absorblisted

# Absorb ## Activation Contract Use this skill when the user wants to inspect an external repository or local project to learn from its AI-harness setup: agents, skills, prompts, orchestration rules, or instruction patterns. Do not use it for application code review, bug hunting, architecture review of the product itself, or test-quality audits. ## Required Input - One or more targets: git URL(s) and/or local path(s). - Optional focus: skills, agents, prompts, workflows, installer patterns, or comparison themes. If no valid target is provided, ask for it before continuing. ## Hard Rules - Analyze harness and agent configuration, not the external project's business code quality. - Verify practices from source files, activation points, or wiring; do not promote README claims as proven behavior. - Contrast every candidate practice against this repository before recommending adoption. - Prefer repo-native context for the contrast step: `AGENTS.md`, `.ai/atl/skill-registry.md`, `domains/*/README.md`, `skills/*/SKILL.md`, and relevant local artifacts. - When available, delegate read-heavy discovery to subagents or researcher passes instead of relying on memory. - Never auto-adopt, auto-commit, or silently edit this repository as a result of the audit. ## Workflow ### 1. Scope and resolve targets For each target: - If it is a local path, verify it exists. - If it is a git URL, clone or update it only with user awareness and to a clearly stated local destination. - Confir