Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →akijain2000/authoring
Draft, review, and improve SKILL.md files using a compiled knowledge base of best practices and anti-patterns.
Passed 18 of 21 test cases with the skill, and 9 of 21 without it.
and 12 more in the full report
11 fixed10 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
We created an evaluation suite JSON file at `evals/json-parser.json`. I plan to execute behavioral testing by running `pytest evals/json-parser.json`. What command should be executed to run behavioral evaluations using the repository's evaluation runner?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies executing bun run scripts/evaluate-skill.ts evals/json-parser.json to run the suite. | Missed | Passed |
The instructions your model reads when the skill loads.
A meta-skill that queries the Skill Factory wiki to help you write better SKILL.md files.
Accept one of:
If no input provided, ask: "What should this skill do? Describe in 1-2 sentences."
Read the wiki index to understand what knowledge is available. All paths below are relative to the skill-factory root directory.
Read the file wiki/INDEX.md.
This is the master table of contents with one-line summaries. Use it to pick which articles to read next.
Based on the task, read the most relevant wiki articles. Do NOT read all of them. Pick 3-5:
Always read for any task:
wiki/research/anatomy-of-a-good-skill.md (the quality checklist)wiki/concepts/description-writing.md (most common failure point)test cases passed, vs 9 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.