Template
Sleuth - Agent Skills that automate payment fraud investigations, plus a deterministic Python engine as the executable reference. Explainable, deterministic scoring and decisions with tokenized card references and human-review gates.
npx -y skills add yogeshg665/sleuth-fraud-investigator --skill templateAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 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
A clear, complete description of what this skill does and the exact conditions under which an agent should invoke it. Start with the capability, then list trigger phrases. WHEN: "trigger phrase one", "trigger phrase two".
SKILL.md
1.3 KB, 234 tokens by cl100k_base, as published. Nobody here has run it
Skill Name
Overview
One or two sentences stating the purpose of this skill and the outcome it produces.
When to Use
- Concrete condition that should activate this skill.
- Another concrete condition.
- Explicitly note conditions where this skill should NOT be used.
Inputs
| Input | Required | Description |
|---|---|---|
field_name | yes | What it is and where it comes from. |
Process
- First concrete step the agent performs.
- Next step, with the decision or computation involved.
- Continue until the skill produces its output.
Outputs
Describe the structured result this skill returns and how downstream skills consume it.
Rationalizations
| Excuse | Rebuttal |
|---|---|
| "This check can be skipped for small amounts." | State why the step is still required. |
Red Flags
- Signs that the skill is being applied incorrectly or producing unreliable output.
Verification
- Evidence that must exist before the skill is considered complete (for example, a populated output field, a passing test, or a logged rationale).