prompt-versioning
Managing prompt iterations, testing changes, and tracking what works.
- Installs
- 134
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/owl-listener/ai-design-skills --skill prompt-versioning- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads prompt-versioning automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Prompt Versioning
Prompts are code. They should be versioned, tested, reviewed, and deployed with the same rigor as software. Treating prompts as casual text that anyone can edit leads to quality regressions, inconsistent behavior, and debugging nightmares.
Why Version Prompts
- Accountability: Know who changed what and when
- Rollback: Revert to a previous version when a change causes problems
- Testing: Compare performance of different versions
- Collaboration: Multiple people can work on prompts without overwriting each other
- Audit trail: Understand how the prompt evolved and why
Versioning Practices
- Source control: Store prompts in version control (Git, etc.), not in application configuration
- Meaningful commits: Each change should explain what was changed and why
- Change categories: Classify changes as bug fixes, improvements, new features, or experiments
- Review process: Prompt changes should be reviewed before deployment, like code reviews
- Semantic versioning: Major changes (behavioral shift), minor changes (new capability), patches (bug fixes)
Testing Prompt Changes
Before deploying a prompt change:
- Regression testing: Run the golden test set against the new version. Did anything get worse?
- Targeted testing: Test the specific scenario the change was designed to improve
- Edge case testing: Test edge cases related to the change
- A/B testing: For significant changes, run both versions in production and compare
- User testing: For major persona or behavioral changes, test with real users
Prompt Change Management
- Staging environment: Test prompt changes in a non-production environment first
- Gradual rollout: Deploy to a percentage of users, monitor, then expand
- Feature flags: Toggle prompt features on and off without deployment
- Monitoring: Watch quality metrics closely after any prompt change
- Rollback plan: Always know how to revert if the change causes problems
Common Versioning Mistakes
- Untracked changes: Editing prompts in production without recording the change
- Untested changes: Deploying changes without testing against known scenarios
- Big bang changes: Changing many things at once, making it impossible to know what helped or hurt
- Lost context: Changing a prompt without understanding why the previous version was written that way
Design Artefacts
- Prompt repository structure
- Change review checklists
- Testing protocols per change type
- Deployment and rollback procedures
- Prompt change request templates
FAQ
What does the prompt-versioning skill do?
Managing prompt iterations, testing changes, and tracking what works.
How do I install prompt-versioning?
Run npx skills add https://github.com/owl-listener/ai-design-skills --skill prompt-versioning in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/prompt-versioning/ (personal) or .claude/skills/prompt-versioning/ (project).
Which AI agents can use prompt-versioning?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is prompt-versioning safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains prompt-versioning?
It is published by owl-listener in owl-listener/ai-design-skills. It has 134 recorded installs.
More from owl-listener/ai-design-skills
system-prompt-structure
owl-listener/ai-design-skills
Anatomy of effective system prompts — role, context, constraints, format.
guardrail-design
owl-listener/ai-design-skills
Open the skill to read its SKILL.md instructions.
constraint-specification
owl-listener/ai-design-skills
Defining output format, length, tone, and content boundaries within prompts.
generative-ui
owl-listener/ai-design-skills
Designing interfaces where AI generates UI components dynamically.
conversation-patterns
owl-listener/ai-design-skills
Turn-taking, repair sequences, grounding, and dialogue structure for human-AI interaction.
progressive-disclosure
owl-listener/ai-design-skills
Revealing AI capability gradually to match user mental models.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
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.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available