Claude Skills by atman-33

応答口調のキャラクターを切り替える。キャラクター一覧の表示、切替、レベル変更、解除。 「ペルソナ」「キャラクター変更」「口調を変えて」「/persona」で起動。

Configure and use Cloudflare Static Assets with React Router, ensuring compatibility across development and production environments with automatic fallback handling. Use when deploying React Router applications to Cloudflare Workers that need to access files from the public directory.

Guide for implementing sortable and droppable components using dnd-kit library. Use this skill when building React applications that require drag-and-drop functionality with both container reordering (useSortable) and item dropping (useDroppable) capabilities, such as Kanban boards, file management systems, or playlist editors.

Investigates OpenCode runtime errors by locating and analyzing log files. Use when OpenCode fails to start, plugins do not load, MCP servers error out, or terminal shows cryptic errors without details.

Implements React Router v7 app structure, routing patterns, and component templates. Use when creating or modifying React Router v7 applications to ensure consistent folder structure, data loading patterns, and component architecture.

Decompose a strategy handed down from above into a hierarchy of aspects and states, audit it for necessity, sufficiency and overlap, and output it as an xlsx. Use before writing your own team's or unit's policy from a company/department/team strategy, when the user wants to break a strategy down into "what state we need to reach", or asks to check whether a decomposition is MECE.

Prime a session with a team project's current state - backlog, sprint, repo progress - and refresh its _index.md summary. Use when the user asks "where are we" on a team project, or at the start of a work session on one.

Add, refine, split, or reorder PBIs in the file-based product backlog in the team-shared folder. Use when the user wants to create backlog items, write user stories or acceptance criteria, estimate points, split oversized items, or tidy the product backlog.

Plan a sprint - set the goal, commit backlog items into scope, and write the burndown baseline (scope.json). Use at a sprint boundary when the user wants to plan the next sprint or commit items to a sprint.

Generate the daily progress report - PBI status board, burndown chart, and merges of the day - as a self-contained HTML file in the team-shared folder. Use in the daily routine, or when the user asks for today's progress report or a burndown chart.

Write the sprint review - scope vs done, demo pointers, and carry-over decisions. Use at sprint end when the user wants a sprint review, sprint summary, or to close out a sprint.

Set up team-ops for this machine/project - create .claude/team-context.json, scaffold the team-shared ai/ folder skeleton, and optionally register a project. Use when onboarding a machine to a team shared folder, when the team-context hook reports a config error, or when adding a new team project.

Start work on a PBI - set it to doing and issue the convention-compliant work branch name (pbi/<id>-<slug>). Use when a developer picks up a backlog item, or asks which branch name to use for a PBI.

Rebuild or repair the team knowledge base indexes (_index.md files) in the team-shared folder. Use after several notes were added or moved, when indexes look stale, or when team-kb-save reports a larger reshuffle is needed.

Answer questions from the team-shared knowledge base. Use when the user asks about team rules, working agreements, domain knowledge, past decisions, or anything a teammate might have documented in the shared folder.

Save reusable team knowledge into the team-shared knowledge base. Use when this session surfaces a process gotcha, decision rationale, domain know-how, or team rule worth sharing with teammates, or when the user asks to save something to the team KB.

Generate an onboarding briefing for a new team member from the team KB, project specs, and recent progress. Use when someone new joins the team or a project, or when the user asks for an onboarding guide / "explain this team to a newcomer".

Update the project's living spec (docs/spec/spec.md) from PBI acceptance criteria and diffs newly merged into the dev-main branches. Use in the daily routine after repo sync, or when the user asks to bring the spec up to date with what is implemented.

Facilitate and record a sprint retrospective (KPT) with follow-up on the previous retro's action items. Use at sprint end when the user wants a retrospective, KPT, or team improvement discussion.

Update the workhub vault knowledge base indexes (projects/knowledge/archive _index.md files). Smart mode detects changes and updates only what's needed. Full rebuild available with --full flag. Use after adding/moving documents or when indexes feel stale.

