← all publishers

hironow

@hironow source repo

Report this profile Claim this profile

• 44 skills
• 0 followers
• 16 hours ago last updated

1. ▌
   Brand Legal Review · hironow

   This skill should be used when the user asks to "legal review", "policy review", "review AI policy", "法務レビュー", "ポリシーチェック", or needs brand-conscious legal review for company communications that prioritize community trust over legal safety.
   0 installs
2. ▌
   Design An Interface · hironow bundle

   Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
   0 installs
3. ▌
   Gh Address Comments · hironow bundle

   Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
   0 installs
4. ▌
   Ubiquitous Language · hironow bundle

   Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
   0 installs
5. ▌
   Add Guard Protection · hironow bundle

   Protect code paths that have no incoming HTTP request — AI agent tool calls, agent loops, MCP tool handlers, background jobs, queue workers — with Arcjet Guard (`@arcjet/guard` for JS/TS, `arcjet.guard` for Python), covering rate limiting, prompt injection detection, sensitive information blocking, and custom rules. Use when the user says "rate limit my tool calls", "block prompt injection in my agent", "add security to my MCP server", or "protect my queue worker", even without mentioning Arcjet or Guard. Not for HTTP routes, endpoints, forms, or webhooks — that is add-request-protection. Uses the Arcjet CLI (`bunx @arcjet/cli` or `brew install arcjet`) for authentication and site/key setup.
   0 installs
6. ▌
   Writing Great Skills · hironow bundle

   Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
   0 installs
7. ▌
   GCP Serverless Appdev · hironow bundle

   GCP serverless application development guide covering Cloud Run, Firestore, Cloud Tasks, Pub/Sub, Firebase Auth, Cloud Functions, Eventarc, and Cloud Scheduler: service selection, implementation patterns, and gcloud-based deployment. Use when the user is designing or writing the application side — mentions "GCPで開発", "Cloud Runで", "Firestoreに", "新しいGCPプロジェクト", scaffolding a GCP app, choosing between Cloud Tasks and Pub/Sub, Firestore data modeling, Firebase Auth integration, deploying a service with gcloud, or comparing GCP services with AWS/Azure equivalents, including cross-cloud migration discussions. Not for Terraform/OpenTofu — any .tf, `tofu`, "tfファイル", or "インフラをコード化" request is gcp-serverless-tf.
   0 installs
8. ▌
   Japanese Tech Writing · hironow bundle

   日本語の技術文書・書籍原稿の文章規範。整形（一文一行、引用ブロック、脚注、コラム記法）、段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。英語の記事の編集は edit-article。
   0 installs
9. ▌
   Request Refactor Plan · hironow bundle

   Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.
   0 installs
10. ▌
    Security Threat Model · hironow bundle

    Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.
    0 installs
11. ▌
    Add Request Protection · hironow bundle

    Protect a server-side HTTP route or endpoint — API route, form handler, auth endpoint, webhook — with Arcjet, covering rate limiting, bot detection, email validation, and abuse prevention. Works across Next.js, Express, Fastify, SvelteKit, Remix, Bun, Deno, NestJS, and Python (Django/Flask). Use when the user says "add rate limiting", "block bots", "prevent brute force", or "secure my endpoint", even without mentioning Arcjet. Not for code with no HTTP request (tool calls, MCP handlers, agent loops, workers) — that is add-guard-protection. Uses the Arcjet CLI (`bunx @arcjet/cli` or `brew install arcjet`) for authentication, site/key setup, remote rule management, and traffic verification.
    0 installs
12. ▌
    Security Ownership Map · hironow bundle

    Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions.
    0 installs
13. ▌
    Security Best Practices · hironow bundle

    Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.
    0 installs
14. ▌
    Verification Discipline · hironow

    How to not fool yourself (or be fooled) when verifying work — yours, a reviewer's, a subagent's, or a checker's. Use whenever accepting review findings, grading/judging another agent's output, verifying checksums or pinned versions, interpreting a failing (or suspiciously passing) test or gate, or writing any report that claims something is "done", "green", or "verified". Especially load-bearing when the author and the verifier are the same context — the situation this skill exists to break.
    0 installs
15. ▌
    Decision Record Governance · hironow bundle

