Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →akijain2000/skill-factory
Navigate the Skill Factory knowledge base.
Passed 17 of 21 test cases with the skill, and 8 of 21 without it.
and 7 more in the full report
10 fixed9 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want a quick non-interactive report on my skill at './skills/git-helper/SKILL.md' without going through a guided interview. Which skill file handles running this automated authoring gap analysis?
| Checked | Without skill | With skill |
|---|---|---|
| directs execution to authoring/SKILL.md | Missed | Passed |
The instructions your model reads when the skill loads.
Welcome to Skill Factory -- the LLM knowledge base for authoring production-quality AI agent skills.
If the request already names an outcome, route directly. For upstream source updates or new-repository discovery, use Route F; do not start the intake menu.
Ask the user:
What would you like to do today?
A) Review and improve an existing skill -- "I have a SKILL.md and want to make it better"
B) Brainstorm and create a new skill -- "I have an idea (or no idea yet) and want to build a skill"
C) Learn about skill authoring -- "I want to take the course or browse the knowledge base"
D) Extract skills from a big prompt -- "I have a long system prompt or instruction set and want to break it into skills"
E) Evaluate a skill -- "I want to test triggering, compare against the no-skill baseline, or decide whether to retire a skill"
Wait for the user's answer before proceeding.
If the user chose A, ask a follow-up:
How would you like to review it?
A1) Guided brainstorm review -- "Walk me through it like a YC office hours session. Challenge my assumptions and help me rethink the skill."
A2) Quick report -- "Just run the validator, do a gap analysis, and give me a report with fixes."
A YC/CEO office-hours-style deep review of an existing skill.
test cases passed, vs 8 / 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.