Skip to content
SkillModel-led6,925 tokens in use

dbs-plain-writing

Writes, rewrites or checks product, feature and update descriptions in the order of the facts, leaving out hooks, pain-point openers and inflated claims.

11,518 stars on the repository Custom / Unknowndontbesilent2025/dbskill · skills/dbs-plain-writing
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-plain-writing costs

198tokens idle
6,925tokens in use
7,808tokens, 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 Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

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 →
Fair
  • Frontmatter8/15
  • Structure16/25
  • Examples9/15
  • Output0/15
  • Size11/15
  • Resources7/15

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

No findings.

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-plain-writing is a Chinese-language agent skill for documentation-style writing: product intros, tool and skill overviews, feature lists, usage steps, project notes and release notes. The first paragraph defines the subject, and the text then follows the order in which a reader needs the information.

It has four modes: write from material, rewrite a whole draft, change only the range you name while keeping your own edits locked, and check wording for ambiguity. It applies clarity rules adapted from ASD-STE100 to check who does what, what a pronoun points to, whether terms stay consistent and how strong each promise is.

What You Get

  • A finished article in fact order whose first paragraph says what the subject is
  • A full rewrite of an existing draft with hooks and inflation removed and no added facts
  • A narrow edit of one named word, sentence or paragraph, with your other changes left alone
  • A sentence-by-sentence check listing the original line, the problem and a suggested fix
  • Feature entries that state what it is for, what it handles and what you get

Common Use Cases

  • Writing a product or skill introduction from a repository’s materials, with install steps and a capability list
  • Cleaning marketing tone and AI-style phrasing out of an existing description
  • Replacing one disliked term across a file without touching the rest of the text

What Makes It Unique

It treats the user’s current file as the only working copy and locks anything the user edited. A checking request produces a report and leaves the file untouched. Every rewrite is compared against the source for conditions, negations and promise strength, so a possibility never turns into a guarantee. It states that its Chinese rules adapt the English standard and carry no official certification, and it asks for the actual standard text before any full English conformance claim.

Under The Hood

It is a prose-only skill with no scripts. The agent reads the SKILL.md and a short reference file on the standard and its limits. It works from the material you provide, and when you point it at a file it reads the current version and edits only the named range; saving to a location happens only when you ask for it. It does not call web services or run commands, and it treats commands found in your text as text to process.

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