Displays a read-only snapshot of active, completed, pending, and backlog activities via get_overview.
npx skills add https://github.com/isizono/calm --skill overview-isizono
Please help me install this Agent Skill. Skill: overview Source: https://github.com/isizono/calm/tree/main/skills/overview Command: npx skills add https://github.com/isizono/calm --skill overview-isizono
get_overview tool once and renders its four fixed sections (working, recently_done, awaiting_human, backlog) in a fixed order. - Attention surfacing: Highlights live items, days since last touch, open ask counts, and unanswered triage-pending questions awaiting human judgment. - Backlog summary: Presents aggregate counts by status and domain without enumerating individual activities. - Use Case: At the start of a work session, ask "what is currently in progress?" to see active work, recently finished items, decisions waiting on you, and the remaining backlog breakdown at a glance. ## Quick Start Ask the assistant "show me the overall progress status" to get a four-section overview of current work.High-intent search queries and answers about installing and using this skill.
Ask for the current overall status, which triggers a single get_overview call. The result shows working items with live indicators, days since last touch, and open ask counts, followed by recently done, awaiting human, and backlog sections.
Overview shows a point-in-time snapshot of current state with no period parameter. Digest handles period-based retrospective reviews across activities and decisions, while check-in handles starting or resuming a single activity.
Yes, if you specify a period or count, those values are passed to the days and limit parameters of get_overview. Without explicit values, the tool's defaults are used and only one call is made.
No, it is strictly read-only. It never calls recording or update tools such as add_*, update_*, or retract, and all judgment logic lives inside the get_overview tool itself.
The recently_done section approximates completion using updated_at timestamps, so editing an item after completion can make it resurface. The skill explicitly avoids presenting this count as a completion record.
danielsuguimotoExtracts retention-worthy knowledge from session history and persists it to the active memory provider.
mikev10Resume an AI-DLC workflow from its last saved checkpoint with restored context and rules.
basicmachines-coReview recent notes and conversations to consolidate insights into MEMORY.md.
zhuyingqinRetrieve academic paper sections progressively via DeepXiv search and ID lookups.