checkpoint
Meta-cognitive decision support that analyzes current context and surfaces intelligent next-step options to the user. Use this skill when: (1) User explicitly invokes /checkpoint, (2) Significant work has been completed and a checkpoint is valuable, (3) Uncertainty or ambiguity exists about requirements or approach, (4) Task complexity has expanded beyond initial scope, (5) Before finalizing or committing to ensure nothing is missed. This skill pauses execution, assesses the situation holistically, and presents 2-5 contextually-appropriate options via AskUserQuestion, with a recommended option and rationale.
- Installs
- 43
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/petekp/agent-skills --skill checkpoint- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads checkpoint automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Checkpoint
Pause, assess, and surface intelligent next-step options to the user.
When to Trigger Proactively
Suggest this skill (without being asked) when detecting:
- Completion signal: A feature, fix, or milestone just finished
- Uncertainty signal: Requirements unclear, multiple valid paths, or low confidence in current direction
- Complexity signal: Scope expanded, unexpected dependencies emerged, or task is taking longer than expected
- Drift signal: Work may have diverged from user's original intent
- Quality signal: Code works but may benefit from review, testing, or refactoring
Workflow
1. Context Assessment
Silently evaluate the current state across these dimensions (do not output this analysis):
- Progress: What has been accomplished? What remains?
- Quality: Is the work solid, or are there rough edges?
- Alignment: Does recent work match what the user actually wants?
- Uncertainty: What assumptions were made? What's unclear?
- Risk: What could go wrong? What hasn't been tested?
- Efficiency: Is there a better path forward?
2. Generate Options
Based on assessment, generate 2-5 contextually-appropriate options. Draw from (but don't limit to) these archetypes:
| Archetype | When Relevant |
|---|---|
| Commit progress | Meaningful progress made, good stopping point |
| Systems audit | Complex changes, potential for bugs or regressions |
| Prioritize/plan | Multiple pending tasks, unclear what matters most |
| Re-evaluate decisions | Low confidence in recent choices, new information available |
| Clarify with user | Assumptions made, requirements ambiguous |
| Test/verify | Code works but edge cases untested |
| Refactor/clean up | Code functional but messy |
| Document | Complex logic that needs explanation |
| Step back | May be overcomplicating or missing simpler solution |
| Continue current path | Clear next step, no reason to pause |
Option generation principles:
- Options should be meaningfully different, not variations of the same thing
- Include at least one "continue forward" option when momentum is valuable
- Include at least one "pause and verify" option when risk is present
- Avoid analysis paralysis - fewer sharp options beat many vague ones
3. Select Recommendation
Choose one option as recommended. The recommendation should reflect:
- What would a thoughtful senior engineer do here?
- What reduces risk of wasted effort or rework?
- What serves the user's underlying goals (not just stated requests)?
4. Present via AskUserQuestion
Use AskUserQuestion with this structure:
Question: "What would you like to do next?"
Header: "Next step" (or contextually appropriate 1-2 words)
Options: [generated options with descriptions]
Option format:
label: Action verb phrase (e.g., "Commit current progress", "Run systems audit")description: 1 sentence explaining what this involves and why it might be valuable
Recommendation:
- Place recommended option FIRST in the list
- Append "(Recommended)" to its label
- Include rationale in the description
Example Output
For a scenario where a feature was just implemented but with some shortcuts:
AskUserQuestion:
question: "Feature implementation complete. What would you like to do next?"
header: "Next step"
options:
- label: "Review and refactor (Recommended)"
description: "Clean up the shortcuts taken during implementation before they become technical debt. The core logic works but could be more maintainable."
- label: "Add test coverage"
description: "Write tests for the new feature to catch edge cases and prevent regressions."
- label: "Commit and move on"
description: "The feature works - commit it and tackle the next task. Can refactor later if needed."
- label: "Walk me through what was built"
description: "Explain the implementation so you can verify it matches your expectations before proceeding."
Anti-Patterns
- Don't overthink: This skill should take seconds, not minutes
- Don't list every possible option: Curate the most valuable 2-5
- Don't recommend "ask user" when the situation is clear: Have a point of view
- Don't trigger too frequently: Reserve for genuine decision points, not every minor step
- Don't explain the assessment process: Just present the options naturally
FAQ
What does the checkpoint skill do?
Meta-cognitive decision support that analyzes current context and surfaces intelligent next-step options to the user. Use this skill when: (1) User explicitly invokes /checkpoint, (2) Significant work has been completed and a checkpoint is valuable, (3) Uncertainty or ambiguity exists about requirements or approach, (4) Task complexity has expanded beyond initial scope, (5) Before finalizing or committing to ensure nothing is missed. This skill pauses execution, assesses the situation holistically, and presents 2-5 contextually-appropriate options via AskUserQuestion, with a recommended option and rationale.
How do I install checkpoint?
Run npx skills add https://github.com/petekp/agent-skills --skill checkpoint in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/checkpoint/ (personal) or .claude/skills/checkpoint/ (project).
Which AI agents can use checkpoint?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is checkpoint safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains checkpoint?
It is published by petekp in petekp/agent-skills. It has 43 recorded installs.
More from petekp/agent-skills
typography
petekp/agent-skills
Apply professional typography principles to create readable, hierarchical, and aesthetically refined interfaces. Use when setting type scales, choosing fonts, adjusting spacing, designing text-heavy layouts, implementing dark mode typography, or when asked about readability, font pairing, line height, measure, typographic hierarchy, variable fonts, font loading, or OpenType features.
macos-app-design
petekp/agent-skills
Open the skill to read its SKILL.md instructions.
optimize-agent-docs
petekp/agent-skills
Build a retrieval-optimized knowledge layer over agent documentation in dotfiles (.claude, .codex, .cursor, .aider). Use when asked to "optimize docs", "improve agent knowledge", "make docs more efficient", or when documentation has accumulated and retrieval feels inefficient. Generates a manifest mapping task-contexts to knowledge chunks, optimizes information density, and creates compiled artifacts for efficient agent consumption.
codebase-study-guide
petekp/agent-skills
Generate a pedagogically-grounded study guide for learning an unfamiliar codebase. Use when the user wants to onboard onto a codebase, understand a project's architecture, create learning materials for a team, or asks things like "help me learn this codebase", "create an onboarding guide", "I'm new to this project", "how does this system work", "study guide for this repo", or "explain this codebase to me". Produces a structured document that builds understanding from purpose to systems to patterns, using evidence-based learning techniques (elaborative interrogation, concept mapping, threshold concepts, worked examples, progressive disclosure).
unix-macos-engineer
petekp/agent-skills
Expert Unix and macOS systems engineer for shell scripting, system administration, command-line tools, launchd, Homebrew, networking, and low-level system tasks. Use when the user asks about Unix commands, shell scripts, macOS system configuration, process management, or troubleshooting system issues.
explainer-visuals
petekp/agent-skills
Create high-quality animated explainer visuals for essays and blog posts. Use when the user wants to visualize concepts, processes, data, or ideas with interactive web animations. Triggers on requests like "create a visual for", "animate this concept", "make an explainer", "visualize this idea", "diagram this process", "show this data", or when essay content would benefit from visual explanation. Handles abstract concepts (mental models, frameworks), technical processes (algorithms, systems), and data visualization (trends, comparisons). Outputs self-contained HTML/CSS/JS that embeds directly in web content.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available