KS
Killer-Skills

refine — Categories.community

v1.0.0
GitHub

About this Skill

Ideal for Code Assistant Agents like Claude Code needing advanced specification refinement capabilities. A lightweight framework for spec-driven development with Claude Code and other AI coding assistants.

heiko-braun heiko-braun
[0]
[0]
Updated: 3/4/2026

Quality Score

Top 5%
51
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add heiko-braun/draft

Agent Capability Analysis

The refine MCP Server by heiko-braun is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Ideal for Code Assistant Agents like Claude Code needing advanced specification refinement capabilities.

Core Value

Empowers agents to refine existing specifications using focused refinement questions, supporting spec-driven development with features like loading specs from `/specs/{feature}.md` and handling multiple spec matches, all while integrating with AI coding assistants through protocols like Markdown file analysis.

Capabilities Granted for refine MCP Server

Refining existing specifications based on user feedback
Loading and analyzing specs from designated directories
Asking targeted questions to clarify spec requirements

! Prerequisites & Limits

  • Requires existing specification files in Markdown format
  • Limited to refining specs within the `/specs/` directory hierarchy
Project
SKILL.md
2.7 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Refine Existing Spec

Refine an existing specification based on new insights, feedback, or changing requirements.

Feature to refine: $ARGUMENTS

Instructions

  1. Load the existing spec from /specs/{feature}.md

    • If no spec exists for this feature, suggest using /spec instead
    • If multiple specs match, ask the user which one to refine
  2. Ask 2-3 focused refinement questions (one at a time):

    • What aspect needs refinement? (goals, criteria, approach, scope)
    • What new information or feedback has emerged?
    • Are there specific pain points with the current spec?
  3. Check scope and modularity:

    • Does the refinement keep the spec small enough for a single vertical slice?
    • If criteria are being added, does the total still stay at ~5 or fewer?
    • Does the refinement change which modules are affected? Update the "Affected Modules" section.
    • If the refinement significantly expands scope or blast radius, suggest a separate spec instead.
  4. Update the spec in place:

    • Preserve front-matter: Keep all existing front-matter fields (title, description, author). Keep status: proposed (refinements don't change status)
    • Preserve completed acceptance criteria checkboxes
    • Update goals, criteria, or approach as needed
    • Update "Affected Modules" and "Test Strategy" if the changes alter them
    • Add to "Out of Scope" if removing features
    • Add refinement notes to the "Notes" section with timestamp
  5. Show a diff summary:

    • Highlight what changed (goals, new criteria, removed items, affected modules, etc.)
    • Ask for confirmation before saving
  6. Get user confirmation before proceeding to implementation

    • If confirmed, use the implement skill with the refined spec
    • If not, ask if they want to refine further

Refinement Guidelines

  • Preserve progress: Don't uncheck completed criteria unless they're no longer valid
  • Be additive when possible: Add new criteria rather than rewriting existing ones
  • Document changes: Always add a timestamped note explaining what was refined and why
  • Validate scope: Check if refinements are expanding scope significantly - if so, suggest a new spec
  • Validate modularity: If the refinement introduces new module dependencies or widens the blast radius, flag it explicitly

Example Refinement Note

markdown
1## Notes 2 3**Refinement 2026-01-25**: Updated approach to use WebSocket instead of polling based on performance testing results. Added new acceptance criterion for connection handling. Blast radius unchanged — change is contained within the `transport` module.

Remember:

  • Keep refinements focused and minimal
  • Preserve the spec's history through notes
  • Suggest new specs for major scope changes

Related Skills

Looking for an alternative to refine or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication