debugging_log

Auto-gather git changes, confirm scope with the user, and draft a commit title and message following the project commit style guide.

Extract UX copy and layer names from a Figma frame, page, or component using the Figma MCP server and emit a Markdown table compatible with the project's UX copy workflow. Use when a user provides a Figma URL and asks to pull text into a copy table for review, key naming, or localization.

Lint repository file and folder names for format compliance. Use when users ask to check naming conventions, enforce file extensions, or validate notes naming patterns; applies a fixed set of rules from the skill and reports any discovered repository style guides for reviewer reference.

Polish one or more Markdown files so the repo core writing rules are enforced - straight quotes (not curly), no contractions, the Oxford comma, sentence case headings, plain hyphens (never en-dash or em-dash), consistent capitalization and punctuation, simple non-idiomatic wording, and no sentence split across a line break. After applying these fixes, also runs the link-polisher skill on the same files to format raw URLs. Use when a user asks to polish, clean up, style-check, or enforce writing rules on a Markdown file, or before committing prose changes to docs.

Interact with GitHub repositories using the GitHub CLI (gh). Covers pull requests, issues, releases, workflow runs, and branch operations. Supports beginner and intermediate tracks, write-operation confirmation, and an --auto flag to skip prompts.

Fetch all comments on a GitHub pull request (reviews, inline review comments, and general issue comments) and emit a single consolidated Markdown report. Use when a user wants to read, summarize, audit, or triage every comment on a PR in one place. Accepts a PR number, a `owner/repo#n` reference, or a github.com pull-request URL.

Bring the current git branch up to date with commits from the main branch. Use when the user asks to pull latest main, sync/refresh the branch, rebase onto main, or merge main into a feature branch.

Rewrite raw, unformatted URLs in Markdown files as Markdown links with a sensible human-readable label fetched from the source (Figma file name, GitHub issue or pull request title, etc.). A raw URL is any link that is not already wrapped in Markdown link syntax `[text](url)` with a meaningful label - this includes bare URLs, angle-bracketed autolinks (`<https://...>`), and links whose visible text is the URL itself or a generic placeholder like `Figma` or `github.com`. Use when a user adds or pastes a raw URL, asks to polish or format links, or when you notice an existing bare link in a Markdown file you are editing or reviewing. Currently supported link types: Figma (`figma.com`), and GitHub issues and pull requests (`github.com/<owner>/<repo>/issues/<n>` or `/pull/<n>`). Other URLs are kept as-is unless the user explicitly asks to polish them.

Audit the repository for missing or outdated folder `README.md` files. Use after adding new folders, moving files between folders, renaming files, or whenever folder contents change in a way that may make existing READMEs inaccurate.

Audit and enforce the AGENTS.md "Scripts" guidelines for helper scripts in this repo - banning Python, preferring Node.js `.mjs` modules or zsh, requiring `--help` output, a top-of-file notes section (general notes, usage, output), and status emojis. Use when adding or reviewing a helper script, or to sweep the repo for scripts that do not follow the guidelines.

Fully sync `Skill(<name>)` entries in `.claude/settings.json` under `permissions.allow` with the skills in the repo's `skills/` folder, adding entries for new skills and removing entries for skills that no longer exist.

Fully sync `Skill(<name>)` entries in `.claude/settings.json` under `permissions.allow` with the skills in the repo's `skills/` folder, adding entries for new skills and removing entries for skills that no longer exist.

Review and polish the English UX copy in Markdown tables (especially columns like English or EN) by directly updating the English cells for clarity, consistency, grammar, vocabulary simplicity, active voice, and US English style, and add TODO comments when user review is required. Use when a user asks to improve, polish, or standardize English UI text, error messages, labels, helper text, or table-based localization copy.

Review Japanese UX copy in Markdown tables (especially columns like Japanese, Key, Description, English, Notes) for clarity, consistency, grammar, natural phrasing, punctuation, and terminology compliance. Use when a user asks to QA or improve Japanese UI text, error messages, labels, helper text, or table-based localization copy.

