スキルを探す

Keeps brand definitions, several side by side, and turns one into a Claude Design System, DESIGN.md, VOICE.md or guide. Trigger to define a brand, palette, type or voice; turn a style guide or site into tokens; make, connect or sync a design system; audit for brand drift (off-palette colours, old names); pass or fail a page against a brand, or apply one to a README or generated output; critique or check a built UI (hierarchy, spacing, states, generic look); or say brandscribe (setup, build, export, sync, audit, gate, ui). Microcopy and messages are commscribe's; React libraries design-sync's; charts dataviz's; canon lorescribe's; a pre-build brief, fit across widths and themes, and game UI uismith's; no logos.

日本語の概要は準備中です。原文の説明を表示しています。

Paces a Claude subscription's usage — how fast to spend this week, what can still run at N% weekly, whether planned work fits before a reset. Reads the 5-hour, weekly, per-model and CI-minutes meters, sets a spend mode (normal, pace, turbo, overnight, work-day, owner-away, reset-eve) and re-cuts waves that don't fit. Also when something ate usage overnight, CI minutes run low, context runs high (compact or clear?), a new model needs a measured baseline, or which skill or subagent used tokens; or say pacewright (check, mode, fit, context, uba, baseline, spend, refresh). The plan table is dispatchwright's; the handoff, handoffwright's; one artifact's cost, skillwright's slim; the meter statusline, rigwright's; a scheduled check, agentwright's.

日本語の概要は準備中です。原文の説明を表示しています。

Directs pixel art that must read at several zoom scales at once — per-scale palette and silhouette rules, terrain-versus-unit contrast, a one-scene look test, and briefs for an artist or image generator. Trigger when a game renders one world through zoom bands or levels of detail, a pixelated 3D or 2.5D band with billboards included; when a sprite, unit or icon vanishes against terrain zoomed out; for a cross-band look test or pixel-art style guide; or say pixelsmith (test, brief, audit, 3d). Works from a described scene. Drawing is an art tool's job; rendering and LOD code the game's engineering; a brand palette brandscribe's; game audio soundsmith's.

日本語の概要は準備中です。原文の説明を表示しています。

Vets third-party skills, plugins, MCP servers and GitHub Actions before install, with a verdict (PASS, CONDITIONAL, HOLD, FAIL) and install terms. Trigger on any should-I-install question, even with its files or hooks pasted in or a scan already clean; is this skill safe, vet this MCP server, check this GitHub Action, what does this installer write, a licence check before a fold-in, what changed in a plugin update; or say trustwarden (vet, revet, terms, refresh). Uses skillspector, zizmor, pinact and Scorecard when present; lists files no scanner read. Runtime permissions are gatewarden's; secrets shieldwarden's; your own skills skillwright's; sandboxing a download hypervrunner's.

日本語の概要は準備中です。原文の説明を表示しています。

Transcribes local audio and video to txt, srt, vtt and json with timestamps using whisper.cpp, and proves which backend ran. Trigger to transcribe, caption or subtitle a recording, meeting, podcast or video locally; to pick a Whisper model for this GPU or estimate a batch; when a transcript is empty, cut short or repeating; when Whisper ran on the CPU or a pasted log must prove the GPU ran; when it shares the GPU with LM Studio or ComfyUI; or say whisperrunner (audit, check, plan, run, status, refresh). Never a cloud API or a download. Voice-overs are comfyrunner's; clips and burned-in captions obsrunner's; game audio soundsmith's; summarising transcripts lmstudiorunner's.

日本語の概要は準備中です。原文の説明を表示しています。

Designs, hardens and audits the system around an agent that runs on its own — bot, scheduled task, routine, automation — all but the prompt text. Trigger for guardrails, kill switches, cadence and loop pacing (cron, wake, /loop), retries and failures, output contracts, protected resources, handoffs between agents, or isolating untrusted email and web content; to emit a spec as a Cowork task, routine, scheduled task or CI job; or say agentwright (emit, audit, refresh); it never schedules or runs one. Prompt text is promptwright's; CLAUDE.md, rigwright's; skills, skillwright's; runtime grants and credentials, gatewarden's scan; code threats, a security harness's.

