A checkpoint skill to ensure goals remain aligned during complex tasks.

Install

mkdir -p .claude/skills/checkpoint && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13342" && unzip -o skill.zip -d .claude/skills/checkpoint && rm skill.zip

Installs to .claude/skills/checkpoint

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Named decision point for long-running tasks — PIVOT, REFINE, or PROCEED
71 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Assess the current state of a long-running task
  • Verify goal alignment with the original objective
  • Identify new risks or unknowns since the last checkpoint
  • Make explicit decisions to PIVOT, REFINE, or PROCEED
  • Document abandoned approaches and reasons to `context/learnings.md`
  • Provide a structured output for checkpoint status

How it works

The skill provides a structured pause to assess task progress, goal alignment, and new risks, forcing an explicit decision (PIVOT, REFINE, or PROCEED) with documented rationale, and logs abandoned paths.

Inputs & outputs

You give it
Current state of a long-running task
You get back
Checkpoint status with decision (PIVOT, REFINE, or PROCEED), rationale, and next action

When to use checkpoint

  • Pause long-running project
  • Pivot strategy
  • Refine project approach

About this skill

Checkpoint Skill

A structured pause during long-running tasks. Prevents tunnel vision and catches drift before it compounds.

What Claude Gets Wrong Without This Skill

Without checkpoints, Claude continues executing a plan past the point where new information has invalidated one of its assumptions. The compound reliability math is real: at a 10% error rate per step, 10 steps yields 35% success. A checkpoint at step 5 resets the accumulation.

The Three Decisions

PROCEED — on track, no new risks, continue as planned.

REFINE — mostly correct, but one or two steps need adjustment. Document what changed and why, then continue.

PIVOT — the approach is fundamentally wrong or blocked. Stop. Re-plan the affected phase. Write the abandoned approach to learnings.md — this is high-value content.

A PIVOT is not a failure. A PIVOT without documentation is a failure.

Checkpoint Output

Checkpoint — [task] — Step [N] of [N]

Completed: [list]
In Progress: [current step]
Blocked / New Info: [if any]

Decision: PROCEED / REFINE / PIVOT
Rationale: [one sentence]
Next: [specific next action]

When Checkpoints Are Required

  • After every 5 sequential steps (mandatory)
  • When a blocker appears
  • When new information invalidates an assumption
  • When the task has been running for a long time without a natural pause
  • When context usage reaches 90% (warning threshold — do not wait for 95%)

Context Usage Thresholds

Claude Code compacts at 93% of effective context (window minus 20k overhead). PSC checkpoints fire earlier:

LevelAction
~90%Run checkpoint immediately — surface state, decide PIVOT/REFINE/PROCEED
~95%Blocking threshold — new tool calls may fail. Compact now.
Mid-debugDo NOT compact — stack traces and error traces are the tool

Signals that context is at 90%+: earlier parts of the conversation feel distant, rules from CLAUDE.md feel less active, you are uncertain about a constraint stated early in the session.

When in doubt, checkpoint. The cost of a false positive is one checkpoint. The cost of a missed threshold is silent context drift.

Anti-Patterns

Do not issue a PROCEED when there are unresolved blockers. Acknowledge them and decide.

Do not PIVOT without writing the abandoned approach to learnings.md. Future sessions will revisit the same dead end without that record.

Mandatory Checklist

  1. Verify completed steps are listed accurately (not optimistically)
  2. Verify any new information since the last checkpoint was surfaced
  3. Verify the decision (PIVOT/REFINE/PROCEED) has an explicit rationale
  4. Verify a PIVOT writes the abandoned approach to context/learnings.md
  5. Verify the next action is specific, not "continue with the plan"

When not to use it

  • When the user wants to issue a PROCEED with unresolved blockers
  • When the user wants to PIVOT without documenting the abandoned approach
  • When the user wants to compact context during mid-debug

Limitations

  • It requires manual verification of completed steps and new information
  • It does not automatically resolve blockers or implement refinements
  • It relies on the user to document abandoned approaches during a PIVOT

How it compares

This skill introduces mandatory decision points and documentation for long-running tasks, preventing tunnel vision and ensuring explicit choices to pivot, refine, or proceed, unlike continuous execution without formal review.

Compared to similar skills

checkpoint side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
checkpoint (this skill)04moNo flagsIntermediate
planning-with-files2336moReviewIntermediate
trello412moReviewBeginner
pmbok-project-management389moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

planning-with-files

davila7

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

233106

trello

openclaw

Manage Trello boards, lists, and cards via the Trello REST API.

41205

pmbok-project-management

jgtolentino

Comprehensive PMP/PMBOK project management methodologies and best practices. Use this skill when users need guidance on project management processes, templates, knowledge areas, process groups, tools, techniques, or certification preparation. Covers all 10 PMBOK Knowledge Areas and 5 Process Groups with practical templates, frameworks, and industry-standard approaches. Includes risk management, stakeholder engagement, schedule management, cost control, quality assurance, and resource planning.

38183

clickup

civitai

Interact with ClickUp tasks and documents - get task details, view comments, create and manage tasks, create and edit docs. Use when working with ClickUp task/doc URLs or IDs.

37176

ma-playbook

alirezarezvani

M&A strategy for acquiring companies or being acquired. Due diligence, valuation, integration, and deal structure. Use when evaluating acquisitions, preparing for acquisition, M&A due diligence, integration planning, or deal negotiation.

39122

create-plan

antinomyhq

Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with objectives, step-by-step implementation tasks using checkbox format, verification criteria, risk assessments, and alternative approaches. Use when users need thorough analysis and structured planning before implementation, when breaking down complex features into actionable steps, or when they explicitly ask for a plan, roadmap, or strategy. Strictly planning-focused with no code modifications.

36121

Search skills

Search the agent skills registry