates it with necessary metadata.yaml and proposal.md artifacts.

Initialize a new feature — scaffold change directory, generate metadata.yaml and proposal.md. Use when starting a new feature from user description, Confluence pages, or documentation files.

When not to use it

  • →When the user has not provided clear input for the feature.
  • →When the task does not involve initializing a new feature or generating `metadata.yaml` and `proposal.md`.
  • →When ignoring the `openspec` CLI for scaffolding.

Limitations

  • →The skill requires a feature name or description as input.
  • →The skill uses the `openspec` CLI for scaffolding.
  • →The skill mandates generating `metadata.yaml` before `proposal.md`.

How it compares

This skill automates the initial setup and documentation for a new feature, ensuring consistent artifact generation and adherence to predefined project standards, unlike a manual feature initiation process.

Compared to similar skills

init side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
init (this skill)08moReviewIntermediate
daily19moNo flagsBeginner
feature-pipeline18moReviewBeginner
planning-with-files23310moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry