declauding

# Declauding Turn LLM-shaped prose into prose a human technical writer would have written. Two output modes: - **clean** (default) — the rewritten text, nothing else. - **annotated** — a single-file HTML artifact: rewritten text, every changed passage marked, each with the original, the tic name, and why it goes. A toggle hides the marks so the result can be read straight through. Three ways it gets called, which change what you deliver: - **Pasted text** (default) — the user gives text in the conversation. Return the rewrite, plus a short list of what changed if the edit was substantial. - **File** — the user points at a path. Rewrite the file in place and report a summary in the conversation rather than pasting the whole result back. Edit prose only: leave code blocks, frontmatter, data, link targets and quoted specimens alone. - **Embedded** — another skill or agent is calling this as one step of a larger job (a PR description, a commit message, a doc). Return the final text and nothing else. No preamble, no summary, no tic list. ## Do not invent specifics The rewrite must not contain a fact, name, number, date, quote or citation that is not in the source. This is the failure mode the skill invites rather than prevents: the fix for a vague sentence is a specific one, and the specific has to come from the source or from the author. *Experts believe it plays a crucial role* becomes *the sources here do not say who studies it*, or gets cut. It does not b...