Skill creator defaults
A personal collection of agent skills.
npx -y skills add taujiong/skills --skill skill-creator-defaultsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Guide to project-specific defaults for skill creation. Use when users want to create a new skill, edit an existing skill, write SKILL.md, or modify any files in .agents/skills. Also triggers when users mention create skill, new skill, write skill, edit skill, or .agents/skills.
SKILL.md
1.5 KB, as published. Nobody here has run it
Skill Creator — Project Defaults
Apply these conventions whenever creating or editing a skill in this project.
Default Output Location
If the user does not specify an output path, save the skill to:
<project_root>/.agents/skills/<skill-name>/
<project_root> is the current working directory.
Writing Style
Skills are written for agents. Follow these standards:
- Concise: omit filler words and redundant explanation
- Precise: use unambiguous terminology; prefer specific terms over general ones
- Imperative: use command form ("Do X", not "You should do X" or "X can be done")
- Formal: avoid colloquialisms, contractions, and conversational tone
Description Format
Always use this exact three-part format for the description field in SKILL.md frontmatter:
Guide to <what the skill does>. Use when users want to <primary use cases>. Also triggers when users mention <trigger keywords or phrases>.
Example:
Guide to automate the git commit workflow. Use when users want to commit changes, stage and commit, or generate a commit message. Also triggers when users mention commit my changes, help me commit, ok commit it, or looks good commit.
Gives 1 of the 12 instructions most skill authoring skills give
Counted across 521 of the 523 authors here whose files we hold, read 2026-08-06
- keep skill files under 500 linesin 182 of 521, across 89 files
- use imperative form in instructionshere, and in 101 of 521, across 30 files
- draft assertions while test runs are in progressin 88 of 521, across 22 files
- save test cases to evals jsonin 87 of 521, across 21 files
- create two to three realistic test promptsin 85 of 521, across 20 files
- write skill descriptions to be pushyin 84 of 521, across 19 files
- ask questions about edge cases and input formatsin 81 of 521, across 16 files
- save timing data immediately when runs completein 74 of 521, across 9 files
- include all trigger conditions in the skill descriptionin 73 of 521, across 7 files
- capture intent before writing a skillin 70 of 521, across 4 files
- launch all test runs in a single turnin 68 of 521, across 2 files
- write the description in third personin 56 of 521, across 19 files
Said here and by no other author read
- save the skill under .agents/skills/
- use concise wording
- use precise terminology
- use formal tone
- use the exact three-part description format
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.