Skip to main content

/

/

Stats

Actions

Tags

Stats

Actions

Tags

ClaudePluginHub

Community directory for discovering and installing Claude Code plugins.

Find plugins for your project

AI-powered recommendations based on your stack.

Product

Browse Plugins
Marketplaces
Pricing
About
Contact

Resources

Learning Center
Blog
Weekly Digest
Claude Code Docs
Plugin Guide
Plugin Reference
Plugin Marketplaces

Community

Browse on GitHub
Get Support

Legal

Terms of Service
Privacy Policy

Browse · Plugins · Top Plugins · Marketplaces · Components · Technologies · Skills · Agents · Commands · Hooks · MCP Servers · LSP Servers · Output Styles · Themes · Monitors

Categories · Productivity · Development · Testing · Deployment · Security · Documentation · Data · Utilities

© 2025 ClaudePluginHub

Community Maintained · Not affiliated with Anthropic

ClaudePluginHub

ClaudePluginHub

Tools Learn Pricing

Search everything...

authoring-living-spec | spec-driven

Home
Skills
spec-driven
authoring-living-spec

Skill

authoring-living-spec

From spec-driven

Creates or edits a living spec under docs/specs with current-state-only content, the domain/status/governing_adrs frontmatter, one capability per file, and a verification section.

Invocation

How this skill is triggered — by the user, by Claude, or both

Slash command

/spec-driven:authoring-living-spec

User invocable

Model invocable

Inline context

Default effort

Context Preview

The summary Claude sees in its skill listing — used to decide when to auto-load this skill

A living spec is the current-state source of truth for one capability, edited in

SKILL.md

46 lines · ~430 tokens

Stats

LanguagePython

Parent stars0

MaintenanceGood

Last CommitJun 8, 2026

Actions

View Source View Plugin View on GitHub View README

Stats

LanguagePython

Parent stars0

MaintenanceGood

Last CommitJun 8, 2026

Actions

View Source View Plugin View on GitHub View README

Authoring Living Spec

Overview

A living spec is the current-state source of truth for one capability, edited in place forever. It describes what the capability does today and how to verify it — never why (that is an ADR's job).

When to use

A capability needs a current-state spec.
An existing spec must be updated to reflect new behavior.

When NOT to use

Recording why a decision was made → writing-adr.
Writing an implementation plan or a work-in-progress handoff.

Steps

Pick the path docs/specs/<domain>/<capability>.md; create the domain folder if no existing domain fits.
Write the frontmatter per ${CLAUDE_PLUGIN_ROOT}/references/spec-and-adr-frontmatter.md (name, domain, status, governing_adrs, last_updated).
Write the body: current-state WHAT plus a how-to-verify section. One capability per file.

STOP: if you are writing past tense or rationale ("we used to…", "we chose…"), stop — that belongs in an ADR, not the spec.

Common mistakes

A changelog inside the spec — history lives in git + ADRs.
Multiple capabilities crammed into one file — one capability per file.
Missing governing_adrs — link the decisions that shaped the current state.
Rationale prose where current-state belongs — move the why to an ADR.

Pointers

${CLAUDE_PLUGIN_ROOT}/references/spec-and-adr-frontmatter.md
${CLAUDE_PLUGIN_ROOT}/references/change-lifecycle.md
docs/specs/meta/spec-governance.md

$

npx claudepluginhub baranovxyz/agent-context-kit --plugin spec-driven

Similar Skills

writing-skills

230.8k

Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.

6 files

View writing-skills