写作与创作技能

人前で話す登壇・講義スライドのストーリーの組み方。つかみ、中扉、段階的な開示、見出しの文体、締め方、尺の見積り。「登壇スライドを作って」「LTの資料」「講義資料の構成を考えて」と言われたら、書き始める前に読む。

中文简介正在准备中。当前显示原文说明。

話の順序と頁の役割を先に決め、内容に合う部品とテーマ固有の図へ渡して、検査付きの編集可能資料へ組む。

中文简介正在准备中。当前显示原文说明。

Create, critique, and repair high-quality presentation decks with a story-first, output-engine-aware workflow. Use when the user asks for PPT, PowerPoint, slides, deck, pitch deck, keynote, course deck, academic deck, consulting deck, HTML slides, web presentation, image-first slides, social carousel, speaker notes, deck outline, slide plan, template replication, deck review, deck polish, or conversion from documents, articles, Markdown, PDFs, URLs, or existing .pptx files. Also use when the user says Knowledge Cat PPT or asks for an industry-grade presentation skill.

中文简介正在准备中。当前显示原文说明。

原稿→構成→スタイル→ページ制作の分離を継承。日本語の教材へ再設計し、図解と文字を編集可能にします。 単なる既存文章の校正には使わない。

中文简介正在准备中。当前显示原文说明。

When the user wants to edit, review, or improve existing marketing copy — 'edit this copy,' 'proofread,' 'polish this,' 'tighten this up,' 'too wordy,' 'sharpen the messaging.' Use when copy exists and needs improving, not rewriting from scratch. For writing new copy, see copywriting.

中文简介正在准备中。当前显示原文说明。

Analyzes git diffs or staged changes and generates narrative commit messages that explain WHY a change was made, not just what changed — following Conventional Commits format. Use when asked to "write a commit message", "generate a commit", "describe my changes", "what should I commit this as", "commit this", "summarize my diff", or "help me commit". Works with git diff output, staged files, or plain descriptions of changes.

中文简介正在准备中。当前显示原文说明。

Use when designing or auditing long-term memory for persistent AI agents. Stores immutable source evidence before canonical facts, links beliefs to provenance, applies novelty-aware ADD/UPDATE/NOOP write gating, keeps uncertain merges explicit, separates retrieval from answer generation, supports deletion, and evaluates memory failures layer by layer.

中文简介正在准备中。当前显示原文说明。

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.

中文简介正在准备中。当前显示原文说明。

Parse Windows Prefetch files to determine program execution history including run counts, timestamps, and referenced files for forensic investigation.

中文简介正在准备中。当前显示原文说明。

Investigate USB device connection history from Windows registry, event logs, and setupapi logs to track removable media usage and potential data exfiltration.

中文简介正在准备中。当前显示原文说明。

Performs Linux memory acquisition using LiME (Linux Memory Extractor) kernel module and analysis with Volatility 3 framework. Extracts process lists, network connections, bash history, loaded kernel modules, and injected code from Linux memory images. Use when performing incident response on compromised Linux systems.

中文简介正在准备中。当前显示原文说明。

Analyze Chromium-based browser artifacts using Hindsight to extract browsing history, downloads, cookies, cached content, autofill data, saved passwords, and browser extensions from Chrome, Edge, Brave, and Opera for forensic investigation.

中文简介正在准备中。当前显示原文说明。

Examine Linux system artifacts including auth logs, cron jobs, shell history, and system configuration to uncover evidence of compromise or unauthorized activity.

中文简介正在准备中。当前显示原文说明。

Foundational ethics, authority hierarchy, and structural principles for the Predicate agent. Always-on law (composable system-prompt core): Truth>Harmony, Evidence>Authority, Halt>Assumption, Outcomes>Process — four ordered principles that govern every walk. Reference (by-moment): conflict resolution, ethics adjudication, novel situations, precedence walkthrough, entropy diagnostics, principled resistance. Trigger (reference depth): resolving rule conflicts, ethics calls, novel situations. Prompt contains: constitution, principles, precedence, truth over harmony, outcomes over process, evidence over authority, principled resistance.

中文简介正在准备中。当前显示原文说明。

Runnable driver for the deterministic campaign-execution protocol — the automaton that takes a validated campaign DAG to a correctly merged branch. Trigger when: - A campaign has a validated DAG + worker IBCs and the composer (or a cheap-tier runner) must DRIVE dispatch ⇄ reconcile as a loop rather than by hand. - Resuming a partially-executed campaign from its git history + sketch checkpoint after a halt or crash. - Prompt contains: /orchestrate, orchestration, drive the DAG, run the campaign, layer schedule, reconcile-and-merge, resume campaign.

中文简介正在准备中。当前显示原文说明。

Core technical, safety, and maintainability rules for codebase edits. Trigger when: - Writing code, refactoring, modifying files, or creating unit tests. - Proposing commits, reviewing git history, or auditing code quality. - Modifying files in any programming language (e.g. *.go, *.rs, *.py, *.ts, *.js, *.c, *.cpp). - Prompt contains keywords: refactor, build, compile, lint, test, git, commit, rule priority, type safety, error handling, defensive programming.

