5,325 件 ・ 関連度順
概要と使いどころ
Delegate a prompt to Claude via `claude -p`. Use when the user wants to offload a task to Claude from another agent (Codex, Cursor, another Claude session), get a second opinion, or run a parallel implementation. Default model is opus.
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 the "Report Sources" child page for a finished Weekly Community Signal report — an evidence-backed defense of WHY every item landed in the column/section/rank it did. The agent argues each placement like a lawyer (claim → evidence → rule → rebuttal) but is under oath: it CANNOT invent, spin, or overstate — every claim ties to a verifiable fact (issue #, label, PR type, quoted comment, npm output, the front-door test). Not CYA — it's so Nathan can defend the report with facts and see the exact reasoning behind each call. Runs after the report (invoked by weekly-report, last steps) and on "report sources", "defend the report", "why is this here".
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。
TDD Refactor Phase - Improve code while keeping tests green using Simple Design Rules and APP mass
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。
The complete AI Business Mentor.
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。
BluOS CLI (blu) for discovery, playback, grouping.
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。
Expert-level semiconductor materials covering band theory, silicon processing, compound semiconductors, wide bandgap materials, and semiconductor device fundamentals.
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。
Expert-level medicinal chemistry knowledge. Use when working with drug design, structure-activity relationships, ADMET properties, pharmacophores, lead optimization, target identification, drug metabolism, or pharmaceutical development. Also use when the user mentions 'SAR', 'drug design', 'pharmacophore', 'ADMET', 'lead compound', 'hit to lead', 'drug metabolism', 'bioavailability', 'selectivity', 'binding affinity', 'scaffold hopping', or 'bioisostere'.
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。
Use when writing, debugging, or configuring an omp hook or extension — blocking or rewriting tool calls, redacting tool output, reshaping LLM context, registering tools/commands, or wiring modules through config.yml. Covers ExtensionAPI (current) vs HookAPI (legacy), the event catalog, discovery and load order, and disable controls. Not for Claude Code hooks (~/.claude/settings.json) or the shared harness safety guard (~/.agents/harness/hooks/).
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。
PR formatting reference — title, body template, label mapping, assignment, and draft policy. Invoked by pr/create and pr/update-desc commands to ensure consistent PR formatting.
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。
Form a committee of two high-reasoning agents to step back, do root cause analysis, and produce a plan. Use when stuck, looping, tunnel-visioning, or facing a hard planning problem.
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。
Pin the current cmux workspace to the done lane with `cmux workspace status set done` once a session goal is reached and verified. Use at the end of a work session running inside a cmux terminal, right before the final response; skip when work is blocked, handed off, awaiting user input, or when nothing was changed.
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。
Coordinate multi-agent work through durable artifacts in git instead of chat. Use this whenever a task involves sending a message to another agent, agent mailboxes or handoffs, claiming work from a shared queue, notifying another agent or crew (OpenClaw, Grok Bot, Claude Code, Codex, Gas Town/Gas City workers) that work is ready, or whenever the user mentions the artifact bus, message bus, agent mail, beads mail, doorbells, or pings between agents — even if they don't say "bus" explicitly.
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。
Use when invoked as $new-project or when creating a brand-new repository or project from scratch — scaffolds mise-pinned tools, a just task surface, the standard repo files, and CI for Python (uv), TypeScript (bun), Rust (cargo), or Go.
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。
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
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。
Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.
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。
kpopper Hub: optional experimental application for exploring the project record. Use when the user explicitly requests kpopper Hub or its record page, its graph, layout or verification, or has a standing preference for this application. Do not render automatically after mapping or recording. Install the HTML runtime before use. Not for ordinary HTML documents or a text answer from the record. Requests come in any language.
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。
Write what the work found into the project's knowledge record, so the next session inherits it instead of re-deriving it. Use the moment something worth keeping exists: a fact taken from a source, a rule worked out, a decision or conclusion, a measurement, a correction to a recorded value, or a question left open - and check for unrecorded findings before implementation, handoff (including a PR), or finishing work. Record within the user's write authorization. The first write creates GROUNDING.yaml. Covers one-report update, add, set, review, same and distinct, judgments with a falsifier, and background capture.
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。
Update Codex's pinned `v8` / `rusty_v8` versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update `rusty_v8` artifacts, prepare or validate a V8 release candidate, check `v8-canary`, or diagnose why a V8 version update no longer builds.
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。
Opinionated constraints for building better web interfaces with coding agents. Use this skill whenever the user asks you to build, review, or fix a UI — landing pages, dashboards, components, or any frontend code — and whenever you write Tailwind CSS, motion/react animations, accessible component primitives (Base UI, React Aria, Radix), or review agent-generated interface code for quality, accessibility, and performance. Also trigger for "make the UI better", "review my interface", "clean up this component", or any frontend work in React, Next.js, or plain HTML/CSS.
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。
Diagnose and fix CJK (Korean, Japanese, Chinese) text-wrapping issues in web UIs. Systematically traces mid-syllable breaks, orphaned glyphs, and awkward line splits through a layered fix strategy covering global CSS cascade, component-library overrides, headline balancing, and translation-level phrase binding. Produces an evidence-based diagnosis and verification report before any code change is applied.
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。
Shaping a UI component tree — composition vs inheritance, slot patterns, prop API design, controlled vs uncontrolled, polymorphic — on 'split this component'. Feeds react-shadcn-ui.
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。
Use when balancing eng-team velocity vs quality vs burnout — on-call load, focus fragmentation, reorg shock. Triggers on 'team is burning out', 'why is velocity dropping'.
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。
Use when shaping brand voice — voice attributes, tone-by-context matrix, consistency review. Triggers on 'define our voice', 'why does our copy sound different on every surface'.
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。
Before adding/installing any dependency the agent named — verify the package exists (slopsquatting: ~1 in 5 AI suggestions are hallucinated), isn't typo-adjacent, is pinned + locked, and CVE-scanned
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。