KS
Killer-Skills

mcaf-feature-spec — how to use mcaf-feature-spec how to use mcaf-feature-spec, mcaf-feature-spec setup guide, mcaf-feature-spec alternative, mcaf-feature-spec vs competing specs, what is mcaf-feature-spec, mcaf-feature-spec install, mcaf-feature-spec technical specification, feature specification best practices, mcaf-feature-spec documentation

v1.0.0
GitHub

About this Skill

Perfect for Architectural Agents needing precise feature specification generation in Markdown format. mcaf-feature-spec is a technical specification skill that ensures implementable and verifiable feature specs without guesswork, using concrete module names and testable rules.

Features

Generates docs/Features/<feature>.md files for clear feature documentation
Updates links to and from ADRs and architecture maps for consistent navigation
Enforces spec quality with anti-guesswork checklists and explicit questions
Utilizes concrete module/boundary names from docs/Architecture/Overview.md for accuracy
Ensures rules are testable with numbered specifications for reliable implementation

# Core Topics

Zendevve Zendevve
[0]
[0]
Updated: 3/7/2026

Quality Score

Top 5%
47
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add Zendevve/opentweak/mcaf-feature-spec

Agent Capability Analysis

The mcaf-feature-spec MCP Server by Zendevve is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use mcaf-feature-spec, mcaf-feature-spec setup guide, mcaf-feature-spec alternative.

Ideal Agent Persona

Perfect for Architectural Agents needing precise feature specification generation in Markdown format.

Core Value

Empowers agents to create and update feature specifications with concrete modules and testable rules, utilizing Markdown format and linking to ADRs and architecture maps.

Capabilities Granted for mcaf-feature-spec MCP Server

Generating feature specifications in docs/Features/<feature>.md files
Updating links to ADRs and architecture maps
Creating testable rules for feature implementation

! Prerequisites & Limits

  • Requires access to docs/Architecture/Overview.md for module names
  • Markdown format only
  • Needs explicit questions for unknown specifications
Project
SKILL.md
2.2 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

MCAF: Feature Spec

Outputs

  • docs/Features/<feature>.md (create or update)
  • Update links from/to ADRs and architecture map when needed

Spec Quality (anti-guesswork checklist)

Write a spec that can be implemented and verified without guessing:

  • No placeholders: avoid “TBD”, “later”, “etc.”; if something is unknown, list it as an explicit question.
  • Concrete modules: use real module/boundary names from docs/Architecture/Overview.md.
  • Rules are testable: numbered business rules with clear inputs → outputs (no vague adjectives).
  • Flows are executable: scenarios include preconditions, steps, expected results (happy + negative + edge).
  • Verification is real: commands copied from AGENTS.md, and scenarios mapped to test IDs.
  • Stakeholders covered: Product / Dev / DevOps / QA each get the information they need to ship safely.

Workflow

  1. Start from docs/Architecture/Overview.md to pick the affected module(s).
  2. Create/update the feature doc using docs/templates/Feature-Template.md.
    • follow AGENTS.md scoping rules (do not scan the whole repo; use the architecture map to stay focused)
    • keep the feature’s ## Implementation plan (step-by-step) updated while executing
  3. Define behaviour precisely:
    • purpose and scope (in/out)
    • business rules (numbered, testable)
    • primary flow + edge cases
  4. Describe system behaviour in terms of entry points, reads/writes, side effects, idempotency, and errors.
  5. Add a Mermaid diagram for the main flow (modules + interactions; keep it readable).
  6. Write verification that can be executed:
    • test environment assumptions
    • concrete test flows (positive/negative/edge)
    • mapping to where tests live (or will live)
    • traceability: rules/flows → test IDs (so tests reflect the spec)
  7. Keep Definition of Done strict:
    • behaviour covered by automated tests
    • static analysis clean
    • docs updated (feature + ADR + architecture overview if boundaries changed)

Guardrails

  • If the feature introduces a new dependency/boundary, write an ADR and update docs/Architecture/Overview.md.
  • Don’t hide decisions inside the feature doc: decisions go to ADRs.

Related Skills

Looking for an alternative to mcaf-feature-spec 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