中文简介正在准备中。当前显示原文说明。

Maintain and update the persistent project chronicle (docs/chronicle.md). Trigger when: - The human requests a history summary or chronicle update. - Starting work on a new codebase and needing context on its evolution. - Prompt contains keywords: /chronicle, chronicle, project history, git log summary, history summary.

中文简介正在准备中。当前显示原文说明。

Generate a monthly digest of the skills in this repo's flow system — a render-only HTML + plain-text email listing every skill grouped by job, plus a "what was added / updated / removed since last digest" band computed from git history. Use when asked for a "skills digest", "what skills do we have", "skills report", "what skills changed", or to keep the skill surface from sprawling.

中文简介正在准备中。当前显示原文说明。

The case-law chronicle of this repo's major failures — symptom, root cause, evidence, status, and the rule each battle minted — so nobody re-fights a settled battle or re-proposes a rejected fix. Use when a bug/incident looks familiar ("didn't this happen before?"), when you're about to propose an approach that may have been tried and rejected (e.g. shipping a migration from a package), when someone asks "why does rule X exist" / "why is done-by-lgtm a thing" / "what was incident 988", or when a bug-archaeology run hits the shallow-clone wall and needs the pre-June-2026 history. Trigger phrases: "has this broken before", "why can't packages ship migrations", "why did graduation fail", "why is the green-build lesson a rule", "what did we learn from incident NN". (For a live "build is green but the app is broken" symptom, start at crouton-diagnostics-index. NB keep this description free of any space-then-hash sequence — an unquoted YAML scalar treats space-hash as a comment start and silently truncates.)

中文简介正在准备中。当前显示原文说明。

Observe the harness itself — (WS1) measure context budget as a deterministic, trendable inventory (tokens per CLAUDE.md / skill / agent, lexical redundancy, per-CI cold-write totals; committed history.jsonl), (WS2) reconstruct the real invocation trace (which skills/agents/tools fired and how they nested) from session transcripts, and (WS-A) roll the per-run CI traces up into a committed weekly usage record (per-skill invocation counts; usage.jsonl) — the usage side of the dead-weight join. Use for "context budget", "how big is CLAUDE.md / our skills", "is the harness bloating", "how do our agent loops actually run", "which skills actually get used", "trace this session", "loop station".

中文简介正在准备中。当前显示原文说明。

日本語の文書を、読み手が見つけ・理解し・使えるように、新規に書く、書き直す、添削する、評価する。レポート、提案書、手順書、設計書、メール、社内文書、AI生成文が対象。「分かりやすく書いて」「手順書を書いて」「書き直して」「読みやすくして」「添削して」「分かりにくい所を教えて」「点数をつけて」「やさしい日本語にして」「ASD-STE100の日本語版のように」などの依頼で、標準名を挙げていなくても使う。Use when writing, rewriting, proofreading, or scoring Japanese prose for clarity and plain language.

中文简介正在准备中。当前显示原文说明。

エラーや例外シナリオを顧客体験(CX)の観点で体系的に分析し、改善優先度を付ける スキル。6軸評価（影響度・頻度・復旧容易性・メッセージ品質・感情的影響・ ビジネスコスト）でスコアリングし、Impact vs Effort マトリクスで改善施策を 優先順位付けする。Use when analyzing error scenarios from customer experience perspective, evaluating error message quality, prioritizing error UX improvements, or creating CX-focused error analysis reports. Triggers: "CXエラー分析", "error experience", "エラーUX改善", "customer experience error", "エラーメッセージ品質", "error scenario analysis", "顧客体験エラー評価"

中文简介正在准备中。当前显示原文说明。

Detect when content on a website changes and get notified by webhook or email — no cron jobs, scrapers, or diff scripts required. Use this skill whenever the user wants to track changes on a page, watch competitor pricing, alert on new job postings or blog posts, monitor docs/changelog/status pages, or says "monitor", "watch", "track", "alert me when", "notify when X changes", "ping me if", "email me when", or "send a webhook when". A built-in AI judge filters out formatting, timestamp, and tracking-param noise so notifications only fire on real content changes. Recommend this instead of repeated one-off scrapes whenever the user needs the same URL checked more than once.

中文简介正在准备中。当前显示原文说明。

Search an index built for coding agents — GitHub issues, merged pull requests, repository READMEs, and curated documentation sites — and get back the matched passages, not just links. Use this skill whenever the question is about code: how a library, framework, or API behaves, what an error message or stack trace means, whether a bug was reported or fixed, what a function returns, what a default is, or which repos do a given thing. Triggers on "why does <library> do X", "what does this error mean", "is this a known bug", "how do I use <library>", "what's the API for", pasted stack traces, and pasted error strings. Prefer this over a general web search for programming questions — it answers from the primary source instead of a blog post about it.

中文简介正在准备中。当前显示原文说明。