ワンクリックで
next-role
next-role には tam159 から収集した 14 個の skills があり、リポジトリ単位の職業カバレッジとサイト内 skill 詳細ページを表示します。
このリポジトリの skills
Rewrite a candidate's resume tailored to one specific JD using a hiring-recon report, emit it as a rendercv YAML, then render to PDF. Reorders jobs/bullets and adjusts language to incorporate JD keywords without inventing experience. Outputs one YAML (source of truth, user-editable) plus a .pdf published alongside it.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Stage current changes and create a Conventional Commits-style commit matching this repo's history. Use when the user says "commit", "commit this", or asks for a commit message. Pre-commit hooks will run automatically.
Fetch current documentation before answering library, framework, SDK, API, CLI, cloud-service, version-migration, setup, or configuration questions. Use when the user asks about external technical docs, package APIs, framework behavior, or dependency upgrades; do not use for pure repo refactors, business-logic debugging, or general programming concepts.
Run this repository's quality and validation workflow. Use when the user asks for quality checks, pre-commit, linting, formatting, type checking, test validation, or before reporting code changes as done.
Upgrade Python backend dependencies to their latest compatible versions. Resolves the lockfile with `uv lock --upgrade`, syncs the venv, bumps the matching `>=` pins in `backend/pyproject.toml` and `ruff-pre-commit` rev in `.pre-commit-config.yaml`, runs the backend unit tests, rebuilds the backend Docker image if requested, opens a PR with the change (watching CI for upgrade fallout), and reports what moved vs. what stayed pinned by transitive constraints. Use when the user says "upgrade backend libs", "bump backend deps", "update Python dependencies", or after they've manually run `uv lock --upgrade` and want the pyproject/config files reconciled.
Upgrade the Next.js frontend's pnpm dependencies to their latest versions in verified waves. Inventories with `pnpm outdated`, removes verified-unused deps, batches safe minor/patch bumps, handles the @langchain/react + langgraph-sdk lockstep pair, takes majors one commit at a time with registry peer-dep checks, gates every wave on type-check + lint + unit tests + build + an agent-browser check against baseline screenshots, then dedupes, audits for duplicate versions, and opens a PR. Use when the user says "upgrade frontend libs", "bump frontend deps", "update npm/pnpm packages", or `pnpm outdated` shows a backlog. Backend deps are a separate flow (`upgrade-backend-deps`).
Generate a concise PRD for the feature built in the current session and save it to docs/prd/. Use this skill whenever the user says "write a PRD", "generate a PRD", "/write-prd", asks to document the feature just shipped, or otherwise requests a product/feature spec for work done in this session — even if they don't name the docs/prd/ folder.
Apply this skill in Stage 5 to produce the day-of one-pager(s) the candidate carries into the interview. Reads the tailored resume + interview-coach prep + research report and emits a tight, scannable battlecard as a JSON source-of-truth plus a rendered PDF.
Upgrade the Next.js frontend's pnpm dependencies to their latest versions in verified waves. Inventories with `pnpm outdated`, removes verified-unused deps, batches safe minor/patch bumps, handles the @langchain/react + langgraph-sdk lockstep pair, takes majors one commit at a time with registry peer-dep checks, gates every wave on type-check + lint + unit tests + build + an agent-browser check against baseline screenshots, then dedupes, audits for duplicate versions, and opens a PR. Use when the user says "upgrade frontend libs", "bump frontend deps", "update npm/pnpm packages", or `pnpm outdated` shows a backlog. Backend deps are a separate flow (`upgrade-backend-deps`).
Pre-interview reconnaissance. Given a processed resume, JD, and optional intake, gather public intel on the company (size, financials, reputation, hiring signals) and the role (market context, salary range bracketed by location), then produce a match analysis as a single markdown report.
Produce a structured interview prep doc with a reusable self-introduction (60s + 30s) and per-round STAR stories, grounded in the resume, JD, intake (for round info and timeline), and hiring-recon report. Output is one markdown file.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Run the full quality gate across backend and frontend (pre-commit run --all-files). Use before opening a PR, after a large refactor, or when you want to confirm the whole repo is clean.