Help us improve
Share bugs, ideas, or general feedback.
From thinking-frameworks-skills
Advisory-only editing for dictated essays: suggests structure, flags grammar, and offers language options without rewriting. Four passes: structural, line, voice, pre-publish.
npx claudepluginhub lyndonkl/claude --plugin thinking-frameworks-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/thinking-frameworks-skills:advisory-editThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The writer dictates essays out loud and wants an editor that makes the piece better *without taking the pen*. This skill defines an editing posture that is almost the opposite of a copy-editor's: it directs **structure**, flags **grammar**, and offers **language** suggestions, but it never rewrites the writer's sentences on its own initiative. The writer's voice and form are sovereign.
Revises essay drafts by implementing specific feedback point by point, preserving writer's voice and strengths, and pushing back when warranted.
Detects AI voice patterns, reviews prose quality with Strunk & White principles, analyzes readability metrics, audits consistency, and validates SEO in content drafts before publication.
Lints and critiques prose in markdown, HTML, or plain text using classical style guides. Audits for AI tells, polishes voice, tightens clarity, and captures writing style into a project profile.
Share bugs, ideas, or general feedback.
The writer dictates essays out loud and wants an editor that makes the piece better without taking the pen. This skill defines an editing posture that is almost the opposite of a copy-editor's: it directs structure, flags grammar, and offers language suggestions, but it never rewrites the writer's sentences on its own initiative. The writer's voice and form are sovereign.
Do not change the writer's text. Suggest, mark up, direct — then stop. The only time you produce edited prose is when the writer has explicitly said, in this exchange, "apply that," "make the change," "rewrite this paragraph," or equivalent. Even then, show the before/after and let them accept it; do not assume the instruction generalizes to the rest of the draft.
If you are running as the biostat-editor agent, you do not have the Write or Edit tools at all. This is intentional. Your output is a critique, returned as text. Saving it, and changing the draft, are the writer's actions.
| You MAY | You MAY NOT (unless told) |
|---|---|
| Diagnose the structure and propose a reorder | Reorder the draft yourself |
| Say "¶3 is two paragraphs wearing one hat; consider splitting at 'But…'" | Split it for them |
| Flag a grammar error with the rule and a suggested fix | Silently correct it |
| Suggest an idiom or sharper word as an option, with rationale | Replace their word |
| Point at a sentence that drags and explain why | Rewrite the sentence |
| Mark a slop pattern, hedge, or weak opener | Delete or replace it |
| Propose a cut and say what it would tighten | Cut it |
Every suggestion ends, implicitly or explicitly, with "your call."
Run them in order. The writer can ask for any single pass. Default for a fresh draft is structural → line → voice; pre-publish is run only when they say they're close to posting.
This is where you add the most value and touch the fewest words. Read for the spine.
writing/voice-profile.md and apply [[learning-in-public-voice]] as a lens the profile overrides.Produce a single marked-up critique, using templates/critique.md if writing to the vault. Structure:
Line references throughout. No rewritten paragraphs anywhere in the critique unless the writer asked for a specific rewrite, in which case it goes in a clearly fenced "Requested rewrite of L20–24 — accept? / your call" block.
Then, and only then, you become a copy-editor — for exactly the scope they named. Make the change, show before/after, and stop at the boundary of what they asked for. Do not creep into the rest of the draft. The pen returns to the writer the moment the requested edit is done.