writing-skillslisted

# Writing skills One property decides whether a document works: the agent takes the same process every run. The levers below produce it. The packaging differs across a skill, an AGENTS.md, and a pointer-reached doc; the writing does not. ## Contract | Field | Bound contract | |---|---| | Trigger | A SKILL.md or AGENTS.md/CLAUDE.md is being authored, refactored, ported, or upgraded, or the user asks to write a skill, improve one, or fix unreliable skill firing | | Authority | Reversible local writes to the target document and the skill directory it belongs to, plus the repository-owned registration or attribution surfaces those artifacts require. Never publishes, installs, commits, or mutates remote state | | Side effect | The target document changes on disk when the request is to author or refactor one. Guidance alone when the request is a review | | Done | The document is predictable, and the repository's own gate passes on every changed file | ## Inputs The document being authored or refactored: a skill, an AGENTS.md/CLAUDE.md, or a pointer-reached doc. Optionally the surrounding skill tree, which co-location and routing decisions need. ## Procedure Each step names its lever and its completion criterion. The levers themselves live in `references/authoring-levers.md`; load it when a step's name is not enough to act on. 1. Identify the document type: a skill, an AGENTS.md/CLAUDE.md, or a pointer-reached doc. Done when: the type is named, because step 8 fires only f