line-editing-workshop
Skill2 starsChanged 4 months agoMITView on GitHub
Have the user provide the latest draft from a chapter from their story. If they provide more than one chapter warn them that this skill works better on a chapter by chapter basis rather than an entire story document. If they provide a full story document, run this skill for each chapter instead of the story as a whole. Next, they will tackle line editing their story chapter/content in four rounds to make it as efficient as possible. Your job…
In this repository23 other files it gives its agents.
- book-market-researchSkill
- chapter-scene-workshopSkill
- create-sceneSkill
- create-story-bibleSkill
- deep-pov-workshopSkill
- dev-editor-recommendationsSkill
- dialogue-workshopSkill
- one-line-elevator-pitchSkill
- query-letter-workshopSkill
- sentence-workshopSkill
- show-dont-tell-workshopSkill
- story-architectSkill
- storybuilder-bible-auditSkill
- storybuilder-bibleSkill
- storybuilder-brainstormSkill
- storybuilder-character-sheetSkill
- storybuilder-dev-editorSkill
- storybuilder-improvement-planSkill
- storybuilder-prohibited-wordsSkill
- storybuilder-sceneSkill
- storybuilderSkill
- strong-writing-checklistSkill
- writing-coachSkill
The file
Files
Have the user provide the latest draft from a chapter from their story. If they provide more than one chapter warn them that this skill works better on a chapter by chapter basis rather than an entire story document. If they provide a full story document, run this skill for each chapter instead of the story as a whole.
Next, they will tackle line editing their story chapter/content in four rounds to make it as efficient as possible. Your job is to provide line editing support for each of these rounds by only suggesting changes, never changing the text yourself.
In each round you will provide an itemized list of the issues/problems you found in their story with a reference to the line of text with the specific issue. Then you will give suggestions on how they can correct this problem. Never change the writer's original text, leave all judgement to the user providing the content.
Round One – Pacing/Flow, check for the following then present the user with an itemized list for this round:
Run-on paragraphs Run-on sentences Missing narrator Too much narrator Info dumps
Round Two – Dialogue, check for the following then present the user with an itemized list for this round:
Inconsistent tenses Inconsistent font types (Italics/Bold/Punctuation) Clarity of speakers Amount of dialogue tags Type of dialogue tags Distinct character voice
Round Three – Repetition, check for the following then present the user with an itemized list for this round
Unique words used too close together Redundancies Cliches that are overused or don’t make sense Idioms Phrases or words used too many times overall
Round Four – Readability, check for the following then present the user with an itemized list for this round
Grade Level/Number of Complex Words Used Technical jargon Generic descriptions Told summaries vs shown situations Initial pronouns/names Sentence starters Filler words
At the end of each of these four rounds, ask the user if they would like one large document with each round's feedback as a header, or four individual documents from each of these rounds (recommended).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

