Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add design1online/author-it --skill strong-writing-checklistgit clone --depth 1 https://github.com/design1online/author-itWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/design1online/author-it/strong-writing-checklist)<a href="https://agentmods.dev/skills/design1online/author-it/strong-writing-checklist"><img src="https://agentmods.dev/badge/skills/design1online/author-it/strong-writing-checklist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/design1online/author-it/strong-writing-checklist"><img src="https://agentmods.dev/badge/skills/design1online/author-it/strong-writing-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02061 |
| Opus 5 | $0.00000 | $0.01030 |
| Sonnet 5 | $0.00000 | $0.00412 |
| Haiku 4.5 | $0.00000 | $0.00206 |
Grade A, and why
strong-writing-checklist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strong Writing Checklist
This is a comprehensive checklist that can be used to evaluate good writing or strengthen existing writing.
- Show, don't tell
- Maintains the character voice by taking into account their personality, background, wound/flaw, age, occupation and experiences. An old woman shouldn't suddenly sound like a valley girl. A private detective shouldn't act like a school teacher. A layperson wouldn't have knowledge or skills in advanced mathematical research without a concrete explanation. Someone who is poor doesn't own a million dollar car without a logical reason (ie inherited it from a rich relative, stole it, etc)
- Every scene should incorporate as many senses as possible to help the reader feel immersed in the environment: balance, sight, smell, taste, touch, temperature
- No repetitive phrases or words (ie don't start every sentence with I in a first person POV or use the word blue three times within the same four paragraphs)
- Use strong adjectives over adverbs
- Don't use second person pronouns unless they are in character dialogue or the entire scene is written in second person perspective
- Show the actions a character is taking or the emotions a character is feeling rather than telling the action or emotion directly (ie he smiled rather than he's happy)
- Pacing is important to good writing. Actions scenes, fight scenes or intense scenes should have shorter and punchier sentences. Sentences, paragraphs and chapters should vary in length. Lots of long sentences in a row is harder for people to read. If you do an analysis of sentence length it should have a variation in the length rather than lots of sentences in similar lengths. This helps set a rhythm to the story
- Chapters should be at least 1,500 words long. Chapters should typically be no longer than 3,500 words long. Chapters must never be more than 5,000 words
- Every scene needs a hook, escalation, pivot, conflict and consequences with the consequences leading to the hook of the next chapter
- Reduce the use of dialogue tags, the voice of the character or flow of the story should make it easy for the reader to tell who is talking. Only use dialogue tags when it's not clear who is talking in a long section of back and forth dialogue.
- Avoid adverbs in dialogue, use stronger verbs or adjectives
- Don't use passive indications or passive sentences.
- Tenses must be consistent throughout the story, scenes and chapters unless the passage is a flashback/something that happened in the past
- Don't use cliches
- Remove redundancies in words or sentences that say almost the exact same thing more than once
- Consistent point of view, for the chapter or scene, no head hopping
- No unnecessary filler words, reduce glue words by writing a sentence with stronger verbs or adjectives
- Writing word choice should meet the target audience, for example don't use words at an 8th grade reading level for a book written for kindergarteners. Do a lexical analysis to make sure the text is at the appropriate reading level.
- Slang/colloquialisms should exist in the character dialogue or story elements so that the world feels authentic. For example, characters might call food "chum" if they live in a world where eating is done out of necessity because it doesn't taste good
- World building should make sense for the location or elements presented in the story
- World building established should persist throughout the story, something introduced in chapter 1 shouldn't suddenly disappear by chapter 10
- Limit sentences that start with an initial pronoun or character names
- Avoid sentence starters
- Avoid generic descriptions
- Avoid misspelled words
- Avoid incorrect punctuation
- Avoid grammatical errors
- Don't start the story with a character waking up or in a dream
- Don't start the story with weather unless it's unusual weather
- The protagonist must be active with their actions/decisions driving the story forward not just reacting to the plot or environment changes happening around them
- POV must be consistent throughout the entire scene unless there's a scene break
- No head hopping where the narrator shifts between character perspectives within a single scene, paragraph, or even sentence.
- Avoid using anything other than he/she said or asked after character dialoge for best dialoge readability.
- Avoid plot holes or story beat inconsistencies
- Strong hook on the first sentence: catches readers attention and keeps them reading, has strong character voice, leaves reader asking questions, has tension or conflict or stakes
- No info dumping
- The last sentence of a chapter should setup a strong hook for the next chapter
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 106 lines · 0 tokens per session scan A 86d08ef77e0c
strong-writing-checklist is a skill published in the GitHub repository design1online/author-it (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,061 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.