日本語の概要は準備中です。原文の説明を表示しています。

Runs a session's fan-out — splits a large request into tiered, recoverable units, dispatches and reconciles them against the repo. Trigger when work needs many agents or spans many repos or files (rebuild, re-architect, sweep, migrate, 'do all of this'); when subagents would launch with no model or effort set; for the plan table (units, models, tokens, meters) before launch; to resume a unit that died or hit a usage limit; when units would share a repo; or say dispatchwright (plan, dispatch, resume, audit, refresh). Tiers come from its own table (scoutwright flags it stale); pacing, pacewright's; hooks, rigwright's; schedules, agentwright's.

日本語の概要は準備中です。原文の説明を表示しています。

Interviews a request until no essential choice is left to guess, then hands the settled decisions on. Trigger on 'grill me', 'interview me before you build', 'stress-test this idea', 'ask me questions until it's clear', 'what am I missing before we start', or a vague plan, feature, prompt or skill where a wrong build costs more than questions. Or say grillwright (grill, record, resume, questionnaire — for someone else to answer, docs — check against glossary and ADRs). Builds nothing — prompts are promptwright's, skills skillwright's, agents agentwright's, game code slicesmith's, what a running agent may do gatewarden's, even asked as a grill.

日本語の概要は準備中です。原文の説明を表示しています。

Writes handoffs — a committed session state verified against git, or a forward task brief for a later session or agent — each ending with a paste-ready starter prompt for the next chat. Trigger on 'write the handoff', 'hand off', 'give me a prompt to hand off', 'pause here', 'holding position', a usage-limit or compaction warning, or closing a session with work still open; 'handoffwright resume' reads one back; 'now' passes it to one fresh agent. Not for resuming an active dispatchwright fan-out (its ledger holds the state), a hook that writes handoffs (rigwright's), or a chat with no filesystem (task-observer's handoff-doc mode).

日本語の概要は準備中です。原文の説明を表示しています。

Writes, fixes and red-teams prompts — system prompts, templates, meta-prompts, agent or bot instructions — as copy-paste-ready artifacts, and picks the model tier for a prompt, task or plan's subtasks. Trigger to write, improve, debug or rewrite a prompt; which model should run this; a prompt that costs too many tokens, to cut with behavior held; or say promptwright (model, optimize — tune against test cases, slim, refresh). Not for a fan-out's units (dispatchwright), installed local models (lmstudiorunner), skills or their slim (skillwright), sourced comparisons (researchscribe), handoffs (handoffwright) or a pre-build interview (grillwright).

日本語の概要は準備中です。原文の説明を表示しています。

Decides where a standing rule lives and builds the config Claude reads before work — CLAUDE.md, AGENTS.md, Project instructions and knowledge files, profile preferences, .claude/rules and agents, hooks, .mcp.json. Trigger on 'where should this rule live', 'set up a Claude Project', 'write or trim my CLAUDE.md', 'my rules get ignored', 'audit my setup for bloat or stale status', 'cut my CLAUDE.md token cost', 'add what we learned to CLAUDE.md', or rigwright (place, build, audit, learn, slim, refresh). Permissions, hook safety and config maps are gatewarden's; skills, skillwright's; unattended work, agentwright's; a block's wording, promptwright's.

日本語の概要は準備中です。原文の説明を表示しています。

Finds what changed in Claude — docs, release notes, changelogs, GitHub and community posts on Claude Code, claude.ai, Cowork, the API and models — and turns each change into adopt rows for your setup, plus a fit card for a new model or feature and a monthly bench of your skills against public skill and plugin repos (build, adopt or skip). Trigger on what changed since a date or version, a weekly sweep, features worth adopting, a feature that broke unannounced, a stale model table, what a new model or feature is good for, or how your skills compare with popular or little-known skill and plugin repos; or say scoutwright (sweep, since, watch, adopt, fit, bench, sources, refresh). Outside research is researchscribe's; applying a row, skillwright's; config, rigwright's; schedules, agentwright's; tier picks, promptwright's.

