agentsclimarketplace

Release narrative

Skill authenticfake/clike/extensions/vscode/templates/harper-init/.clike/skills/vendor/bmad/release-narrative

Clike is an AI-native developer experience layer AI Native Pipeline principles and from some visionar on internetFrom the repository description

Install
npx -y skills add authenticfake/clike --skill release-narrative

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.3 KB, 470 tokens by cl100k_base, as published. Nobody here has run it

BMAD Skill Mapping: Release Narrative

Intent

Create clear release-facing documentation and stakeholder summaries from validated CLike artifacts and evidence.

BMAD source/reference concept

Inspired by BMAD documentation and stakeholder communication practices: explain what was built, why it matters, risks, and operational readiness.

CLike adaptation

Use this mapping in finalize/tech-writer to improve final docs and BMAD companion release notes without changing promotion evidence.

Applies when

Applies to finalize/tech-writer.

Required inputs

  • PLAN, plan.json, SPEC, TECH_CONSTRAINTS.
  • Eval and Gate reports.
  • Candidate or promoted artifacts.
  • BMAD companion docs when present.

Required outputs

  • CLike finalize outputs and release companion artifacts grounded in actual evidence.
  • Clear runbook, user/maintainer notes, and known limitations when applicable.

Companion outputs

  • docs/harper/bmad/finalize/DOC_REVIEW.md
  • docs/harper/bmad/finalize/RELEASE_NARRATIVE.md
  • docs/harper/bmad/finalize/STAKEHOLDER_SUMMARY.md

Downstream consumers

Human reviewers, maintainers, audit trails, release managers, and future Harper phases.

Quality checks

  • Claims are traceable to canonical artifacts or reports.
  • Known risks and limitations are not hidden.
  • Documentation separates product behavior, operations, and evidence.
  • No unsupported success claims are introduced.

Eval/Gate evidence expectations

Finalize text must reflect EvalRunner and Gate outcomes and must not imply promotion if Gate has not approved it.

Forbidden behavior

  • Do not fabricate test results, coverage, security status, or gate decisions.
  • Do not modify eval reports or gate reports.
  • Do not add runtime dependencies.
  • Do not treat BMAD companion narrative as canonical evidence.

Runtime dependency status

Reference-only. No BMAD documentation runtime or CLI is executed.

Cloud usage notes

Use selected snippets to improve final docs and companion narrative while honoring active output paths.

Local-agent usage notes

If local finalize packaging is used, treat this mapping as writing guidance only and keep CLike report authority intact.

Governance boundaries

CLike owns final artifact contracts, EvalRunner evidence, Gate authority, and audit status.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.