Skip to main content
skill CX Codex

openspec-propose · lis186 — Claude Code skill: a full change proposal in one step

This skill turns a short description into a complete change proposal: proposal.md, design.md and tasks.md. Handy when you want a plan before writing code.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add lis186/ccxray --skill openspec-propose -a claude-code
Open on GitHub

What openspec-propose does

Give the skill a name in kebab-case or just describe what you want to build. It scaffolds the change under openspec/changes/<name>/ with an .openspec.yaml file, then walks the artifact chain: proposal.md covering what and why, design.md covering how, tasks.md listing the implementation steps.

The build order comes from the CLI, not from guesswork. The skill runs openspec status --change "<name>" --json, reads the applyRequires array and follows dependencies. Per-artifact guidance arrives via openspec instructions <artifact-id> --change "<name>" --json, which supplies the template, the rules and the output path. TodoWrite tracks progress, and each file is checked for existence before the next one starts.

An installed openspec CLI is required — every step calls into it. If a change with that name already exists, the skill asks whether to continue it or start fresh. Once the required artifacts are done, it points you at /opsx:apply to begin implementation.

What it helps with

  • turn a rough feature idea into proposal, design and task files
  • derive a kebab-case change name from a plain description
  • order artifacts by their dependencies instead of guessing
  • confirm every artifact needed for implementation exists
  • resume an existing change rather than creating a duplicate

Example prompts for the agent

  • I want to add email login — draft a change proposal for it
  • Create the add-user-auth change and generate all its artifacts
  • What else is needed before this change is ready to implement?

How to install openspec-propose

1Skills CLI (Vercel)

npx skills add lis186/ccxray --skill openspec-propose -a claude-code

2Manually: put the files in place

~/.claude/skills/openspec-propose/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/openspec-propose/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about openspec-propose

How do I install openspec-propose in Claude Code?

Run npx skills add lis186/ccxray --skill openspec-propose -a claude-code. The skill lands at ~/.claude/skills/openspec-propose/SKILL.md.

What does openspec-propose do?

It creates an OpenSpec change and generates every artifact in one pass: proposal.md, design.md and tasks.md. The result is a set ready for implementation.

What does the skill need to run?

The openspec CLI has to be installed. The skill uses it to scaffold the change directory, learn the artifact order and fetch templates.

Source text

SKILL.md · MIT
---
name: openspec-propose
description: Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
license: MIT
compatibility: Requires openspec CLI.
metadata:
  author: openspec
  version: "1.0"
  generatedBy: "1.2.0"
---

Propose a new change - create the change and generate all artifacts in one step.

I'll create a change with artifacts:
- proposal.md (what & why)
- design.md (how)
- tasks.md (implementation steps)

When ready to implement, run /opsx:apply

---

**Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.

**Steps**

1. **If no clear input provided, ask what they want to build**

   Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
   > "What change do you want to work on? Describe what you want to build or fix."

   From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).

   **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.

2. **Create the change directory**
   ```bash
   openspec new change "<name>"
   ```
   This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.

3. **Get the artifact build order**
   ```bash
   openspec status --change "<name>" --json
   ```
   Parse the JSON to get:
   - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
   - `artifacts`: list of all artifacts with their status and dependencies

4. **Create artifacts in sequence until apply-ready**

   Use the **TodoWrite tool** to track progress through the artifacts.

   Loop through artifacts in dependency order (artifacts with no pending dependencies first):

   a. **For each artifact that is `ready` (dependencies satisfied)**:
      - Get instructions:
        ```bash
        openspec instructions <artifact-id> --change "<name>" --json
        ```
      - The instructions JSON includes:
        - `context`: Project background (constraints for you - do NOT include in output)
        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
        - `template`: The structure to use for your output file
        - `instruction`: Schema-specific guidance for this artifact type
        - `outputPath`: Where to write the artifact
        - `dependencies`: Completed artifacts to read for context
      - Read any completed dependency files for context
      - Create the artifact file using `template` as the structure
      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
      - Show brief progress: "Created <artifact-id>"

   b. **Continue until all `applyRequires` artifacts are complete**
      - After creating each artifact, re-run `openspec status --change "<name>" --json`
      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
      - Stop when all `applyRequires` artifacts are done

   c. **If an artifact requires user input** (unclear context):
      - Use **AskUserQuestion tool** to clarify
      - Then continue with creation

5. **Show final status**
   ```bash
   openspec status --change "<name>"
   ```

**Output**

After completing all artifacts, summarize:
- Change name and location
- List of artifacts created with brief descriptions
- What's ready: "All artifacts created! Ready for implementation."
- Prompt: "Run `/opsx:apply` or ask me to implement to start working on the tasks."

**Artifact Creation Guidelines**

- Follow the `instruction` field from `openspec instructions` for each artifact type
- The schema defines what each artifact should contain - follow it
- Read dependency artifacts for context before creating new ones
- Use `template` as the structure for your output file - fill in its sections
- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
  - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
  - These guide what you write, but should never appear in the output

**Guardrails**
- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
- Always read dependency artifacts before creating a new one
- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
- If a change with that name already exists, ask if user wants to continue it or create a new one
- Verify each artifact file exists after writing before proceeding to next

© openspec · MIT · lis186/ccxray

Similar skills

All skills for Agent setup: memory, context, orchestration →

openspec-propose by other authors comes first.

From the same set2

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor