OpenParable
Skip to content
← Back to skills

Cross Artifact Analysis

Productivity
cross-artifact-analysis

Cross Artifact Analysis is an Agent Skill for productivity published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Perform cross-artifact consistency and coverage analysis across constitution, specification, plan, and task artifacts to detect gaps, conflicts, and misalignments before implementation.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/methodologies/spec-kit/skills/cross-artifact-analysis/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/cross-artifact-analysis, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

  • When verifying that all specification requirements have corresponding tasks
  • When checking for contradictions between constitution and plan
  • When assessing readiness for the implementation phase

Key Principle

Every specification requirement must be traceable through the plan to at least one task. No artifact should contradict another. Coverage gaps and conflicts must be resolved before implementation.

Process

  1. Build traceability matrix - Map requirements -> plan components -> tasks
  2. Detect coverage gaps - Requirements without corresponding tasks
  3. Identify conflicts - Contradictory constraints or requirements across artifacts
  4. Verify constitution compliance - Plan and tasks comply with governance
  5. Check acceptance criteria - Task criteria match specification requirements
  6. Score consistency - Numeric score (0-100) across dimensions
  7. Determine readiness - Boolean assessment for implementation phase
  8. Human review - Approve analysis results before proceeding

Tool Use

Invoke via babysitter process: methodologies/spec-kit/spec-kit-planning (analysis phase) Full pipeline: methodologies/spec-kit/spec-kit-orchestrator