agentleFS
hardness1020hardness1020/VibeFlow/.claude/skills/validate-checkpoint/SKILL.md

validate-checkpoint

Skill8 starsChanged 8 months agoMITView on GitHub

Checkpoint validation and guardrail enforcement for the VibeFlow docs-first development workflow

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All validation scripts output JSON with this structure:

    line 106
  2. Very specific:

    After a checkpoint passes, update docs/workflow-state.yaml:

    line 140

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

validate-checkpoint

Checkpoint validation and guardrail enforcement for the VibeFlow docs-first development workflow.

Purpose

This skill validates checkpoint completion before stage progression:

  • Checks that required artifacts exist with all sections
  • Enforces the docs-first mandate
  • Runs validation scripts and reports pass/fail/warn status
  • Returns structured JSON reports with blocking issues

Workflow

Validate Request
    │
    ├── Determine checkpoint or document type
    ├── Locate required artifacts
    └── Select validation script
    │
    ▼
Run Validation
    │
    ├── Execute validation checks
    ├── Collect errors and warnings
    └── Generate JSON report
    │
    ▼
Report Results
    │
    ├── Output pass/fail summary
    ├── List blocking issues
    └── Return exit code (0=pass, 1=fail, 2=warn)

Usage

Validate a Specific Checkpoint

/validate-checkpoint <number>

Example:

/validate-checkpoint 1

Validate Current State

/validate-checkpoint

This auto-detects the current stage and validates the appropriate checkpoint.

Validate Specific Document

/validate-checkpoint prd
/validate-checkpoint discovery <ID>
/validate-checkpoint spec <spec-name>
/validate-checkpoint feature <ID>
/validate-checkpoint opnote <ID>

Checkpoints

#CheckpointAfter StageValidates
1Planning CompleteDPRD, Discovery, SPECs, ADRs
2Design CompleteEFEATURE spec with API Design
3Tests CompleteFFailing unit tests with stubs
4Implementation CompleteHPassing tests, quality validation
5Release ReadyJOP-NOTE with all sections
6DeployedLDeployment verified, indices updated

Scripts

The following scripts are available in scripts/:

  • validate_checkpoint.py - Master validator, orchestrates all checks
  • check_planning.py - Checkpoint #1: Planning phase validation
  • check_design.py - Checkpoint #2: Design phase validation
  • check_tests.py - Checkpoint #3: Test phase validation
  • check_implementation.py - Checkpoint #4: Implementation validation
  • check_release.py - Checkpoint #5: Release readiness validation
  • check_deployed.py - Checkpoint #6: Deployment verification

Output Format

All validation scripts output JSON with this structure:

{
  "checkpoint": 1,
  "name": "Planning Complete",
  "valid": false,
  "issues": [
    {
      "severity": "error",
      "file": "docs/prds/prd.md",
      "message": "Missing required section: Success Metrics"
    }
  ],
  "warnings": [
    {
      "file": "docs/specs/spec-api.md",
      "message": "Spec version not incremented despite contract changes"
    }
  ],
  "passed": 5,
  "failed": 2,
  "summary": "Checkpoint #1 NOT PASSED: 2 errors, 1 warning"
}

Exit Codes

  • 0 - All validations passed
  • 1 - Validation failed (blocking issues found)
  • 2 - Warnings only (can proceed with caution)

Manifest Update

After a checkpoint passes, update docs/workflow-state.yaml:

  • Set checkpoint to the number that passed (e.g., checkpoint: 2 after CP#2 passes)

Stage advancement is handled by: /manage-work advance <ID>

References

See references/checkpoint-criteria.md for detailed validation criteria for each checkpoint.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.