    Create, update, and supersede (or reverse) decision records — ADRs for technical decisions and PDRs for product decisions — governed by decision-queue.md (the list of decisions awaiting approval) and a quality rubric. Always checks every other DR for contradiction, duplication, misreading, false relation, and mistaken relationship, and when anything is found, requires a Slack consultation that involves the people behind the conflicting record so a human rules on it. Use when the user mentions ADR, PDR, decision record, decision queue, 決定記録, 意思決定の起票・更新・supersede・反転, DR の矛盾・整合性チェック, 決裁の相談・催促, or wants to manage architecture or product decisions.
    0 installs
16. ▌
    Intent Handover Governance · hironow bundle

    Govern development continuity with two files — docs/intent.md (why we are doing this now, the human's intent) and docs/handover.md (how far we got and what comes next). The intent is settled by a human and never guessed by the AI; the handover is updated at the end of every session and kept readable in two minutes. Before any update, check intent ⇄ handover ⇄ the repository's actual state for drift, and leave the ruling on any gap to a human. Use when the user mentions intent.md, handover.md, 引き継ぎ（ハンドオーバー）, 意図の記録・確認, セッション終了・作業再開, starting or switching a work unit, or wants session continuity captured in docs.
    0 installs
17. ▌
    Update Submodule Changelog · hironow

    Update docs/changelogs.md after submodules under protocols/*, payments/*, or gcloud/* change. Applies automatically on keywords such as "サブモジュール更新", "changelog更新", "プロトコル変更まとめ", after git submodule update, or whenever dependency changes need to be documented.
    0 installs
18. ▌
    QA · hironow bundle

    Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
    0 installs
19. ▌
    Yeet · hironow bundle

    Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
    0 installs
20. ▌
    Review · hironow bundle

    Review the changes since a fixed point (commit, branch, tag, or merge-base) on two separate axes, Standards and Spec, using parallel sub-agents. Use when the user wants to review a branch, a PR, or work-in-progress changes, or asks to "review since X".
    0 installs
21. ▌
    To Prd · hironow bundle

    Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
    0 installs
22. ▌
    Caveman · hironow bundle

    Ultra-compressed communication mode: drops filler, articles, and pleasantries while keeping full technical accuracy. Use when the user asks for caveman mode ("caveman mode", "talk like caveman", /caveman).
    0 installs
23. ▌
    Dogfood · hironow bundle

    Exploratory testing of a running web application through a real browser (agent-browser): systematically drive the UI, find functional/UX/console issues, and produce a report with screenshot-and-video repro evidence per issue. Use for "dogfood", "bug hunt", or "exploratory test this site/app"; for filing issues the user reports conversationally, use the qa skill.
    0 installs
24. ▌
    Diagnose · hironow bundle

    Disciplined diagnosis loop for hard bugs and performance regressions - build a feedback loop, reproduce and minimise, hypothesise, instrument, fix with a regression test. Use when the user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
    0 installs
25. ▌
    Imagegen · hironow bundle

    Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.
    0 installs
26. ▌
    Zoom Out · hironow bundle

    Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
    0 installs
27. ▌
    Gh Fix CI · hironow bundle

    Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. If the organisation ships a skill describing its shared CI hub and self-hosted runner conventions (for example a consume-hub-actions skill), read it first, then run this workflow. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
    0 installs
28. ▌
    Hatch Pet · hironow bundle

    Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly. Requires the Codex runtime (built-in $imagegen system skill and the Codex app pet contract); do not use from other agents.
    0 installs
29. ▌
    To Issues · hironow bundle

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
    0 installs
30. ▌
    Screenshot · hironow bundle

    Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
    0 installs
31. ▌
    Openai Docs · hironow bundle

    Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
    0 installs
32. ▌
    Edit Article · hironow bundle

