Skill
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
npx -y skills add skillberry-ai/cap-evolve --skill skillAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
<One paragraph. WHAT this skill does and WHEN an agent should reach for it. This is the host's activation signal, so be concrete and self-contained — an agent decides whether to load the skill from this text alone.>
SKILL.md
2.2 KB, as published. Nobody here has run it
<Skill Title>
One-sentence statement of what running this skill accomplishes.
When to use this skill
Concrete triggers. What situation in the pipeline calls for it.
Inputs
Read inputs/INPUTS.md. For every input marked NEEDED that is not already
present, ASK THE USER — quote the expected path, the command/options to
obtain it, and any alternatives — and do not fabricate it. RECOMMENDED inputs
may be skipped, with a logged note.
What you must implement
The optimizer agent implements the abstract methods in scripts/abstract.py
(or confirms the project adapter already covers them). Then run scripts/check.py
— it refuses until every method is real and deterministic, and tells you exactly
what is still stubbed.
How to run
python scripts/check.py # gate: must pass first
python scripts/run.py <args> # executes the step; prints a JSON result to stdout
The JSON on stdout is the contract surface — downstream skills (and hosts that can't import Python) consume it directly.
References — load only when you need them
references/concepts.md— grounded background and the reasoning behind the design.references/examples.md— concrete worked examples.references/pitfalls.md— failure modes and important points to watch.
Prompt
prompt/PROMPT.md is the prompt template handed to the using-agent when this
skill drives a model step. Fill its {{placeholders}} from the inputs.