prompt-version-control-workflow

Solid

Sets up a prompt versioning system with naming conventions, diff tracking, A/B evaluation gates before promotion, and rollback triggers.

AI & Automation 9 stars 0 forks Updated 3 weeks ago MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
33
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Prompt Version Control Workflow ## What this skill does This skill designs a prompt versioning workflow so you can track changes, test before promoting, and roll back safely. Most teams store prompts as hardcoded strings inside application code — this means prompt changes go unreviewed, regressions are invisible, and rollbacks require a full code deploy. This skill fixes that. ## How to use ### Claude Code / Cline Copy this file to `.agents/skills/prompt-version-control/SKILL.md` in your project root. Then ask: - *"Use the Prompt Version Control skill to set up versioning for our prompts."* - *"How should we manage prompt versions across staging and production?"* Provide: - Number of prompts in your system - Current storage method (hardcoded, env vars, database, files) - Whether you need A/B testing or just safe deploys - Tech stack ### Cursor / Codex Describe your current prompt management alongside these instructions. ## The Prompt / Instructions for the Agent ### Step 1 — Choose a storage approach | Approach | Best for | Tradeoffs | |---|---|---| | **Git files** (prompts/*.md) | Small teams, prompts change rarely | Simple, diffable, but requires deploy to change | | **Database table** | Prompts change frequently, need hot-swap | Live updates, but needs admin UI | | **Dedicated tools** (Braintrust, LangSmith, Langfuse) | Eval-heavy teams | Best tooling, external dependency | | **Environment variables** | Single prompt, simple apps | Easy but no history, no dif...

Details

Author
Notysoty
Repository
Notysoty/openagentskills
Created
6 months ago
Last Updated
3 weeks ago
Language
JavaScript
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category