skill-harmonization

Skill Harmonization

If a slash or dollar invocation already supplied these instructions, follow them directly. In that case, do not invoke this skill again through a skill tool.

Treat the current Git repository and relevant user-installed skills as one repository-centered portfolio. Inventory it mechanically. Distinguish defects from judgment calls and deliberate relationships. Then report, plan, or implement according to the invoking task's authority.

Success means every repository skill was considered against relevant repository and user candidates. Every conclusion has path and client evidence. Observations remain separate from inference. The selected mode ends with appropriate findings, recommendations, validation, and deliberate no-change conclusions.

Input and Prerequisites

[task] is optional free-form guidance. Use it to narrow the question, desired outcome, or authorized implementation scope. If it is absent, infer intent from the surrounding request. An invocation without write intent is read-only.

1. Require ai-skillet 1.0.0 or newer on PATH. If it is unavailable or too old, stop and ask the user to install or upgrade it.

2. Require git on PATH, then resolve the current repository with git rev-parse --show-toplevel. Do not read Git history. If Git is unavailable, stop with:

   skill-harmonization: Git is required and was not found on PATH.
   

   If repository resolution fails, stop with:

   skill-harmonization: run from inside a Git repository.
   

Authority and Mode

Derive behavior from the user's task and the host's authority rules. This skill does not introduce its own phase gate.

• For inspection, audit, review, diagnosis, or an invocation with no write intent, investigate and return an assessment. Do not edit.
• For a planning request, return a decision-complete plan grounded in the inventory and static evidence. Do not implement it.
• For an implementation request, apply the authorized changes, validate them, and report the resulting portfolio.
• Do not force a report-first step, saved report, plan approval, or implementation phase. Ask only when an unresolved choice changes scope, safety, or intended outcome.
• Preserve normal confirmation boundaries for renames, removals, destructive actions, and global skills whose canonical source ownership remains unknown.