    Edit and improve an article draft by restructuring sections, improving clarity, and tightening prose. Use when the user wants to edit, revise, or improve an article draft; Japanese technical prose is japanese-tech-writing instead.
    0 installs
33. ▌
    Manager Loop · hironow bundle

    Run very long-horizon, multi-hour autonomous builds in Claude Code by splitting roles - a manager session that interviews the user, writes a phased checklist and steers, and a separate implementer agent that finishes one phase at a time "extremely well" while ticking a progress dashboard. Use whenever the user asks for an ambitious end-to-end build, a large migration or rewrite, a "build the whole thing" request, or anything a human team would need days for; also when the user says "manager loop", "run this to completion", "keep going until it's done", "long-running", "autonomous build", or complains that a long agent run stalled in minutiae, plateaued, or asymptoted. Not for ordinary single-task coding.
    0 installs
34. ▌
    Fallacy Check · hironow bundle

    議論・主張・討論ログのテキストから、誤謬パターン（ストローマン、人身攻撃、レッテル貼り、 loaded language、衆人・権威・新しさへの訴え、誤った二分法、連続性の虚偽、前件否定、 後件肯定など）を検出してフラグする。出典はニコニコ大百科「詭弁の特徴のガイドライン」と Wikipedia「詭弁」（references/rules.yaml）。「指摘して」「チェックして」「レビューして」のように 検出と報告だけを求められたときに使う（詭弁の指摘、論理の飛躍や主張の穴の点検、 説得文・ポリシー論・議論スレッドの論理面レビュー）。原稿そのものを直す・書き直す・ 並べ替える依頼は argument-gap-edit。 Use when reviewing an argument, essay, policy statement, or debate log for logical fallacies without editing the text itself.
    0 installs
35. ▌
    Obsidian Vault · hironow bundle

    Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
    0 installs
36. ▌
    Playwright CLI · hironow bundle

    Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
    0 installs
37. ▌
    Agents Md Triage · hironow

    Audit AGENTS.md / CLAUDE.md / GEMINI.md and their spoke files (docs/agents/* etc.), classify every line as discoverable / task-specific / always, and produce a staged plan to shrink the hub and extract skills. Use whenever the user wants agent instruction files audited, slimmed, reorganized, or skill-ified, or asks about context/token reduction or an instruction budget for those files — whether or not they say "audit".
    0 installs
38. ▌
    Decision Mapping · hironow bundle

    Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
    0 installs
39. ▌
    Develop Web Game · hironow bundle

    Use when building or iterating on a web game (HTML/JS) and a reliable development + testing loop is needed: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.
    0 installs
40. ▌
    Jupyter Notebook · hironow bundle

    Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
    0 installs
41. ▌
    Argument Gap Edit · hironow bundle

    書籍原稿で、無理筋な議論、段落間に埋めがたいギャップ、理論や引用の見せびらかし、段落単位の割り込みを検出し、論理単位ごとに再配置・削除・橋渡しする編集を行う。「直して」「書き直して」「並べ替えて」のように原稿そのものを編集する依頼、ある箇所で得た編集方針を別箇所へ適用するとき、議論の筋を点検して直すときに使用する。誤謬を指摘するだけで本文を変えない依頼は fallacy-check。
    0 installs
42. ▌
    Cloudflare Deploy · hironow bundle

    Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.
    0 installs
43. ▌
    GCP Serverless Tf · hironow bundle

    Generate and maintain Terraform/OpenTofu configurations for GCP serverless architectures (Cloud Run, Firestore, Cloud Tasks, Pub/Sub, Cloud Functions, Eventarc, Cloud Scheduler, Artifact Registry, Secret Manager). Use whenever the request involves Terraform, OpenTofu, .tf files, `tofu` or `terraform` commands, or infrastructure as code for those services — initial .tf generation, updating .tf after application code changes, and the Terraform-vs-OpenTofu choice — including Japanese requests such as "tfファイル作って" or "インフラをコード化". Not for application code, service selection, or gcloud-based deployment — that is gcp-serverless-appdev.
    0 installs
44. ▌
    Xcodebuildmcp CLI · hironow bundle

    Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
    0 installs