← Search

Yomiyasu
Writing 🧪 Install ran in our test sandbox · Nov 18, 2026 📌 Pinned version: commit 79d15a6
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: none for the core skill (it works on text you hand…

Yomiyasu

Curated by Skill Harbor: Rewrites AI-generated Japanese into natural, high-information-density prose while preserving meaning: it dismantles inanimate subjects,

At a glance
What
Curated by Skill Harbor: Rewrites AI-generated Japanese into natural, high-information-density prose while preserving meaning: it dismantles inanimate subjects,
Cost
Free
Needs
none for the core skill (it works on text you hand it); Python 3 optional, only if you want to run the bundled linter, diff and check scripts. No account or key is needed, and installing the skill itself sends nothing anywhere.
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

Quick answer

Yomiyasu is a free Muse skill that rewrites AI-generated Japanese into natural, high-information-density prose while preserving meaning. It dismantles inanimate subjects, concretizes metaphorical verbs, strips emoji and decorative colons, and rebuilds sentences so who did what is clear. A bundled linter and diff checker help verify each rewrite.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 79d15a6

Before you start: tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead. Prerequisites: none for the core skill (it works on text you hand it); Python 3 optional, only if you want to run the bundled linter, diff and check scripts. No account or key is needed, and installing the skill itself sends nothing anywhere. Install "Yomiyasu" for me. It rewrites AI-generated Japanese into natural, high-information-density prose while preserving meaning: claims, emphasis, strength of assertion and each sentence's function, with bundled linter, diff and check scripts and reference lists. Source: https://raw.githubusercontent.com/nanaism/yomiyasu/79d15a621751cb7ad3bea556832209e9112e575f/skills/yomiyasu/SKILL.md (the skill is the whole skills/yomiyasu/ folder at that commit: SKILL.md, the references/ tree including its lists/ and domains/ subfolders, and the Python scripts in scripts/) Pinned version: install the code at commit 79d15a621751cb7ad3bea556832209e9112e575f exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. [FINGERPRINTS] SKILL.md at the pinned commit: SHA-256 8ff8c995a76adf08acb07b5698795bc0d24ffd8f60f5b5f17781455235ab48f9, 110,665 bytes (39,483 characters). If the fetched file does not match, it changed since the review: stop, tell me what you found and let me decide. Updated October 19, 2026: Skill Harbor regenerated this install prompt from the current upstream file. What changed since the version the previous prompt described (2.0.1): the skill is now version 2.0.2, and its trigger conditions are tightened — this is the only change to SKILL.md itself, whose rewriting rules and body are otherwise unchanged. In 2.0.1 the skill also fired on general requests such as making a text more readable, removing an AI feel, making Japanese sound natural, or reviewing technical articles, specifications, PR descriptions, internal reports and essays. In 2.0.2 it is used only when you invoke it explicitly by name (`/yomiyasu`, `$yomiyasu:yomiyasu`, `yomiyasu で推敲して` and the like) or when you clearly ask for Japanese polishing using the skill; standing instructions in CLAUDE.md, AGENTS.md or custom instructions that direct the use of yomiyasu count as a named invocation. It is not used for Japanese-writing requests that do not name it, nor for code, configuration or documentation updates. The name-only behavior from 2.0.1 is unchanged: with no text handed over it first reuses body text it wrote earlier in the conversation at my request (status reports and change notes do not count); failing that, it lists the `.md` and `.txt` files at the top of the working folder, excluding instruction files like AGENTS.md or CLAUDE.md and its own `.material.txt` extracts: it polishes the single candidate, asks me when there are several, and asks for pasted text when there are none; a file polished this way is saved under a new name in the same folder and the original file is never overwritten. The bundled scripts were updated internally with the version bump; they remain local Python standard-library tools with no network calls. Nothing is sent anywhere during installation itself, beyond the announced download of the skill folder from GitHub. 1. Download the whole skills/yomiyasu/ folder at the pinned commit (SKILL.md, references/ and scripts/) into a temporary folder. 2. Compare SKILL.md with the fingerprint from Skill Harbor's review of 2026-10-19: - SKILL.md: SHA-256 8ff8c995a76adf08acb07b5698795bc0d24ffd8f60f5b5f17781455235ab48f9, 110,665 bytes, 39,483 characters If it does not match, it changed since the review: do not install it yet, tell me what you found and let me decide. 3. Read SKILL.md and tell me in plain words: what the skill does when used, which services it connects to, whether it reads or sends any personal information or keys, and anything that seems unusual. Confirm these points from the file: - The tightened trigger conditions above: the file's description now limits use to explicit invocation by name (or a clear request to polish Japanese with the skill, including standing instructions in CLAUDE.md, AGENTS.md or custom instructions that name yomiyasu), and excludes Japanese-writing requests that do not name it and code, configuration or documentation updates. - The name-only invocation above, including that the polished file is saved under a new name and the original is never overwritten. - Meaning preservation comes first: claims, emphasis, assertion strength and sentence function are checked before and after the rewrite, and nothing is added that is not in the source, the request or the provided materials. - The scripts/ folder holds local Python text tools (linter, diff, check, and a hook script): tell me what each one does before anything runs them, and flag any network call or credential access. Nothing is sent anywhere during installation itself. 4. When I say yes, copy the whole folder's contents into my skills folder, in a folder named "yomiyasu". 5. Check the copy with no network calls (valid frontmatter, files in place) and tell me what was installed, where, and what is left for me to do (for example: disable similar Japanese style skills to avoid conflicting instructions, and install Python 3 if I want the bundled scripts). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: only touch the temporary folder and the install target. If something seems off, stop and ask me. Never print or paste a secret value.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit 79d15a6 · 2026-10-19
🧪 Install ran in our test sandbox · Nov 18, 2026
👁 Observed during the install test · Nov 18, 2026 : no network contact
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
79d15a6 · 2026-10-19
Sandbox install test
Install ran in our test sandbox · Nov 18, 2026
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.