From keycard-cli
Shows what credentials are configured in this Keycard session — which services are available and what they provide access to. TRIGGER when: user asks what credentials, tokens, or services are available in the current Keycard session ("what tokens do I have", "what services are available", "am I authenticated", "list my credentials", "do I have access to X", "am I signed in to X", "is my X token loaded"). DO NOT TRIGGER when: user wants to add, remove, or rotate credentials (use `keycard credential` commands directly).
How this skill is triggered — by the user, by Claude, or both
Slash command
/keycard-cli:keycard-credentialsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Report what credentials are available in the current Keycard session.
Report what credentials are available in the current Keycard session.
Run:
keycard credential info --json
If the command fails, display the returned error message and stop.
The command outputs one JSON object per line (JSONL): {"env_var":"VAR_NAME","resource":"https://..."}.
Present results under a ## Credentials heading as a Markdown list:
`ENV_VAR` → `resource-URL` (service label) where ENV_VAR is the env_var field value.api.github.com → GitHub API). Omit the label if the hostname does not map to a recognizable service.keycard run -- <command> to start a hydrated session.Invocation:
/keycard-credentials
Sample output (credentials present):
## Credentials
- `GITHUB_TOKEN` → `https://api.github.com` (GitHub API)
- `NPM_TOKEN` → `https://registry.npmjs.org` (npm Registry)
Sample output (no credentials):
No credentials found. Start a secure session with: `keycard run -- <your-command>`.
Command failure (no configuration file):
/keycard-credentials
Sample output:
No keycard.toml found. Ensure keycard.toml exists and contains at least one [[credentials.default]] entry, then start a secure session with: `keycard run -- <your-command>`.
npx claudepluginhub keycardai/plugins --plugin keycard-cliCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.