From keycard-cli
Set or change a field in keycard.toml — reads the current value and writes a targeted update. TRIGGER when: user wants to set or change a field in keycard.toml; wants to add or update a credentials entry. DO NOT TRIGGER when: user asks about Cedar policy rules (use `keycard-query-policy`); user asks what credentials are active in the current session (use `keycard-credentials`); user is asking a field question only with no intent to write (read `.agents/reference/keycard-config-fields.md` directly).
How this skill is triggered — by the user, by Claude, or both
Slash command
/keycard-cli:keycard-upsert-config [what to change, e.g. 'set my zone to dev-123' or 'add a GitHub credential entry for GITHUB_TOKEN'][what to change, e.g. 'set my zone to dev-123' or 'add a GitHub credential entry for GITHUB_TOKEN']The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are helping the user set or change a field in the Keycard CLI configuration file.
You are helping the user set or change a field in the Keycard CLI configuration file.
For field definitions, precedence rules, and the credentials section format, see .agents/reference/keycard-config-fields.md.
keycard.toml. If the file does not exist, start with an empty document — do not error.<field> field is env/flag only and is silently ignored in keycard.toml. Set it with export <ENV_VAR>=<value> instead." Then stop.keycard.toml and show the user the modified section to confirm the change was applied.environment = "production"
[zone]
id = "my-zone-id"
# WRONG — org.id is env/flag only; this line will be silently ignored
[org]
id = "my-org"
Set these via environment variable instead:
export ORG=my-org
/keycard-upsert-config set my zone to dev-zone-123
/keycard-upsert-config switch to staging
/keycard-upsert-config add a credentials entry: env_var = "GITHUB_TOKEN", resource = "https://api.github.com"
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.