Japanese Writing Drafter

What it does

When your agent uses it

• User mentions writing-rule proposal
• Writing lint 提案

Example prompts

• “this wording is bad, say it like X instead”
• “/japanese-writing-drafter”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Read, Bash

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1before / after を確定する: 直された元の表現 (before) と、operator が示した / 暗に求めた書き直し後の表現 (after) を会話から抽出する。before…
2. 2pattern を作る: before の該当フラグメントを Go 正規表現 (RE2) として書く。特殊文字はエスケープする。ヒット範囲を広げすぎない（writing-rule.v1 の pattern は文全体ではなく該当箇所のみでよい）。
3. 3good を作る: after をそのまま、または要点を保った短い言い換えとして書く。
4. 4scenes を決める: 会話の文脈から分かるときだけ ["external"] / ["chat"] / ["docs"] 等を付ける。不明なら省略する（省略は「全シーン適用」の意味になる。無理に推測しない）。
5. 5id を作る: 内容が分かる kebab-case スラッグに 8 桁の一意サフィックスを付ける（例: no-meta-narration-a1b2c3d4）。
6. 6追記する: 以下のコマンドで templates/schemas/writing-rule-proposal.v1.json に対する手書きバリデーション（必須キー + additionalProperties: false）を通してから 1…
7. 7operator に伝える: 追記した id と、確認・承認コマンド (scripts/writing-rule-list.sh / scripts/writing-rule-approve.sh --id ) を短く伝える。承認するかどうかは operator…

What it can do on your machine

Read from SKILL.md and the folder at commit 2b2b748. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Japanese Writing Drafter loads about 1.5k tokens when it runs. Until then it costs about 221 tokens; SKILL.md has 150 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~221

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Chachamaru127/claude-code-harness at commit 2b2b748, republished under its MIT licence (© Chachamaru127). 150 words, ~1,476 tokens.

name

japanese-writing-drafter

description

Detect when the operator corrects the agent's Japanese phrasing mid-conversation (rewrites a sentence, calls out a style problem, says 'this wording is bad, say it like X instead') and draft a pending writing-rule proposal into ~/.claude/writing-lint/proposals.jsonl for later human review. This skill is the ONLY writer of proposals.jsonl — it never edits rules.jsonl and never sets status to anything but pending. Promotion to rules.jsonl only happens via the human-run scripts/writing-rule-approve.sh. Use when user mentions writing-rule proposal, 表現を直して, 文体を直して, その言い方はNG, writing lint 提案, 指摘をルール化して. Do NOT load for: approving or rejecting proposals (use scripts/writing-rule-approve.sh), listing pending proposals (use scripts/writing-rule-list.sh), or scanning text against the existing dictionary (the writinglint engine / PostToolUse hook does that).

allowed-tools

Read, Bash

description-en

Detect when the operator corrects the agent's Japanese phrasing mid-conversation (rewrites a sentence, calls out a style problem, says 'this wording is bad…

description-ja

会話内で operator が agent の日本語表現を直した（文を書き直した、文体を明示的に指摘した、「その言い方じゃなくてこう書いて」と言った）ことを検知し、~/.claude/writing-lint/proposals.jsonl へ pending の writing-rule…

user-invocable

true

python3 - <<'PY'
import json, os, sys, uuid
from datetime import datetime, timezone

repo_root = "REPO_ROOT"  # 呼び出し時に実際のリポジトリルートへ置き換える
schema_path = os.path.join(repo_root, "templates/schemas/writing-rule-proposal.v1.json")
proposals_path = os.environ.get("CLAUDE_WRITING_LINT_PROPOSALS") or os.path.join(
    os.path.expanduser("~"), ".claude/writing-lint/proposals.jsonl"
)

with open(schema_path, encoding="utf-8") as f:
    schema = json.load(f)

record = {
    "id": "SLUG-" + uuid.uuid4().hex[:8],
    "pattern": "PATTERN_HERE",
    "good": "GOOD_HERE",
    "status": "pending",
    "evidence": "EVIDENCE_HERE",
    "created_at": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
}
# scenes / severity は分かるときだけ足す:
# record["scenes"] = ["external"]
# record["severity"] = "warning"


def validate(data, sch):
    required = set(sch.get("required", []))
    props = sch.get("properties", {})
    if sch.get("additionalProperties") is False:
        extra = set(data.keys()) - set(props.keys())
        if extra:
            raise ValueError(f"additional properties not allowed: {sorted(extra)}")
    for key in required:
        if key not in data:
            raise ValueError(f"missing required property: {key}")


validate(record, schema)

os.makedirs(os.path.dirname(proposals_path) or ".", exist_ok=True)
with open(proposals_path, "a", encoding="utf-8") as f:
    f.write(json.dumps(record, ensure_ascii=False) + "\n")

print(f"drafted pending proposal: {record['id']}")
PY

© Chachamaru127, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/japanese-writing-drafter of Chachamaru127/claude-code-harness.

Open the folder on GitHubat commit 2b2b748