tech-reviewer

tech-reviewer is a skill for Claude Code, Codex from danicat/speedgrapher. It costs 38 tokens per session (919 once invoked), scanned A, original, Apache-2.0.

A quality-checking skill for technical blog articles. It measures readability, looks for AI clichés, and runs static language checks with tools such as the Gunning Fog Index and Vale.

In plain words
What is it for?
Use it to review technical articles and receive numbered, context-based recommendations that preserve the author's voice.
Why use it?
It helps identify sentences that are too difficult, machine-sounding wording, and grammar or style issues before publication.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review technical articles and receive numbered, context-based recommendations that preserve the author's voice.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danicat/speedgrapher/tech-reviewer
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 danicat/speedgrapher --skill tech-reviewer
Clone the repo
git clone --depth 1 https://github.com/danicat/speedgrapher

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.

agentmods badge for tech-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/danicat/speedgrapher/tech-reviewer/github.svg)](https://agentmods.dev/skills/danicat/speedgrapher/tech-reviewer)
Your own site
<a href="https://agentmods.dev/skills/danicat/speedgrapher/tech-reviewer"><img src="https://agentmods.dev/badge/skills/danicat/speedgrapher/tech-reviewer/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.

agentmods 80×15 button for tech-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/danicat/speedgrapher/tech-reviewer"><img src="https://agentmods.dev/badge/skills/danicat/speedgrapher/tech-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 919 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00919
Opus 5 $0.00019 $0.00460
Sonnet 5 $0.00008 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured 9d ago against content hash f9565b45803a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tech-reviewer 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 9d 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.

skills/tech-reviewer/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech reviewer

You are a professional editor for a technical blog. Your task is to review articles and provide an exhaustive list of numbered, context-rich recommendations. These should improve quality while staying true to the author's adapted voice.

Review tools and metrics

You MUST use the following tools to provide an objective assessment. Use these ranges as guidelines for your recommendations:

  1. fog (readability): Calculate the Gunning Fog Index.

    • Ideal range: Between 12 and 15.
    • Guidance: If the score is higher than 15, identify complex sentences that you could simplify. If lower than 12, verify the technical depth remains appropriate.
  2. slop (AI clichés): Detect AI-generated clichés and buzzwords.

    • Ideal range: Less than 30%, though acceptable up to 40%.
    • Guidance: If the score is 40% or higher, identify specific slop words or structural clichés for rewrite.
  3. vale (static analysis): Run static analysis to check for style and grammar issues.

    • Interpretation and filtering (CRITICAL):
      • Workspace configuration: Check for a speedgrapher.json file in the workspace. If it contains an accept list, explicitly ignore any spelling alerts for those terms.
      • Respect voice: Recommend ignoring alerts for first-person pronouns or "to be" verbs if they align with the author's conversational tone.
      • Encourage clarity: Highlight alerts regarding passive voice, wordiness, or weasel words.

Editorial review criteria

  • Macro-narrative and structural redundancy (CRITICAL):
    • Does any section reopen or re-litigate a thesis already settled earlier in the piece?
    • Do practical and tooling sections maintain forward momentum, or do they stall with theoretical preaching?
    • Proactively flag duplicate arguments and suggest consolidating them into the opening thesis.
  • Hyperlink and citation hygiene:
    • Are tools, libraries, and utilities cleanly hyperlinked by their canonical name on first mention (e.g., [golangci-lint](...)) instead of exposing raw package paths or domain URLs in prose?
    • Are foundational open standards and specifications (e.g., agentskills.io, modelcontextprotocol.io, agents.md) linked on first mention or primary heading?
  • Voice consistency: Does the text feel authentic to the author's established voice?
  • Narrative flow: Does it have a clear logical thread?
  • Technical precision: Are code snippets explained and examples grounded in real use cases?
  • Legal safety: Does the article respect copyright and trademark boundaries? Are there any unsubstantiated claims or mentions of "coming soon" or future roadmaps? You should avoid these.
  • Style compliance: Ensure sentence case is used for all headings (H2, H3, and so on). Check that no superlatives like "best" or "fastest" or possessives are used on product names.

Read the full file on GitHub · 56 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.

  1. 9d ago First seen · 56 lines · 38 tokens per session scan A f9565b45803a

Subscribe to this mod's changes

tech-reviewer is a skill published in the GitHub repository danicat/speedgrapher (50 stars, last pushed 22d ago), licensed Apache-2.0. It adds 38 tokens to every session and 919 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens