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 agentmods add skills/cdeistopened/skill-stack/voice-analyzernpx skills add cdeistopened/skill-stack --skill voice-analyzergit clone --depth 1 https://github.com/cdeistopened/skill-stackWhat 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 | $0.00059 | $0.02498 |
| Opus 5 | $0.00030 | $0.01249 |
| Sonnet 5 | $0.00012 | $0.00500 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
voice-analyzer 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 2d 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Analyzer
Transform writing samples into a codified voice style that can be replicated consistently.
Purpose
This skill analyzes 3-5 samples of writing to extract the patterns, techniques, and characteristics that define a distinctive voice. The output is a complete voice skill that can be used alongside anti-ai-writing to produce content in that voice.
Core Philosophy: Every distinctive writer has patterns - conscious or unconscious. By identifying and codifying these patterns, we can replicate voice authentically without losing what makes it human.
When to Use This Skill
- Establishing your own writing voice for consistent content
- Codifying a brand voice for team use
- Creating voice guides for ghostwriting clients
- Analyzing competitors or inspirations to understand their approach
- Building a library of voice styles for different contexts
Requires: 3-5 writing samples of 500+ words each (more samples = better analysis)
Output: A complete voice-[name]/SKILL.md file ready for use
The Analysis Process
Phase 1: Gather Samples
Collect 3-5 writing samples that represent the voice at its best:
Ideal samples:
- Published content the author is proud of
- Writing that received strong engagement or feedback
- Pieces that "sound like" the author
- Content from the same medium (all newsletters, all blog posts, etc.)
Avoid:
- Heavily edited or committee-written pieces
- Content written under constraints (legal, corporate)
- Very old writing that doesn't reflect current voice
- Mixed media (don't combine tweets with long-form)
Sample preparation:
- Paste each sample into a separate section
- Note the source/context for each
- Remove any content that was clearly written by others (quotes, etc.)
Phase 2: Extract Voice Characteristics
Analyze the samples across these dimensions:
2.1 Sentence Structure
Questions to answer:
- What's the average sentence length? (Short and punchy? Long and flowing?)
- Does the writer vary length deliberately?
- Are sentences simple or complex?
- How does the writer use punctuation?
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.
- 2d ago First seen · 380 lines · 59 tokens per session scan A 925993ccdec7
voice-analyzer is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 2,498 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…