# Agent Instructions This repository is the source vault for automation-oriented Skills. ## Scope Work in this repository should focus on: - collecting automation Skill source code - maintaining `SKILL.md` files - maintaining scripts, tests, fixtures, and examples - documenting migration and installation workflows - keeping a lightweight registry of available Skills Do not migrate existing CCPE System content into this repository. Do not pre-register speculative Skill candidates. Skills should come from real business-system needs or recurring local workflow automation. ## Boundary With CCPE `skills-vault` owns automation Skill implementation source. `ccpe-system` owns: - expert agents - committees - runtimes - model cards - model indexes - architectural registrations for important Skills If an automation Skill becomes a dependency of a CCPE runtime, agent, or committee, create only a lightweight CCPE registration in `ccpe-system`. Do not duplicate this repository's implementation source there. ## Editing Rules - Prefer small, focused changes. - Keep Skill directories self-contained. - Use lowercase kebab-case for Skill names and file names. - Run Python code and tests through the shared `skills-vault` conda environment by default, for example `conda run -n skills-vault python ...`. Use another environment only when a concrete dependency conflict requires it. - Preserve behavior during first migration; refactor only after baseline behavior is captured. - Add tests for transformations, file rewrites, parsing behavior, and safety checks when practical. - Do not write secrets, tokens, machine-specific credentials, or generated cache files into the repository. - Do not treat business systems such as `video-workbench` as direct consumers of this repository. They should use installed Skills from `.agents/skills`; this repository owns source copies. ## Expected Skill Directory ```text skills// SKILL.md README.md scripts/ tests/ fixtures/ ``` Use [templates/skill](templates/skill) for new migrations.