Alignment Checkpoint

Create or review an explicit pre-action alignment checkpoint. Use when the user requests a checkpoint or an unresolved decision materially changes scope, risk, or authority; ordinary bounded implementation does not require a checkpoint.

9 stars 4 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add jscraik/Agent-Skills --skill alignment-checkpoint
Manual install
git clone --depth 1 https://github.com/jscraik/Agent-Skills.git /tmp/Agent-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/Agent-Skills/Skills/agent-ops/alignment-checkpoint ~/.claude/skills/alignment-checkpoint

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Alignment Checkpoint

## When To Use

- The user explicitly requests a checkpoint before action.
- An unresolved decision materially changes scope, risk, or authority.
- Do not activate merely because a task is high-stakes or has multiple steps.
  Use proportionate verification for a clear, authorized task instead.

## Inputs

- User request, target, constraints, and existing authorization.
- The unresolved decision and its consequences, if a decision is missing.
- An explicit tool hold, if the user requested one.

## Outputs

- A concise statement of the goal, assumptions, and success criteria.
- The one material question or decision and the action waiting on it.
- An explicit approval boundary; schema-bound outputs include `schema_version`.

## Workflow

1. Identify the requested checkpoint or material unresolved decision.
2. Inspect only relevant read-only evidence unless the user prohibited tools.
3. State the decision and consequences; ask only what changes scope, risk, or
   authority. Do not ask for duplicate approval of an existing bounded request.
4. Hold only the affected action. Continue independent authorized work.
5. Finish the checkpoint when its decision and waiting action are clear.
   Continue implementation only under the authority actually granted.

## Failure Mode

- If the user says no tools, return the checkpoint without invoking tools.
- If evidence is unavailable, state the uncertainty and ask the necessary
Read the full skill on GitHub

Details

Skill name
alignment-checkpoint
Path
Skills/agent-ops/alignment-checkpoint/SKILL.md
License
Apache-2.0
Repo updated
16 November 2026

FAQ

What does the Alignment Checkpoint skill do?

Create or review an explicit pre-action alignment checkpoint. Use when the user requests a checkpoint or an unresolved decision materially changes scope, risk, or authority; ordinary bounded implementation does not require a checkpoint.

How do I install the Alignment Checkpoint skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jscraik/Agent-Skills --skill alignment-checkpoint. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Alignment Checkpoint popular?

It lives in jscraik/Agent-Skills, which has 9 GitHub stars and 4 forks.

Related skills

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.