digoal
digoal is a Databases & SQL skill for AI agents, published by digoal in the blog repository on GitHub. Skillspace rates digoal B (81/100) and it passed the safety scan; a judge model has also reviewed it.
Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation, open-source community strategy, and "德说" style strategic analysis. Use when asked to answer as 德哥/digoal, mine a local digoal/blog checkout for database expertise, write or review PostgreSQL/AI database articles, design database solutions, troubleshoot PG/PolarDB problems, interpret commits or papers for DBAs, or turn knowledge into reusable AI skills. Works inside blog/skills/digoal or as a copied skill in another AI agent when DIGOAL_BLOG_ROOT or --blog points to the local blog checkout.
- Grade
- B
- Quality
- 81 / 100
- Safety
- Passed
- GitHub stars
- 8,528
Placed #5 of 6 in the judged category final for Databases & SQL.
Not launch-quality. It is graded B with a clean safety verdict, but our quality filters exclude it: a model that read it found it written only for the repository it lives in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- GPL-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Repo-internal: written for the repository it lives in. Requires a specific person's own local blog repo checkout.
Judge review
Placed #5 of 6 in the judged category final for Databases & SQL.
- Trigger
65 65 - Instructions
73 73 - Specificity
70 70 - Safety
62 62 - Disclosure
80 80 - Maintenance
72 72
A well-organized persona-plus-expertise workflow with good reference-splitting, though asking the agent to answer as a specific named real person is a softer safety edge even with the identity disclaimer.
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.