日本語の概要は準備中です。原文の説明を表示しています。

Builds, audits and packages Agent Skills, with their evals. Trigger to build, audit (security too), score or package a skill or SKILL.md; to design or integrate a pack; whether a skill beats incumbents; for trigger evals, test cases or assertion suites (skill, prompt card, agent spec); to slim a skill; when a skill did not fire or a run cost too much; for a prose pass on a skill's own files; to port or sanitize a skill set; to build or contract-test the MCP tools a plugin or mod ships; or say skillwright (evals, slim, diagnose, mcp, refresh, port, pack, integrate, upkeep). Prompt tuning is promptwright's; config slims, rigwright's; other docs, commscribe's; brands, brandscribe's; runtime grants, gatewarden's.

日本語の概要は準備中です。原文の説明を表示しています。

Proves a Godot 4.x build is actually green and holds its project conventions. Trigger when a GUT or GDScript result needs believing (a suite green while a script failed to parse, drifted CI guard counts, a coverage claim, a gate figure, a failing check someone wants softened); to review scenes, signals, awaits, threads, determinism, saves, imports or .uid files, or the upgrade rule (not the migration); to prove a simulation or balance rule; for import settings and the pixel-art render precondition; or say godotsmith (check, guard, gate, review, intake). API reference is the Godot docs'; art reads pixelsmith's; audio direction soundsmith's.

日本語の概要は準備中です。原文の説明を表示しています。

Runs the test-first build loop (spec, plan, thin slices, failing test first, verify, commit) for a Godot 4 game in GDScript or C# first; in a TypeScript, Python or other repo when test-first, slices or a reproduce-first fix is asked for. Trigger to build or add a game feature, mechanic, stat, system or milestone, even when told to test later; to turn a spec or grill record into slices; to fix a game bug from a reproduction, one hypothesis at a time; on "write the test first", "what's the next slice", "is this slice done" or "is this milestone ready to exit"; or say slicesmith (spec, plan, slice, fix, exit). Run proof and gate rulings are godotsmith's; diff review a review tool's; repo maps researchscribe's; art pixelsmith's; audio soundsmith's; interviews grillwright's; fan-out dispatchwright's.

日本語の概要は準備中です。原文の説明を表示しています。

Directs game audio and judges it by numbers — sound palettes, SFX and music briefs, Godot import settings, licence-checked generator briefs, and measured file checks (loudness, peaks, clipping, silence, loop seams). Trigger for game sound design or an audio style guide; an SFX or music list; a loop that clicks; sounds too loud or uneven; what LUFS a game should hit, or normalizing to it; checking WAV or Ogg files before import; or say soundsmith (direct, brief, audit, test). Direction, not DSP; generating a sound starts here. Running ComfyUI is comfyrunner's; audio code godotsmith's; transcription whisperrunner's; canon lorescribe's; pixel art pixelsmith's.

日本語の概要は準備中です。原文の説明を表示しています。

Directs screens and proves they fit — game menus and HUD, web dashboards, single-page artifacts, store-page layouts and plugin panes. Writes the design brief (layout, hierarchy, spacing and type scales, every state, focus and hit size, a check against generic-looking output) and probes the rendered page at phone-to-desktop widths in every theme. Trigger to design or lay out a menu, HUD, dashboard, settings screen or panel, or review its mockup before the build; when a page scrolls sideways on a phone, text is clipped or a dark theme breaks; to check that a page or pane fits from 320 to 1440 px in light and dark; for UI direction before a build, even when nobody says design; or say uismith (direct, probe, fit-first audit). The probe needs optional Playwright. A critique, scored review or brand pass of a built page, palettes and type are brandscribe's; sprites and icons pixelsmith's; Godot scene proof godotsmith's; words commscribe's.

日本語の概要は準備中です。原文の説明を表示しています。

Runs image, video and audio generation on a local ComfyUI server and guards the GPU before long renders. Trigger to generate an image, video, audio or music locally; to run, test or check a ComfyUI workflow before a long or queued render; when a video render crashed the machine, ran out of memory or hung in VAE decode; to render while LM Studio holds the GPU; to run a pixelsmith brief locally; or say comfyrunner (audit, check, test, run, status). Refuses an untiled video decode and scores resolution times frames. Briefs and judging art are pixelsmith's; sound briefs soundsmith's; freeing LM Studio lmstudiorunner's; schedules agentwright's.

