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 jykim/claude-obsidian-skills --skill voice-clone-skillgit clone --depth 1 https://github.com/jykim/claude-obsidian-skillsWrote 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/jykim/claude-obsidian-skills/voice-clone-skill)<a href="https://agentmods.dev/skills/jykim/claude-obsidian-skills/voice-clone-skill"><img src="https://agentmods.dev/badge/skills/jykim/claude-obsidian-skills/voice-clone-skill/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/jykim/claude-obsidian-skills/voice-clone-skill"><img src="https://agentmods.dev/badge/skills/jykim/claude-obsidian-skills/voice-clone-skill.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 | $0.00094 | $0.02741 |
| Opus 5.5 | $0.00038 | $0.01096 |
| Sonnet 5.5 | $0.00019 | $0.00548 |
| Haiku 4.5 | $0.00009 | $0.00274 |
Grade A, and why
voice-clone-skill 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Clone
Use the local MLX runtime selected by VOICE_CLONE_PROJECT (default: ~/dev/VoiceCloning). It should contain the Qwen3-TTS 1.7B Base 8-bit model, a Python 3.11 environment, saved voice profiles, and clone_voice.py.
Treat source recordings as immutable. Use only reference voices the user supplied or authorized, and do not upload, publish, or send generated speech unless explicitly requested.
This skill includes the repository owner's authorized jin reference profile under assets/voices/jin/. To install it locally, copy that directory to $VOICE_CLONE_PROJECT/voices/jin/. The sample is provided for transparent voice-cloning experiments; do not use it to deceive, impersonate the speaker, imply endorsement, or bypass consent requirements.
Choose the mode
- For speech in an existing cloned voice, use the generation workflow below. If exactly one profile exists and the user does not name one, use it. If several exist and the intended voice is ambiguous, list them and ask which one.
- For a new reference recording, create a reusable profile first. If the user supplied no target text, generate the neutral Korean test sentence
안녕하세요. 이 목소리를 바탕으로 만든 보이스 클로닝 테스트입니다.after preparing the profile. - Preserve user-provided target text exactly. Default the language to Korean unless the text or request clearly indicates another language.
Generate with a saved profile
List available profiles when needed:
python3 <skill-directory>/scripts/generate_voice.py --list
Generate speech:
python3 <skill-directory>/scripts/generate_voice.py \
--voice jin \
--text "읽을 문장"
The helper reads the profile's reference.wav and reference.txt, calls the local Base model with both values, and writes a timestamped 24 kHz mono PCM WAV under $VOICE_CLONE_PROJECT/output/ unless --output is provided.
For multi-sentence narration, the helper groups preceding sentences into chunks of at most 220 characters when possible and always generates the final sentence independently. It joins chunks with 220 ms of silence. It does not fade speech or append trailing silence. A single sentence uses the same direct generation path without chunking. Preserve the supplied text exactly; chunking may add timing between sentences but must not add, remove, or rewrite words.
What ships with it
10 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.
- agents/openai.yaml 220 B
- assets/voices/jin/NOTICE.md 670 B
- assets/voices/jin/reference.txt 116 B
- assets/voices/jin/reference.wav 328 KB
- scripts/audio_tail.py 4.1 KB runs code
- scripts/finalize_audio.py 2.0 KB runs code
- scripts/generate_chunked.py 4.3 KB runs code
- scripts/generate_voice.py 3.8 KB runs code
- scripts/prepare_voice.py 3.8 KB runs code
- scripts/verify_output.py 6.4 KB runs code
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.
- 1mo ago First seen · 136 lines · 94 tokens per session scan A ed96bcbc59c3
voice-clone-skill is a skill published in the GitHub repository jykim/claude-obsidian-skills (50 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 2,741 once invoked, about $0.0004 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 2026-09-22.
Other skills, from other repositories
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…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…