krkrkrr
- 21 skills
- 0 followers
- 9 hours ago last updated
- ▌ Dotenvx · krkrkrr bundleUse when working with the `dotenvx` env-var management tool — encrypting .env files, juggling multiple environments (.env.production / .env.staging / .env.ci), committing encrypted secrets to git with `.env.vault` / `.env.keys` / `.env.encrypted`, or wiring dotenvx into GitHub Actions. Trigger on `.env.vault` / `.env.keys` / `dotenvx` commands or symptoms (env-var leak risk, env per-stage management, encrypted secrets workflow) even if the user does not say "dotenvx" by name.
- ▌ Otel Node · krkrkrr bundleNode.js OpenTelemetry setup — SDK init, auto-instrumentation packages, and the esbuild ESM silent-failure gotcha (instrumentation-* packages produce no spans when bundled with esbuild --format=esm). Use when adding OTel to a Node.js/Hono/Express service or debugging missing spans after bundling. See devops/opentelemetry for signal design decisions.
- ▌ Skill Finder · krkrkrr bundleUse ONLY when the user explicitly asks to discover or evaluate a skill from OUTSIDE the curated catalog — e.g., "find a Stripe skill", "is there a skill for X?", "evaluate this candidate before adopting". Meta-skill, complementary to skill-selector: do NOT auto-invoke on routine apm-management, project-init, or catalog-resident requests. Cross-source survey across vetted registries (Anthropic official, claude-skill-registry, VoltAgent/awesome-agent-skills, ComposioHQ, Superpowers, GitHub topic) with a mandatory waxa-eval adoption gate.
- ▌ SQL Security · krkrkrr bundleSQL injection screening for host code (MoonBit / TS / Rust) plus secretlint setup notes. Flags single-line template-literal or string-concat SQL builders, regardless of value source — the scanner is line-based and does NOT trace data flow, so a clean scan is not proof of safety (multi-line template literals are missed) and every hit needs a manual review or an explicit `// sql-security: ok` opt-out.
- ▌ Dep Lib Review · krkrkrr bundlePeriodic dependency review for Node.js/pnpm projects — outdated package triage, security audit, update batching strategy (patch/minor/major), validation checklist. Run monthly or before major releases. Use when asked to review or update dependencies in a repo.
- ▌ Skill Selector · krkrkrr bundleMeta-skill for picking project skills via APM. Invoke ONLY when the user explicitly asks to set up apm.yml, choose which skills a project needs, or evaluate a catalog match — do NOT auto-invoke on routine project-init or apm-management tasks. Two-phase: pick from a curated catalog first; only escalate to broader search/evaluation when the catalog has no fit. Avoids the failure mode of impulse-installing skills you never use or hand-searching GitHub when a vetted answer already exists.
- ▌ Extract Glossary · krkrkrr bundle指定されたリポジトリ、複数リポジトリ、または GitHub organization から、ドメイン固有の専門用語、業界用語、社内・プロダクト用語、リポジトリ実装マップ、技術構成、オンボーディング向け Mermaid 構成図を抽出・生成するときに使う。ユーザーが「用語集を作る」「ドメイン辞書を作る」「オンボーディング資料にする」「repo/org を見て専門用語をまとめる」「AI が再確認しなくてよい知識ベースを作る」と依頼したら起動する。
- ▌ Tech Trend Watch · krkrkrr bundleLong-term technology stack review using State of JS, State of CSS, and Thoughtworks Technology Radar — satisfaction×usage matrix, ADOPT/TRIAL/ASSESS/HOLD mapping, P0–P3 migration priority. Use for annual stack audits, planning major migrations (jest→vitest, webpack→Vite, etc.), or on-demand replacement decisions. Not for general architecture design.
- ▌ Retrospective Codify · krkrkrr bundlePair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, a skill, or a CLAUDE.md rule. Meta-skill: invoke ONLY when the user explicitly says "codify today's lessons," "make it a skill," "drop it into lint," or asks to extract a reusable rule from a trial-and-error fix. Do NOT auto-invoke at every task completion. Spares future-you (or another agent) the same trap.