日本語の概要は準備中です。原文の説明を表示しています。

Runs Docker Desktop and its WSL2 layer, checking RAM and disk before container work. Trigger when Docker Desktop or a container won't start, vmmem eats RAM or the Docker disk keeps growing; to set a WSL memory cap in .wslconfig; to list or install WSL distros; to bring a compose stack up or down; to prune images and build cache; to run a command in a container; to log in to a registry; or say dockerrunner (audit, check, up, down, prune, status, refresh). Local LLMs (Docker Model Runner too) are lmstudiorunner's; images comfyrunner's; VMs and sandboxes hypervrunner's; Docker's MCP catalog its MCP Toolkit's; registry tokens keywarden's.

日本語の概要は準備中です。原文の説明を表示しています。

Answers plain-word questions from a repo's CSV, JSON, Parquet and YAML files, or a .duckdb file, with DuckDB, and shows the SQL it ran. Read-only. Trigger to query, count, join, filter or summarise data files, including analytics CSVs exported from a video platform; to build a Parquet or DuckDB cache; to check no .duckdb, .wal or .parquet cache is committed or stale; when a query hits a locked database file; or say duckrunner (ask, cache, check, refresh). Needs the user-installed duckdb Python package; never a database server. DuckDB docs, S3 and MotherDuck are the duckdb-skills plugin's; outside research researchscribe's.

日本語の概要は準備中です。原文の説明を表示しています。

Runs Hyper-V VMs and Windows Sandbox. Trigger to create, start, stop, check or delete a VM (Gen2, secure boot, virtual TPM, settings proved); to take, list or restore a checkpoint; to test a plugin install on a clean machine from a golden checkpoint; to open a suspicious file or zip in a disposable sandbox with networking off; when Hyper-V says access denied; or say hypervrunner (audit, setup, vm, checkpoint, teardown, cleanroom, sandbox, status). Runs as a Hyper-V Administrators member, never self-elevated. Containers and WSL are dockerrunner's; whether code is trustworthy trustwarden's; secrets in returned files shieldwarden's.

日本語の概要は準備中です。原文の説明を表示しています。

Hands work to a local model served by LM Studio and verifies what comes back. Trigger to offload, delegate or batch work to a local, offline or on-device model; to queue unattended runs that keep only what passes; to ask which installed model fits a job or whether to switch; to size a task before delegating; when a local model returns nothing, repeats itself or drifts on a long list; when LM Studio shares the GPU with an image tool, or to free its hold; or say lmstudiorunner (audit, size, queue, run, status). Reads models from the live LM Studio API. Cloud model picks and prompt text are promptwright's; a schedule's guardrails agentwright's.

日本語の概要は準備中です。原文の説明を表示しています。

Drives OBS Studio through its WebSocket, read-only by default, and turns recordings into clips, VOD cuts and chapters with FFmpeg. Trigger to audit an OBS setup; when a stream drops frames or lags; to switch a scene, mark a moment or save the replay buffer; to cut clips, burn in captions, normalize loudness or write chapters; when OBS shares a GPU; or say obsrunner (audit, check, set, mark, post, sheet, status, hold, release, refresh). Live work needs the user-installed obsws-python package. Never goes live, uploads or moderates chat. Caption files are whisperrunner's; thumbnails comfyrunner's; titles commscribe's; analytics duckrunner's.

日本語の概要は準備中です。原文の説明を表示しています。

Writes and cleans up messages and docs for their channel and reader (email, Slack, a text, release notes, store pages, READMEs, Claude Docs) in a plain voice that never moves a fact. Trigger to write, rewrite, shorten, line-edit, retell or change the tone of any message, even a two-line text; to strip dashes or AI tells; to fix UI wording (a dialog, button or error); to score text without rewriting; to plan release comms; to write a store page, launch post or listing title, blurb and tags; to write in a voice or learn one; or say commscribe (draft, reshape, humanize, audit, retell, formats, cadence, voice, docs). It never sends. Skill packages are skillwright's; brand voice and layout brandscribe's; sourced write-ups researchscribe's.

日本語の概要は準備中です。原文の説明を表示しています。