How this skill is triggered — by the user, by Claude, or both
Slash command
/honeycomb:sloThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Dependency chain: derived column (SLI) → SLO → burn alert. All commands require `--dataset`.
Dependency chain: derived column (SLI) → SLO → burn alert. All commands require --dataset.
target_per_million: 99.9% = 999000, 99% = 990000, 95% = 950000.
slo create -f - (file-only, no flags yet — see #109)slo update <id> --name/--description/--target/--time-period (flag-based, read-modify-write) or -f (mutually exclusive)slo get <id> / slo get <id> --detailed (Enterprise-only)slo list / slo delete <id> --yesCreate body: {"name":"...","sli":{"alias":"<derived-column-alias>"},"time_period_days":30,"target_per_million":999000}
Create/update require recipients (non-empty array of {"id":"..."}) and slo as {"id":"..."} (nested, not flat slo_id).
Exhaustion time: {"alert_type":"exhaustion_time","exhaustion_minutes":240,"slo":{"id":"..."},"recipients":[{"id":"..."}]}
Budget rate: {"alert_type":"budget_rate","budget_rate_window_minutes":60,"budget_rate_decrease_threshold_per_million":50000,"slo":{"id":"..."},"recipients":[{"id":"..."}]}
All burn alert commands are file-only (-f), no flags yet (#110, #111).
slo history --slo-id <id> --start-time <unix> --end-time <unix> — --slo-id is repeatable. Response is a map keyed by SLO ID.
npx claudepluginhub bendrucker/claude --plugin honeycombGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Resolves in-progress git merge or rebase conflicts by analyzing history, understanding intent, and preserving both changes where possible. Runs automated checks after resolution.