agentleFS
Sign inStart free
redhat-developerredhat-developer/rhdh-skills/skills/refinement/openspec-new-change/SKILL.md

openspec-new-change

Skill20 starsChanged 20 days agoApache-2.0View on GitHub

Scaffolds a new OpenSpec change directory and shows the first artifact's template without writing it. Use for "start a new change", "scaffold a change", "set up a change for X", or "what's the first artifact I need" — when the user wants the folder and the first template, not a drafted proposal. Creates the change directory and stops — it does not draft or write any artifact content, and it does not implement code.

66 other projects use a version of this, 57 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use draft-openspec-docs, release-openspec and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • goernSkill

    draft-openspec-docs

    Collaborative page-drafting mode for the OpenSpec docs. Builds a scratch plan inside the target page (purpose, structure, numbered draft steps), iterates on it with the user, then drafts one section per approved step and cleans up after itself. Use when a page needs a from-scratch rewrite or a new page is being shaped with the user in the loop.

    Also in 3 projects that use this

  • goernSkill

    release-openspec

    Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is complete, what the next release step is, or to continue a release paused for human approval.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    openspec-update-change

    Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.

    Also in 11 projects that use this

  • VercelSkill

    vercel-react-best-practices

    React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

    Also in 3 projects that use this

  • +2 more from goern

The file

We split this skill into the rules it gives an agent

8 rules. 3 are common, 1 is distinctive, and 4 are very specific to this project.

  • 3

    Common

    Most of the 62 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Ensure the project schema is installed: Check whether openspec/config.yaml and openspec/schemas/rhdh-spec-driven/ already exist.

    line 20
  2. Very specific:

    Get the change name: If the user's request already names it or describes what they want to build, derive a kebab-case name (e.g.

    line 25
  3. Very specific:

    Pick the schema: Prefer rhdh-spec-driven (now on disk).

    line 29
  4. Very specific:

    Read /rhdh-spec-driven-schema for what the context, rules, and template fields in that response mean before summarizing them.

    line 54
  5. Distinctive:

    Do not create any artifacts yet — only show the first artifact's template.

    line 69
  6. Common:

    Do not advance beyond the first artifact.

    line 70
  7. Common:

    If the name is not valid kebab-case, ask for a valid one.

    line 71
  8. Common:

    If a change with that name already exists, suggest continuing that change instead of creating a duplicate.

    line 72

“Common” is measured: kept by at least 6 in 10 of the 62 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Start a new OpenSpec change

Scaffold a change directory and hand the caller the first artifact's template, then stop — drafting content is a separate turn.

Steps

  1. Ensure the project schema is installed. Check whether openspec/config.yaml and openspec/schemas/rhdh-spec-driven/ already exist. Only if either is missing, invoke /rhdh-spec-driven-schema and run its project-install step. Then confirm with openspec schemas --json that rhdh-spec-driven is listed.
  2. Get the change name. If the user's request already names it or describes what they want to build, derive a kebab-case name (e.g. "add user authentication" -> add-user-auth). Otherwise ask what they want to build or fix; do not proceed without knowing.
  3. Pick the schema. Prefer rhdh-spec-driven (now on disk). Pass --schema rhdh-spec-driven, or omit --schema to take the configured default from openspec/config.yaml. If the user names another available schema from openspec schemas --json, use that instead.

  4. Create the change directory:

    openspec new change "<name>" [--schema <name>]

    This scaffolds openspec/changes/<name>/ with the selected schema.

  5. Show status:

    openspec status --change "<name>"

  6. Get the first artifact's instructions. Find the first artifact with status: "ready" in the status output (schema-dependent — proposal for rhdh-spec-driven), then:

    openspec instructions <first-artifact-id> --change "<name>" --json

    Read /rhdh-spec-driven-schema for what the context, rules, and template fields in that response mean before summarizing them.

  7. Stop and wait for user direction.

Output

Summarize: change name and location, schema and its artifact sequence (proposal -> {specs, design} -> tasks for rhdh-spec-driven — specs and design are siblings that each depend only on proposal), current status (0/N artifacts complete), and the template for the first artifact. Close with: "Ready to create the first artifact? Describe what this change is about and I'll draft it, or ask me to continue."

Guardrails

  • Do not create any artifacts yet — only show the first artifact's template.
  • Do not advance beyond the first artifact.
  • If the name is not valid kebab-case, ask for a valid one.
  • If a change with that name already exists, suggest continuing that change instead of creating a duplicate.

Completion

Complete when the change directory exists, its schema is confirmed, and the first artifact's template has been shown to the user — without any artifact file having been written yet.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free