check-in

Retrieves aggregated context and progress for an existing activity via the check_in tool.

3|1|Updated Dec 9, 2025
One-click install
npx skills add https://github.com/isizono/calm --skill check-in-isizono
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: check-in
Source: https://github.com/isizono/calm/tree/main/skills/check-in
Command: npx skills add https://github.com/isizono/calm --skill check-in-isizono

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When resuming work on a long-running project in a new Claude Code session, all prior context is lost. This Skill restores the full picture of an existing activity—its background, decisions, logs, materials, and progress—so you can continue working without re-explaining everything. ## Core Features & Use Cases - Activity Context Aggregation: Calls the check_in tool to gather pinned decisions, logs, materials, related topics, and goal status for a selected activity. - Progress Summarization: Presents a two-section overview (summary and progress) including intent tags and remaining work, so you can start immediately. - Goal Lifecycle Handling: Automatically judges ready goals, sets undefined goals, verifies external waiting conditions, and triages blocking asks. - Use Case: You return to a project after a week and say "前回の続き" (continue from last time). The Skill lists your in-progress activities, checks in to the one you pick, and reports where things stand and what to do next. ## Quick Start Say "check in to my current activity" or "let's resume where we left off" to restore the context and progress of your ongoing work.

Frequently Asked Questions about check-in

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I resume work on a previous activity in Claude Code?▼

Invoke the check-in flow by saying you want to continue prior work. The Skill lists in-progress activities from the SessionStart hook, calls check_in for the one you select, and summarizes its background and progress.

What information does a check-in return for an activity?▼

Check-in returns five frames: anchor (activity and pinned entities), control (goal and blocking asks), context, catalog, and env (hints and session info). Pinned decisions, logs, materials, topics, and activities are surfaced first.

Does check-in work if the activity list is not shown in the session?▼

Yes. If the SessionStart hook list is unavailable or the desired activity is hidden, the Skill falls back to get_activities() to fetch a flat list, showing only topic and activity names without IDs.

What happens when a check-in response is truncated?▼

Truncated responses include a cuts list with section paths and next pointers containing tool calls. Invoking the indicated tool with its arguments retrieves the trimmed content for the sections you need.

When should I use check-in versus starting a new activity?▼

Use check-in only when resuming an existing activity. For new work, use activity-start instead; check-in deliberately does not trigger for new tasks or cross-period retrospectives.