An editing guide for rewriting technical blog drafts so they sound like the author, while keeping the original ideas and removing common signs of generic AI writing.

Use it to revise technical blog posts. It is not intended for academic papers or creating new articles.

It helps a draft retain personal voice, concrete evidence, and a structure suited to the topic instead of sounding polished but impersonal.

text-review — Skill for Claude Code and Codex by woliveiras/geremmyas

Install

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.

Any agent

npx skills add woliveiras/geremmyas --skill text-review

Clone the repo

git clone --depth 1 https://github.com/woliveiras/geremmyas

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/woliveiras/geremmyas/text-review/github.svg)](https://agentmods.dev/skills/woliveiras/geremmyas/text-review)

Your own site

<a href="https://agentmods.dev/skills/woliveiras/geremmyas/text-review"><img src="https://agentmods.dev/badge/skills/woliveiras/geremmyas/text-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/woliveiras/geremmyas/text-review"><img src="https://agentmods.dev/badge/skills/woliveiras/geremmyas/text-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,532 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00034	$0.02532
Opus 5.5	$0.00014	$0.01013
Sonnet 5.5	$0.00007	$0.00506
Haiku 4.5	$0.00003	$0.00253

Measured 2mo ago against content hash 356449e70aea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

text-review 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 2mo 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.

content/skills/text-review/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rewrite blog drafts so they sound like a real technical author with lived context, not like a polished generic assistant.

Prioritize three checks:

Voice: does this sound like the author has a point of view?
Evidence: does the text contain concrete context, constraints, failures, and decisions?
Shape: does the post use the right structure for what it is trying to do?

What to eliminate

Lexical tells

Remove or replace every instance of:

The em dash character: use a comma, parentheses, colon, semicolon, or a new sentence instead
Curly quotes and curly apostrophes (“ ” ‘ ’): use straight quotes (" ') so the text does not carry a copy-paste fingerprint
"delve into", "dive deep", "dive into", "unpack", "tackle", "explore" (as a section opener), "demystify"
"robust", "seamless", "powerful", "cutting-edge", "game-changing", "leverage" (verb), "harness" (verb), "utilize" (use "use")
"crucial", "essential", "vital", "pivotal", "key" (when used as a filler adjective)
AI-vocabulary nouns and verbs: "tapestry", "testament", "landscape" (as an abstract noun), "showcase", "underscore", "highlight" (as a filler verb), "foster", "garner", "intricate", "intricacies", "meticulous", "meticulously", "realm"
Promotional / travel-guide vocabulary: "boasts", "vibrant", "rich" (as filler), "nestled", "in the heart of", "renowned", "profound", "bustling", "hidden gem", "stunning"
"not just X, but Y" constructions - and the related "it's not X, it's Y", "X rather than Y", "no X, no Y, just Z": flatten into a direct claim
"It's worth noting that", "It's important to remember that", "It goes without saying that", "Needless to say"
"In the realm of", "In the world of", "In the landscape of", "When it comes to", "In today's X world", "In an era of"
"Let's", "we'll" used to create false intimacy when the author is writing alone
Forced tricolons (the rule of three): "fast, scalable, and reliable" - keep if each item is doing real work, cut if decorative
"Happy coding!", "Let's get started!", "Stay tuned!" - remove closing platitudes

Read the full file on GitHub · 160 lines

Changes

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.

2mo ago First seen · 160 lines · 34 tokens per session scan A 356449e70aea

Subscribe to this mod's changes

text-review is a skill published in the GitHub repository woliveiras/geremmyas (10 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 2,532 once invoked, about $0.0001 per session on Opus 5.5. 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.

Writing and docs

text-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
text-reviewwoliveiras/geremmyas	Skill	10	3mo ago	MIT	A	34	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code