prompt-governance

Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions, or creating eval pipelines for production AI features. Triggers: 'manage prompts in production', 'prompt versioning', 'prompt regression', 'prompt A/B test', 'prompt registry', 'eval pipeline'. NOT for writing or improving individual prompts (use senior-prompt-engineer). NOT for RAG pipeline design (use rag-architect). NOT for LLM cost reduction (use llm-cost-optimizer).

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and lean, with clear mode-based workflows and useful schemas/thresholds, but it stays at the guidance level without executable code or runnable commands, which limits actionability.

Suggestions

Add a minimal runnable eval-runner snippet (e.g. a short Python function iterating the golden dataset and reporting pass_rate) so the eval pipeline is copy-paste executable rather than described in prose.

Include a concrete one-command rollback example (registry YAML diff or CLI invocation) instead of describing rollback only conceptually.

Tighten or remove the trailing 'To initialize.../To execute evals...' sentences that restate the preceding sections, recovering tokens without losing information.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence without explaining what prompts or LLMs are, but the trailing 'To initialize...' / 'To execute evals...' lines restate the preceding prose, adding minor redundancy.	4 / 5
Actionability	Provides concrete schemas, directory layouts, pass thresholds, and step lists, but offers no executable code or runnable commands for the eval runner or registry init — the 'To execute evals' line describes the process rather than giving copy-paste implementation.	3 / 5
Workflow Clarity	Mode 3 lays out a clear 8-step lifecycle with COMPARE/REVIEW/MONITOR gates and a rollback playbook that re-runs evals to verify, but explicit 'only proceed when eval passes' gating language between steps is only implied.	4 / 5
Progressive Disclosure	Well-organized into clearly signaled modes, tables, and sections with no bundle files needed; not a 5 only because there is no external reference structure to split out, which this self-contained skill does not strictly require.	4 / 5
	Total	15 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a strong, model example: concrete capabilities, natural trigger phrases, complete what/when coverage, and explicit boundary disambiguation against adjacent skills. No improvement needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions, or creating eval pipelines' — giving comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what ('managing prompts in production at scale') and when ('Triggers: ...'), matching the score-5 anchor with concrete trigger phrases and a clear 'Use when' clause.	5 / 5
Trigger Term Quality	Explicit natural trigger phrases ('prompt versioning', 'prompt regression', 'prompt A/B test', 'prompt registry', 'eval pipeline') that users would actually say, with comprehensive coverage and synonym variation.	5 / 5
Distinctiveness Conflict Risk	Clear niche of production prompt governance reinforced by explicit NOT-for boundary disambiguation against senior-prompt-engineer, rag-architect, and llm-cost-optimizer, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: engineering/prompt-governance/skills/prompt-governance/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.