storybuilder-prohibited-words
Skill2 starsChanged 4 months agoMITView on GitHub
Create a Wordlist The purpose of this skill is to create a master list of words that should NOT be used when writing strong fiction prose. Your job is to create a list of words we should not include when we're writing along with an explanation of why that word shouldn't be used in the format [word] - [reason-not-to-use-it]. For example: nice - this word is vague and doesn't communicate what is providing a positive response to what is being…
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
- line-editing-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-sceneSkill
- storybuilderSkill
- strong-writing-checklistSkill
- writing-coachSkill
The file
Files
Create a Wordlist The purpose of this skill is to create a master list of words that should NOT be used when writing strong fiction prose. Your job is to create a list of words we should not include when we're writing along with an explanation of why that word shouldn't be used in the format [word] - [reason-not-to-use-it]. For example:
nice - this word is vague and doesn't communicate what is providing a positive response to what is being described. It doesn't include a concrete description either.
gross - this is a telling word, we should show why this object/item/etc is disgusting rather than telling the reader how to feel about it.
Telling words Include words commonly used to "tell" rather than "show", including feeling words like love or hate, and sense words like taste or smell.
Curated list Here is a curated list of words to ALWAYS flag in your final output. nice good pretty beautiful ugly handsome disgusting gross think ponder wonder realize know understand reflect consider muse deliberate contemplate ask himself ask herself ask myself look looked feels looks feel looking feeling realized felt realizing thinks thinking wonders wondered realizes wondering that just literally something anything someone somebody anyone utilize methodology commence expedite endeavor synergize really very he watched she noticed he saw she saw she watched he noticed he notices she notices he watches she watches suddenly then basically finally and also next after that subsequently truly highly precisely totally actually usually definitely a bit sort of kind of in a sense generally probably organic low key sat down stood up faded away gathered together back home spread out as is start to starts to started to starting to starts start starting started somewhat slightly somehow some how seem seems definitely
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.