- ▌ Upstream Fix And Pin · krkrkrr bundle自分の依存ライブラリにバグや欠けている機能があり、上流に PR を出して取り込まれるまで下流プロジェクトを動かしたいときの運用。git ref pin(branch HEAD SHA → merge SHA)、`link:` への退避判断、SHA 取り扱い、pnpm v10 の build script gating まで含む。
- ▌ Conventional Changelog · krkrkrr bundleReference for Conventional Commits and automatic CHANGELOG generation. Compares release-please / changesets / git-cliff / towncrier and covers commit format, Keep a Changelog, and semver tag practices. Use when setting up or unifying a release flow.
- ▌ Optimizing Descriptions · krkrkrr bundleMeta-skill for auditing and rewriting SKILL.md `description` fields per the agentskills.io optimizing-descriptions framework, layered with mizchi's two-track trigger policy (Meta = explicit-invoke-only, Project = pushy auto-trigger). Invoke ONLY when the user explicitly asks to "optimize a skill description," "audit descriptions," or "rewrite descriptions per agentskills." Do NOT auto-invoke after every SKILL.md edit; description tuning is a deliberate batch, not a per-edit reflex.
- ▌ Utels Project Bootstrap · krkrkrr bundleOne-shot helper for registering a utels.dev project and writing the returned ingest token straight into a wrangler secret. Use when wiring server-side error tracking for a Cloudflare Worker without leaking tokens through the shell.
- ▌ Tech Article Reproducibility · krkrkrr bundleEvaluate the reproducibility of technical articles. Dispatch a subagent to simulate a first-time reader reproducing the work locally and list missing information. Use as the final check on a draft before publication.
- ▌ Playwright CLI · krkrkrr bundleAutomate browser interactions, test web pages and work with Playwright tests.
- ▌ Playwright Test · krkrkrr bundleBest practices and reference for Playwright Test (E2E). Covers how to write tests, avoiding fixed waits, network triggers, DnD, shard/retry setup on GitHub Actions, and more. Use when writing, reviewing, or configuring CI for Playwright tests.
- ▌ Ddd Bdd Tdd Flow · krkrkrr bundleUse when creating a new application or feature from scratch following a structured flow. Executes five mandatory phases in order: (1) structured requirements interview, (2) DDD SUDO modeling with Mermaid diagrams + user review, (3) comprehensive BDD Gherkin feature writing + user review, (4) property derivation and property-based integration/e2e test generation, (5) TDD implementation following t_wada's Red-Green-Refactor cycle. Outputs land in doc/ (models + features), test/ (all tests), src/ (implementation). When NOT to use: small incremental changes to an already-modeled feature; refactors with no behavioral change; hotfixes.
- ▌ Argument Gap Edit · krkrkrr 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。第5章後半のように「前半で得た編集方針を別箇所へ適用する」「議論の筋を点検して直す」ときに使用する。
- ▌ Readme Guidelines · krkrkrr bundleTemplates and policies for README.md files. Use when creating a new README.md, updating an existing one after code changes, or creating/syncing the Japanese version README-ja.md. Covers template selection by project type, section-level writing rules, and which sections to update for which kind of change.
- ▌ Japanese Tech Writing · krkrkrr 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。
- ▌ External API Tos Check · krkrkrr bundleUse before writing or modifying code that integrates, embeds, or calls any third-party API/SDK/service (video/stream embeds like YouTube or Twitch, payment providers, LLM APIs, maps, ads SDKs, auth providers, etc.). Trigger whenever a task adds a new external provider, changes embed/autoplay/player behavior, upgrades an SDK across a major version, or touches code under a provider-named directory (e.g. src/youtube/, src/twitch/) — even if the user does not say "terms of service" or "ToS". Confirms the provider's official Terms of Service / Developer Policy / Developer Agreement allows the planned behavior before implementation, and records material constraints as an ADR.