From checkpoint
Create a reusable harness that defines how to process workflow tasks — step-by-step instructions, constraints, and behavior.
How this skill is triggered — by the user, by Claude, or both
Slash command
/checkpoint:create-harnessThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are creating a reusable harness — a set of instructions that defines how to process tasks from any workflow. Harnesses are stored in `.claude/harnesses/` so they can be applied to different workflows.
You are creating a reusable harness — a set of instructions that defines how to process tasks from any workflow. Harnesses are stored in .claude/harnesses/ so they can be applied to different workflows.
If a harness name was provided as $ARGUMENTS, use it. Otherwise, ask.
Prompt the user for:
tdd, review-and-fix, research-only)Read the harness template from harness.yaml.tmpl.
Create .claude/harnesses/<harness-name>.yaml by populating the template:
{{HARNESS_NAME}} — the slug name{{DESCRIPTION}} — the description sentence{{CREATED_DATE}} — today's date in ISO format (e.g., 2026-03-29)Populate steps, constraints, done_criteria, and pause_between_tasks based on the user's answers from Step 1.
Translate the user's description into concrete, actionable steps. Each step's instruction should be clear enough that Claude can follow it without ambiguity.
Tell the user:
.claude/harnesses/<name>.yaml/checkpoint:run-harness <harness-name> <workflow-name>.claude/harnesses/ if it doesn't existnpx claudepluginhub samklevin/claude-skills --plugin checkpointAuthors a reusable, deterministic agent orchestration workflow as a self-contained .mjs script for Claude Code's Workflow tool, with structured phases, fan-out, and verification.
Framework for long-running, multi-session autonomous agent tasks with progress checkpointing, failure recovery, and task dependency management. Maintains append-only progress logs and checkpoint files for recovery across context window resets.
Suggests and guides creation of orchestrated workflows from natural language descriptions of complex multi-step tasks with sequencing, parallelism, conditionals, and error handling.