ghost-database

Use this skill for persistent PostgreSQL storage in agent workflows — spin up databases on demand, test schema migrations safely on forks, and pass databases as assets between agents using Ghost. **Trigger when user asks to:** - Create a new PostgreSQL database quickly - Manage database lifecycle in agent workflows - Fork a database to test changes safely - Run analytics or heavy queries on a fork without impacting the production database - Share a database snapshot so others can spin up their own copy - Pass a database as an input or output between agents - Create a database for agents - Need many databases that are billed only when queried - Set up the Ghost MCP server or CLI **Note:** If the Ghost MCP server is already installed, use its tools directly — this skill is for environments without the MCP or as a reference for what's possible. **Keywords:** Ghost, ghost.build, database, create database, fork database, PostgreSQL, managed Postgres, MCP, agent database, connection string

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/ghost-database/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

A highly actionable skill body with concrete, executable CLI and MCP guidance for every core workflow. Its gaps are mild verbosity/redundancy and the absence of explicit validation checkpoints in the destructive fork-then-apply workflow.

Suggestions

Add an explicit validation step to the fork workflow (e.g. run a verification query on the fork and compare results before applying the change to the original) so the destructive apply is gated on a real checkpoint.

Trim inferable explanatory prose (e.g. 'Forking creates a full copy of your database in seconds — same schema, same data') and de-duplicate the Getting Started create/list/connect examples against Core Workflows.

Consider splitting the full CLI command reference and per-workflow MCP tool details into a separate reference file to improve progressive disclosure and reduce SKILL.md length.

Dimension	Reasoning	Score
Conciseness	Mostly executable and well-organized, but includes explanatory prose Claude could infer ('Forking creates a full copy of your database in seconds — same schema, same data. Use forks to test migrations...'), and the Getting Started section repeats create/list/connect commands that reappear in Core Workflows, plus a duplicated full CLI/MCP treatment per workflow.	2 / 3
Actionability	Provides fully executable, copy-paste-ready CLI commands and MCP calls with exact syntax, parameters, and example outputs (e.g. 'ghost create my-app-db', 'ghost_sql({ name_or_id: "abc123", query: "..." })', 'returns { id: "abc123", ... }').	3 / 3
Workflow Clarity	The fork workflow is sequenced with a decision branch ('If it worked: apply to original' / 'If it failed: delete the fork'), but it lacks an explicit verification checkpoint defining how to confirm success before applying changes to the original database — a destructive database operation, which caps this dimension at 2 per the rubric's feedback-loop rule.	2 / 3
Progressive Disclosure	Content is a single monolithic SKILL.md with no bundle files; sections are clearly labeled, but substantial inline material (full dual CLI/MCP walkthroughs, command reference) that could live in separate reference files keeps it at the 'structured but content that should be separate is inline' anchor rather than a 3.	2 / 3
	Total	9 / 12 Passed

Description

90%Weight 40%Scale 1-3

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

A strong, well-structured description with explicit what/when guidance and excellent natural keyword coverage; its only real weakness is the second-person voice, which costs it specificity per the rubric's voice rule.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('spin up databases on demand, test schema migrations safely on forks, and pass databases as assets between agents'), which reaches the score-3 anchor, but the description uses second-person voice ('Use this skill for...', 'Trigger when user asks to:') rather than third person, triggering the required specificity reduction of 1.	2 / 3
Completeness	Clearly answers what ('persistent PostgreSQL storage... spin up databases on demand, test schema migrations safely on forks, pass databases as assets') and when via an explicit 'Trigger when user asks to:' clause with concrete trigger cases.	3 / 3
Trigger Term Quality	Strong natural-term coverage in both the trigger list and Keywords block: 'Create a new PostgreSQL database quickly', 'Fork a database', 'Share a database snapshot', plus 'Ghost, ghost.build, database, fork database, PostgreSQL, MCP, connection string' — terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (managed PostgreSQL for agent workflows via Ghost) with distinctive triggers (Ghost, ghost.build, fork database, MCP) that are unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: timescale/pg-aiguide
Path: skills/ghost-database/SKILL.md
Commit: b4f11a4

Reviewed: 11 days 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.