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 felipeelias/claude-marketplace --skill writing-stylegit clone --depth 1 https://github.com/felipeelias/claude-marketplaceWrote 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/felipeelias/claude-marketplace/writing-style)<a href="https://agentmods.dev/skills/felipeelias/claude-marketplace/writing-style"><img src="https://agentmods.dev/badge/skills/felipeelias/claude-marketplace/writing-style/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/felipeelias/claude-marketplace/writing-style"><img src="https://agentmods.dev/badge/skills/felipeelias/claude-marketplace/writing-style.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 | $0.00088 | $0.01591 |
| Opus 5 | $0.00044 | $0.00796 |
| Sonnet 5 | $0.00018 | $0.00318 |
| Haiku 4.5 | $0.00009 | $0.00159 |
Grade A, and why
writing-style 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 12d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Style
Personal writing style skill. Apply when generating or reviewing prose.
Format Detection
Before writing or reviewing, determine the format:
- Blog post: writing for the Jekyll blog, markdown with front matter. Consult
references/blog-post.mdfor structure and conventions. - PR description: writing a pull request body for GitHub. Consult
references/pr-description.mdfor structure and style. - Unknown: anything else (commit message, docs, README, comment)
If the format is unknown, apply only the Voice Rules and AI Pattern Detection below. Do not force a structure template on content that does not match a known format.
Voice Rules (Always Apply)
These rules apply to all writing, regardless of format.
Tone
- Builder who writes about what he's made and why
- First person, practical, no posturing
- Smart but not academic
- Personal but not confessional
- Opinionated but fair: mention alternatives, link to competitors
- State motivation in one sentence and move on
- Trust the reader to figure out why they should care
Sentence Level
- Short sentences. Rarely past 25 words.
- Lead with the concrete thing, not the abstract framing.
- Parentheticals for small asides rather than separate sentences.
- Colons to introduce lists, explanations, or examples.
- No em dashes. Use colons, commas, or restructure.
Blacklisted Phrases
Never use these phrases or patterns:
- "In this post, I'll show you..."
- "Let's dive in" / "Without further ado"
- "You might be wondering..." / "You're probably wondering..."
- "In conclusion" / "To wrap up" / "To summarize"
- "It's worth noting that" / "One thing to note is that"
- "Game-changer" / "Powerful" / "Robust" / "Elegant" / "Seamless"
- "Leverage" / "Utilize" (use "use")
- "Ecosystem" / "Deep dive" / "At the end of the day"
- "Scratch my own itch"
- Hedges: "actually", "maybe", "just", "simply", "really"
Patterns to Avoid
- Preambles that sell the importance of the topic before getting into it
- Summary/conclusion sections restating what was covered
- Rhetorical questions as transitions between sections
- Reader-mind-reading ("you might think", "you're probably wondering")
- Correlative constructions ("not X, but Y") as a rhetorical device
- Symmetrical constructions that sound polished but say nothing
- Abstract analysis without personal stakes or concrete examples
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 155 lines · 88 tokens per session scan A bf6b0fb71a39
writing-style is a skill published in the GitHub repository felipeelias/claude-marketplace (1 stars, last pushed 4mo ago), licensed MIT. It adds 88 tokens to every session and 1,591 once invoked, about $0.0004 per session on Opus 5. 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
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
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…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.
ensure-pipelines-host
Ensures the tenant has a usable Power Platform Pipelines host environment before any pipeline operation runs. Detects host state via the same resolution order as the Power Apps UI (org-db setting → BAP env metadata → default-custom-host setting); if any existing host (Platform or Custom) is found, uses it. If no host…