Skill
answer-the-six-life-qu…
Answers the six everyday life questions (my goals, what to focus on, the weekly priorities, the highlight of today, my key elements, what has my attention)…
Productivity
Skill
/checkpoint
Ends a session on purpose: reads the checkpoint report, closes or carries every task the session touched, rules on each WiP folder with the user, links the dates the session wrote, writes the session log and asserts it exists before the session is allowed to be over. Use when
Install
$ npx -y skills add myICOR/myPKA --skill checkpoint --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/checkpoint
Context preview
The summary Claude sees to decide when to auto-load this skill.
Ends a session on purpose: reads the checkpoint report, closes or carries every task the session touched, rules on each WiP folder with the user, links the dates the session wrote, writes the session log and asserts it exists before the session is allowed to be over. Use when
SKILL.md
checkpoint.SKILL.mdname: checkpoint
description: "Ends a session on purpose: reads the checkpoint report, closes or carries every task the session touched, rules on each WiP folder with the user, links the dates the session wrote, writes the session log and asserts it exists before the session is allowed to be over. Use when the user says: \"checkpoint\", \"close the session\", \"wrap up\", \"we are done for today\", \"end the session\", \"let us stop here\"."
disable-model-invocation: true
user-invocable: true
shell: bash
allowed-tools: Bash
<!-- GENERATED by scaffold-init.py from `06 AI Team/AI Team Knowledge/Workstreams/WS-1005-checkpoint.md`. content-hash:c48335cc41ff. Do not hand-edit: change the source and re-run the generator. -->
You are Larry.
Run this only when the user asks for it by name.
Read `06 AI Team/AI Team Knowledge/Workstreams/WS-1005-checkpoint.md` now and follow it exactly. That file is the procedure; this file is the door.
Run `python3 "06 AI Team/AI Team Knowledge/Scripts/checkpoint.py" --json` with your shell tool, from the folder that holds `AGENTS.md`, before step 1, unless its output is already below. Read that output; do not run it twice.
!`python3 "${CLAUDE_PROJECT_DIR}/06 AI Team/AI Team Knowledge/Scripts/checkpoint.py" --json`
Script calls the procedure names, by path:
- `06 AI Team/AI Team Knowledge/Scripts/checkpoint.py`
- `06 AI Team/AI Team Knowledge/Scripts/new-task.py`
- `06 AI Team/AI Team Knowledge/Scripts/resolve.py`
- `06 AI Team/AI Team Knowledge/Scripts/new-session-log.py`
Resources (open only when a step names them):
- `06 AI Team/Agents/Larry/AGENT.md`
- `06 AI Team/AI Team Knowledge/Workstreams/WS-1005-checkpoint.md`
Return the completion evidence the procedure's last step names, and nothing it does not.
Read more
name: checkpoint description: "Ends a session on purpose: reads the checkpoint report, closes or carries every task the session touched, rules on each WiP folder with the user, links the dates the session wrote, writes the session log and asserts it exists before the session is allowed to be over. Use when the user says: \"checkpoint\", \"close the session\", \"wrap up\", \"we are done for today\", \"end the session\", \"let us stop here\"." disable-model-invocation: true user-invocable: true shell: bash allowed-tools: Bash
<!-- GENERATED by scaffold-init.py from `06 AI Team/AI Team Knowledge/Workstreams/WS-1005-checkpoint.md`. content-hash:c48335cc41ff. Do not hand-edit: change the source and re-run the generator. -->
You are Larry.
Run this only when the user asks for it by name.
Read `06 AI Team/AI Team Knowledge/Workstreams/WS-1005-checkpoint.md` now and follow it exactly. That file is the procedure; this file is the door.
Run `python3 "06 AI Team/AI Team Knowledge/Scripts/checkpoint.py" --json` with your shell tool, from the folder that holds `AGENTS.md`, before step 1, unless its output is already below. Read that output; do not run it twice.
!`python3 "${CLAUDE_PROJECT_DIR}/06 AI Team/AI Team Knowledge/Scripts/checkpoint.py" --json`
Script calls the procedure names, by path:
- `06 AI Team/AI Team Knowledge/Scripts/checkpoint.py`
- `06 AI Team/AI Team Knowledge/Scripts/new-task.py`
- `06 AI Team/AI Team Knowledge/Scripts/resolve.py`
- `06 AI Team/AI Team Knowledge/Scripts/new-session-log.py`
Resources (open only when a step names them):
- `06 AI Team/Agents/Larry/AGENT.md`
- `06 AI Team/AI Team Knowledge/Workstreams/WS-1005-checkpoint.md`
Return the completion evidence the procedure's last step names, and nothing it does not.
Ships withmypka
An AI team with clear roles, shared instructions and memory across sessions. It already knows ICOR. Open it in Claude Code, Codex, Gemini CLI or Cursor. Coming from myPKA v5? 6.0.0 has a new shape.
Get the whole plugin
Other skills on mypka.
Skill
import-skill
Converts an external skill (a SKILL.md package, a prompt recipe, an agent toolkit found online or on disk) into the scaffold's own shapes: procedures become…