Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yaoapp/secret-management
Agents can read user-configured secrets at runtime using the `tai tool` CLI.
Passed 18 of 20 test cases with the skill, and 10 of 20 without it.
and 9 more in the full report
9 fixed11 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am running `tai tool secret_read` in Bash. Give the exact CLI invocation syntax to request a secret named `SENDGRID_API_KEY`.
| Checked | Without skill | With skill |
|---|---|---|
| uses tai tool secret_read to query SENDGRID_API_KEY | Passed | Passed |
| formats input payload as JSON with name set to SENDGRID_API_KEY | Missed | Passed |
The instructions your model reads when the skill loads.
Agents can read user-configured secrets at runtime using the tai tool CLI.
Secrets are encrypted at rest (AES-256-GCM) and decrypted only when read.
| Tool | Description |
|---|---|
secret_list | List secret names and descriptions (no values) |
secret_read | Read a single secret value by name |
# List available secrets
tai tool secret_list
# Read a secret
TOKEN=$(tai tool secret_read '{"name": "GITHUB_TOKEN"}' | jq -r '.value')
git clone "https://${TOKEN}@github.com/org/repo.git"
const { execSync } = require("child_process");
function readSecret(name) {
const raw = execSync(
`tai tool secret_read '${JSON.stringify({ name })}'`,
{ encoding: "utf-8" }
);
return JSON.parse(raw).value;
}
const token = readSecret("GITHUB_TOKEN");
test cases passed, vs 10 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.