Convert an article, tutorial, or prompt pack into focused reusable AgentSkills, one independent capability per skill, with portable instructions, example prompts, working demos, preview screenshots, validation, gallery updates, and a narrow commit.
SkillScore78Maintained
Automatic
◆AI Engineer pack
Last verified 8/10/2026
What it changes
Passed 16 of 20 test cases with the skill, and 8 of 20 without it.
Without skill39%
With skill78%
Checks it passed that the model alone missed
Includes the heading ### Minimal prompt in demo/PROMPT.md.
Restricts YAML frontmatter in SKILL.md to name and description.
Consolidates example prompts into the single file demo/PROMPT.md.
and 12 more in the full report
11 fixed7 passed either way3 still failing2 broke
Pass-rate lift
+39 pp
Tokens
+26%
Agent turns
0%
Response time
-49%
Model gemini-3.6-flashMeasured 8/10/2026v118 of 23 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
When writing the agent configuration file `agents/openai.yaml` for an extracted skill package, what is the character length constraint on the short description field?
What was checked, without and with the skill
Checked
Without skill
With skill
Enforces a length between 25 and 64 characters for the agents/openai.yaml short description.
Missed
Passed
case-08 · gemini-3.6-flash · 8/10/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md148 lines2 files
Article Prompts to Skills
Turn source prompts into small, demonstrable capability packages. Preserve the useful behavior, not the source page's brand or layout.
1. Inspect Before Extracting
Read the repository instructions and the complete source article.
Run git status --short; preserve unrelated work.
Inventory every explicit prompt, heading, example, asset, and acceptance criterion.
Search existing SKILL.md files for overlapping capabilities before creating folders.
If the source is raw HTML and the prompts do not exist yet, use $html-to-interaction-prompts first, then return here.
Do not infer a family of skills from a title alone. Trace each proposed skill to source evidence.
2. Build an Extraction Ledger
Create a working table before editing files:
Source prompt
Reusable capability
Keep
Remove
Skill name
Demo proof
Apply these boundaries:
Create one skill per independently reusable behavior.
Merge steps only when separating them would make either step unusable.
Update an existing skill when its contract already covers the capability.
Skip decorative or editorial fragments that do not create a repeatable method.
Name skills after the outcome or mechanism, never after the source article.
3. Extract the Portable Contract
Keep the source's successful mechanics:
behavior and state transitions;
data model and parameter defaults;
timing, easing, spacing, and responsive rules;
accessibility, reduced-motion, and keyboard behavior;