Claude Skills by otnc

Helps write and maintain Kiritan-based i18n — editing base/*.base.md files with :::kiritan{...} directives, choosing the sidecar/inline/catalog document strategy or the colocated/split/centralized/embedded runtime strategy, running kiritan init/build/check/translate/extract/typegen, and avoiding common mistakes such as hand-editing generated output. Use when a repo has a *.kiritanconfig config file, a base/ directory of *.base.md sources, or generated docs carrying a `<!-- kiritan:untranslate...

Detects and fixes "unnatural line breaks" in prose (Markdown/README-style documentation, and code comments or docstrings) — newlines inserted mid-sentence just to keep lines under some fixed column width. Works on both English and Japanese text. Use for requests like "fix the line breaks," "this is hard-wrapped," "the text is cut off mid-sentence," "unnatural line wrapping," "改行がおかしい," "文の途中で改行が入っている," "一定の文字数で折り返されている," as well as when writing, reviewing, or rewriting documentation and comme...

Stretches Claude Code's 5-hour and weekly plan limits (or API spend) while keeping output quality. Use when the user hits or nears a usage limit, sees high usage in /usage, has a long or slow session, asks to audit or slim down CLAUDE.md, rules, MCP servers, skills, subagents, hooks, model or effort settings, or asks how to use Claude Code more efficiently. Triggers include "usage limit", "rate limit", "session limit", "weekly limit", "token saving", "reduce cost", "context is full", "使用量", "...

Stretches OpenAI Codex (CLI, IDE extension, cloud) 5-hour and weekly usage limits or credits while keeping output quality. Use when the user hits or nears a Codex limit, sees fast usage in /status, has a long session, asks to audit or tune config.toml (model, reasoning effort, verbosity, compaction, tool output limits, MCP servers, profiles) or AGENTS.md, or asks how to use Codex more efficiently. Triggers include "usage limit", "rate limit", "5-hour limit", "weekly limit", "credits", "token ...

Stretches GitHub Copilot's monthly AI Credits (usage-based billing) across Chat, agent mode, Copilot CLI, code review and the cloud agent while keeping output quality. Use when the user is running out of Copilot credits or premium requests, sees a high bill or budget alert, asks which model to pick for cost, or asks to audit copilot-instructions.md, .instructions.md files, AGENTS.md or MCP tools for efficiency. Triggers include "AI Credits", "premium requests", "Copilot usage", "budget", "ove...

Stretches Cursor's monthly included usage (Cursor models pool and other models pool) and on-demand spend while keeping output quality. Use when the user is running out of Cursor usage, sees high on-demand charges, asks when to use Auto, Composer, Max Mode or a frontier model, or asks to audit .cursor/rules, .cursorrules, AGENTS.md, .cursorignore or MCP servers for efficiency. Triggers include "usage limit", "included usage", "on-demand", "Max Mode", "token saving", "reduce cost", "context lim...

Stretches OpenCode usage, including OpenCode Go's 5-hour, weekly and monthly limits, an OpenCode Zen pay-as-you-go balance, and bring-your-own-key provider spend, while keeping output quality. Use when the user hits or nears an OpenCode Go limit, burns through a Zen balance, asks which model to use for cost, or asks to audit opencode.json (model, small_model, compaction, instructions, agents, MCP) or AGENTS.md for efficiency. Triggers include "OpenCode Go", "OpenCode Zen", "usage limit", "5-h...

Cuts token use and stretches usage limits (5-hour, weekly and monthly caps, credits, API spend) of any AI coding agent while keeping output quality. Agent-neutral; use it for agents without a dedicated token-saver skill (Gemini CLI, Windsurf, Cline, Roo Code, Kiro, Amp and others) or when several agents are in play. Use when the user hits or nears a usage limit, sees high cost, has a long session, or asks to audit instruction files, rules, MCP servers, models or reasoning effort for efficienc...