Ingest documents from the workhub vault inbox into the knowledge base. Classifies notes into projects/knowledge/archive, proposes tasks for actionable items, links, and indexes. Use when new notes land in inbox/ or a path needs filing.

Health check for the workhub vault knowledge base. Detects orphan documents, broken links, index drift, tag issues, and stale content across projects/knowledge/archive. Run periodically or as part of weekly review.

Query the workhub vault knowledge base to find information, synthesize answers from multiple notes, and optionally save insights. Use when asking questions about vault content or needing cross-document analysis.

Search the workhub long-term memory database for past conversations - by keyword over any time range, or list the most recent sessions. Use when the user asks what was discussed or decided before, says "recall", "思い出して", or wants to check past session context beyond what was auto-injected.

Set up the workhub long-term memory engine on this machine - install its dependencies, download the local embedding model, initialize the vault memory database, and verify the result. Use when the workhub app prompts for memory setup, when memory hooks report they are skipped, or when the user asks to enable/repair long-term memory.

Edit a workhub mindmap note (projects/<slug>/mindmaps/*.md) from a natural-language instruction — add, rename, move, group, colour or link the nodes in `## Nodes`, and annotate them with sticky notes in `## Stickies`. Use when asked to restructure a mindmap, group ideas under a new branch, prune a subtree, pin a note to a node, or when the workhub app launches a mindmap edit.

Load a vault project's context - read its README first, follow the reading order only as far as the request needs, resolve its repositories, and summarize goal, status, where the source lives and what is in flight. Use when the user says to work on a project by slug or name, or asks what a project is about.

Cut a workhub release — bump the app version, write the changelog entry, commit to main, tag `vX.Y.Z`, push, and verify the GitHub Release published with every required asset. Use when the user wants to release or ship the workhub app, tag a version, or publish a build.

Edit a workhub schedule note (projects/<slug>/schedules/*.md) from a natural-language instruction — move or resize the bars, arrows, milestones and notes in `## Items`, and adjust `## Non-working` days. Use when asked to shift a phase, rebalance a plan, add or remove non-working days, or when the workhub app launches a schedule edit.

Think a decision out loud with a counsel that reads the owner's north star, present state and bottlenecks, argues back, and writes the conclusions into the vault. Use for a daily/weekly/monthly review, or when the user wants to stress-test a direction, priority or trade-off against what they said they were trying to do.

List and filter tasks from the workhub vault task board. Use when the user asks what tasks exist, what is assigned to the AI, what is in progress, or wants to pick a task to work on.

Record the results of a workhub task - store the raw report in the vault AI zone, polished notes in the human zone, update the task's result section, and set status to review. Use when finishing work started via task-start, or when the user asks to report/close out a task.

Start working on a workhub task - mark it doing, load its description as working context, and resolve the target repository. Use when the user says to start/work on a task by id or title, or after picking one via task-list.

Initialize a new workhub Obsidian vault from the bundled template. Use when setting up workhub for the first time or creating a fresh vault at a given path.

Migrate another Obsidian vault into the workhub vault (copy-only, verified).

Set up a machine to work with a workhub vault - check/install required software (git, Node.js, Claude Code, OpenCode), initialize the vault if needed, wire up Claude plugins, and run the OpenCode sync scripts. Use when onboarding a new machine, after a fresh vault-init, or when the harness feels half-configured.

Zennの技術ブログ記事を執筆・編集・レビューするためのガイドラインを提供する。技術的正確性、読みやすさ、AIっぽい文章の排除を重視。Zennの記事（articles/*.md）を書く・直す・レビューするとき、または「Zenn」「技術ブログ」「記事執筆」に言及されたときに使用する。

This skill should be used when the user asks about "Zenn記法", "Zenn Markdown", "メッセージブロック", "アコーディオン", "埋め込み", "Zenn特有の記法", or mentions writing Zenn articles with specific formatting needs. Provides comprehensive knowledge of Zenn-specific Markdown syntax and best practices.