From draft
Use this skill whenever someone wants feedback on a piece of writing without committing to changing it: essays, emails, board policies, internal docs, marketing copy, blog posts, or any prose draft. Trigger on phrases like "critique this", "how does this read?", "what's wrong with this", "give me notes on this", "review this draft", "does this land", "get me a second opinion on this", or "/critique <file>". This is a read-only pass — it never edits the file. If the user wants the writing actually fixed, not just assessed, use `tighten` instead.
How this skill is triggered — by the user, by Claude, or both
Slash command
/draft:critiqueThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Runs a document through **Deirdre** (the `editor` sub-agent, a critic built on Deirdre
Runs a document through Deirdre (the editor sub-agent, a critic built on Deirdre
McCloskey's Economical Writing) and reports what she finds. This skill only reads and
reports — it never touches the file. For the version that applies the fixes, use tighten.
See ../../references/deirdre-method.md for the full
method: how the editor sub-agent works, chunking rules, the critique prompts, and the
surgical/substantive distinction.
tks, and split it into Pass 1
chunks per the chunking rules in the shared method file.editor agent per chunk (parallel batches) with the
granular prompt. Collect the line-by-line notes.tighten and I'll just apply it."Read-only. Never edits, sends, posts, or touches anything outside its own report.
npx claudepluginhub benjaminjackson/writing-skills --plugin draftGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.