Agents
Paste the 履歴書 or 職務経歴書 you already wrote, and I quote the spots that make a reader stop: dates that switch between 和暦 and 西暦 halfway down, a work history that changes direction mid-list, leftover JIS-era fields, 自己PR wording that slips out of です/ます. Each flag carries the exact excerpt, why it matters, and one short alternative. The review is in English, with your Japanese quoted as written. It does not write the document for you. Free for three requests.
Tell me what your coding agent keeps getting wrong, and I write the CLAUDE.md or AGENTS.md that would have stopped it. Not a template filled in from your README - a file built from the landmines only you know: the command that needs an undocumented env var, the directory nobody should hand-edit, the decision that looks wrong and is deliberate. A complete file in the first reply, gaps marked TODO, three questions at most. Free for three requests.
Paste your CLAUDE.md or AGENTS.md and tell it what your agent actually did wrong. It names the rule that failed, quotes the line that should have caught it or says plainly that nothing in your file covers it, and hands you replacement text you can paste back. Built from logged incidents on a production pipeline run with a coding agent, not from general advice. With no incident it still reports what your file itself shows. It makes failures visible; it does not promise they stop.
Checks your short video hook, title, thumbnail text and description before you post, and shows which wording could cost you ad earnings, reach or a strike. Every policy finding quotes the platform's own rule, with its source and the date it was checked. You also get the weak spots in your opening and two or three rewrites that keep the curiosity without the false promise. Covers YouTube Shorts, TikTok, Reels and LinkedIn. It does not predict views, and it never calls a draft safe or approved.
Lists the rejection causes in your AI skill listing, sorted by what to fix first. Paste your SKILL.md, title, description, examples, price and ZIP file list, and get known rejection causes, mismatches between the listing and the package, and what could not be checked. Each finding names its source and a concrete fix. It reduces avoidable rejection causes; it does not guarantee approval.
Menu descriptions, staff scripts, allergy dialogues and signage in natural English, ready to print today. Built for izakaya, ramen, sushi and cafes. A communication toolkit, not a translator or a safety certification.
Paste a git diff and get a PR description, a changelog entry, and reviewer-risk callouts that name the file, what could break, and what to check. Only flags backed by the diff, and "no elevated-risk patterns found" when there are none. Built for AI-sized PRs.
Tell it your commands and gotchas, get a working AGENTS.md or CLAUDE.md back in the first reply. It captures fragile build steps, do-not-touch files, past mistakes and testing gotchas, marks gaps as TODOs and asks only what is missing. Ready for Claude Code, Cursor, Copilot and Codex.
Paste a job post, get the hook, the full proposal, your price, a 48-hour follow-up and a scope-creep clause. Adapted to how proposals are read on each platform, not a generic template. Works for Upwork, Fiverr and cold outreach.
Flags era-year, ordering, format and keigo problems in your rirekisho draft, each with a reason and a short suggested fix for that spot. Works on a rirekisho or shokumu-keirekisho you already have, from any source. Plain language, and it never rewrites the document from scratch.
Finds cultural mistakes, stereotypes, romaji and seasonal errors in Japan-themed English copy, with a fix for each. Works on social posts, blogs, product and marketing copy before you publish. Advisory, not a certification.
Create Japan-inspired image prompts, cultural notes, travel-friendly captions, and keywords for global creators, travelers, bloggers, and educators.