Push and pull Phrase Strings translation keys using the repo scripts in `scripts/`. Parses natural-language intent (pull/push, project, branch, flags) into a concrete command, shows the planned invocation, confirms with the user, and runs it. Use when the user asks to push, pull, sync, upload, or download Phrase keys, translations, or copy for a project listed in `phrase-data/phrase-project-ids.csv`.

Localize Japanese UX copy in `phrase-data/<project>-ja-copy.csv` from the paired English CSV for a user-specified Phrase project and workflow (auto-detect missing JA or user-specified keys). Use when a user asks to add or update Japanese localization values in Phrase CSV files with project validation, key validation, review against `skills/ux-copy-ja-review/SKILL.md`, safe row-level edits, and a precise change report.

Review English UX copy files (typically Markdown docs with localization tables) and audit `Key` values against `kws-writing-style-guide/key-naming-rules.md`. Use when a user asks to check key naming compliance, find invalid keys, suggest corrected keys, or QA table-based copy before Phrase import.

Find existing Phrase keys for UX copy in a highlighted Markdown table by searching the phrase-data CSV files for an exact match. For each row, fill the Key column with the matching key_name, fill the Description column with the matching comment, and set Notes to Reused. Use when a user highlights a table of English or Japanese UX copy and asks to look up, reuse, or back-fill existing keys.

Push new or updated English UX copy authored in a `tasks/` Markdown file into the matching `phrase-data/` English copy and tag CSV files, then hand the user the `pnpm` push command to apply those changes. Reads the project, branch, and tag from the task document, validates the project against `phrase-data/phrase-project-ids.csv`, updates the local CSVs itself, marks pushed rows `Added`, and updates the task Changelog. Use when a user asks to push, add, or sync pending `TODO:` UX copy from a task file into Phrase data.

Creates and maintains Figma Code Connect template files that map Figma components to code snippets. Use when the user mentions Code Connect, Figma component mapping, design-to-code translation, or asks to create/update .figma.ts or .figma.js files.

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `create_new_file` tool call. NEVER call `create_new_file` directly without loading this skill first. Trigger whenever the user wants a new blank Figma file — a new design, FigJam, or Slides file — or when you need a fresh file before calling `use_figma`. Usage — /figma-create-new-file [editorType] [fileName] (e.g. /figma-create-new-file figjam My Whiteboard, /figma-create-new-file slides Q3 Review)

Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the Figma screen to match code', 'convert this modal/dialog/drawer/panel to Figma'. This is the preferred workflow skill whenever the user wants to build or update a full page, modal, dialog, drawer, sidebar, panel, or any composed multi-section view in Figma from code or a description. Discovers design system components, variables, and styles from Code Connect files, existing screens, and library search, then imports them and assembles views incrementally section-by-section using design system tokens instead of hardcoded values.

MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Trigger whenever the user asks to create, generate, draw, render, sketch, or build a diagram — flowchart, architecture diagram, sequence diagram, ERD or entity-relationship diagram, state diagram or state machine, gantt chart, or timeline. Also trigger when the user mentions Mermaid syntax or wants a system architecture, decision tree, dependency graph, API call flow, auth handshake, schema, or pipeline visualized in FigJam. Routes to type-specific guidance, sets universal Mermaid constraints, and tells you when to use a different diagram type or skip the tool entirely (mindmaps, pie charts, class diagrams, etc.).

Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, create individual components with proper variant sets and variable bindings, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. Also use when the user asks to create or generate any component in Figma — even a single one — since components require proper variable foundations, variant states, and design token bindings to be production-quality. This skill teaches WHAT to build and in WHAT ORDER — it complements the `figma-use` skill which teaches HOW to call the Plugin API. Both skills should be loaded together.

This skill helps agents use Figma's use_figma MCP tool in the FigJam context. Can be used alongside figma-use which has foundational context for using the use_figma tool.

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context — e.g. create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically.

This skill helps agents use Figma's use_figma MCP tool in the Slides context. Can be used alongside figma-use which has foundational context for using the use_figma tool.