mcpbeat Sign in

Prompt Builder Agent Skill

Compatibility alias for legacy prompt-building requests. Routes creation and improvement to the hve-builder skill.

588 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1313
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/microsoft/hve-core --skill prompt-builder

The instruction itself

9 sections, as written by the author

Prompt Builder Compatibility Skill

Goal

Preserve legacy prompt-builder activation while routing all source changes, review, behavior testing, validation, and outcome resolution through the hve-builder skill.

Flow

  • Translate promptFiles to targets. Treat files as reference context unless the caller explicitly includes them in the write boundary.
  • Resolve create when an approved target is missing and improve when targets already exist. Route explicit cleanup to the prompt-refactor compatibility skill and read-only analysis to prompt-analyze.
  • Activate hve-builder with the targets, selected mode, requirements, reference context, and any caller-owned evidence root.
  • Return the hve-builder final response without adding a second author, test, or evaluation loop.

Inputs

  • promptFiles: target prompt-engineering artifacts; defaults to current open or attached files
  • files: reference artifacts used to derive requirements
  • requirements: explicit objectives, constraints, and acceptance criteria
  • evidenceRoot: optional caller-owned HVE Builder evidence path

Success Criteria

  • Legacy inputs map to an explicit HVE Builder target set and write boundary.
  • hve-builder completes every required gate for the selected mode.
  • The returned overall outcome is unchanged from hve-builder.

Constraints

  • Do not dispatch retired named lifecycle workers.
  • Do not maintain a second sandbox, status vocabulary, or quality rubric.
  • Do not treat reference files as write targets without explicit approval.

Stop Rules

  • Stop when hve-builder returns Pass, Revise, Deferred, or Blocked.
  • Ask only when target identity or write authority cannot be inferred safely.

Handoff

Use prompt-analyze for a legacy read-only request and prompt-refactor for a legacy behavior-preserving cleanup request. Both route back to hve-builder.

Final Response Contract

Return the mode, targets, changed files, static verdict, behavior-test fidelity and verdict, validation result, overall outcome, evidence links, and next action.

Other skills for the same job

different authors, same section of the catalogue
Skill Creator
by anthropics
vendor ×10

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

56k tokens scripts
Skill Creator
by vercel-labs
vendor ×10

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

12k tokens scripts
Skill Creator
by JayZeeDesign
×9

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

10k tokens scripts
Template Skill
by JayZeeDesign
×7

Replace with description of the skill and when Claude should use it.

35 tokens
Dispatching Parallel Agents
by ZhanlinCui
×5

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

2k tokens
Skill Development
by anthropics
vendor ×4

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

9k tokens
Find Skills
by sanity-io
vendor ×4

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

1k tokens
Writing Skills
by ZhanlinCui
×4

Use when creating new skills, editing existing skills, or verifying skills work before deployment

26k tokens scripts

How to use it

Copy the folder

Take microsoft/prompt-builder from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.