Skip to content
SkillMixed4,470 tokens in use

dbs-skill-maker

Creates a new agent skill or improves an existing one: a written plan first, files only after you approve, then a before-and-after test on real tasks.

11,518 stars on the repository Custom / Unknowndontbesilent2025/dbskill · skills/dbs-skill-maker
npx -y skills add dontbesilent2025/dbskill -g --all
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing dbs-skill-maker costs

131tokens idle
4,470tokens in use
13,999tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/init_skill_project.py, scripts/prepare_github_repo.py, scripts/validate_skill_project.py, scripts/verify_npx_install.sh.

Touches

shelldetectednetworkdetectedwrites filesdetectedgitdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure16/25
  • Examples12/15
  • Output0/15
  • Size15/15
  • Resources11/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 142
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/init_skill_project.py, line 107
  • Runs git commands−5

    does this on the machine, and the frontmatter does not say so

    scripts/prepare_github_repo.py, line 186

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

dbs-skill-maker picks a route by the size of the change: new or major rewrite, fixing a reported problem, a small edit, a read-only diagnosis, or publishing to GitHub. Every route that touches files delivers a plan first and waits for your confirmation. For new skills it asks requirement questions, finds the established solution to the problem at a depth you choose, and anchors each judgement step in a theory with its limits.

After writing it runs a structure validator, then compares old and new versions on the same real tasks and reports keep, keep testing or roll back. Publishing is an optional extra and only starts when you ask for it.

What You Get

  • A plan for a new, changed or repaired skill with files, theory anchors, test plan and rollback
  • The skill files written after your confirmation, with a project skeleton script if wanted
  • A structure validation pass that checks front matter, links, placeholders, local paths and secret-like strings
  • A before-and-after comparison and a keep, continue or roll back verdict
  • Optional GitHub packaging with a README and an install command check

Common Use Cases

  • Turning a problem you keep solving by hand into a reusable skill
  • Fixing a skill that misbehaves on a specific case without breaking what already works
  • Preparing a finished skill for sharing through a GitHub repository

What Makes It Unique

It treats a skill as something to be tested as well as written. Each judgement step needs a theory anchor or an admitted gap, each edit has to explain a stable class of failures and not a single example, and executors in tests never see the expected answers. Remote actions such as creating a repository, pushing, tagging or releasing need your explicit request.

Under The Hood

The skill is an instruction file with reference documents and four helper scripts. They create a skill skeleton, validate a skill folder, stage a public copy for GitHub and test an install. Following it can make the agent write and edit files in your project, run Python and shell commands, and, only when you ask to publish, use git and gh to create a repository, push and install from the network with npx skills add. It looks things up online only when a fact would change the plan.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers