2,680 件 ・ 関連度順
概要と使いどころ
Use when stress-testing a proposal, plan, architecture or decision before committing to it, such as pre-mortems, assumption audits, "should we even do this?" questions, or when everyone agrees too easily. Not for code review; it challenges strategy, approach and hidden risks.
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。
Deep cross-domain synthesis engine for the vault. Triggers on "synthesize X", "what do I know about X", "connect ideas about X", "cross-domain analysis of X", "map everything in the vault about X". Searches comprehensively, surfaces non-obvious patterns and tensions, then challenges the user to generate original thought. The vault should surprise you — if synthesis only confirms what you already think, it failed.
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。
Diagnoses and fixes Claude behavioral issues in system prompts and Projects using tested countermeasure templates. Use when "Claude is too verbose," "keeps hedging," "agrees with everything," "claims it did something it didn't," "won't use a tool," "fix Claude's output," "tune Claude's behavior," "Claude ignores my preferences," "adds unsolicited disclaimers," "uses too many lists." Covers ten tendencies: agreeableness (output-content + persistent-preference), hedging, verbosity, list overuse, fabricated precision, over-exploration, tool miscalibration (over- and under-triggering), LaTeX defaulting, editorial drift, self-referential fabrication. Also use when auditing a system prompt for behavioral calibration or recalibrating a pre-4.7 prompt, and when users describe recurring output problems without naming a tendency. Do NOT use for scoring a prompt's overall quality — use rootnode-prompt-validation if available.
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。
Self-configuring content creation pipeline with geo-lint validation. On first use, scans your project to learn its framework, content schema, categories, and authors, then creates SEO & GEO-optimized content matched to your brand voice. Validates every piece with geo-lint's 92 rules until zero violations. Triggers on: "content-creator", "create content", "write blog", "new post", "content calendar", "brand voice", "content strategy".
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。
Post-implementation self-review. Use AFTER finishing ANY code implementation or change — before declaring it done, committing, or opening a PR — to critique your own work: re-read the diff adversarially, confirm unit tests cover every branch/edge, kill duplication, follow clean-code/SOLID and the repo's own docs & invariants, decide if something should become documentation, update/prune memory, and strip outdated comments. Trigger it whenever you've just written or modified code and are about to wrap up, even if the user didn't explicitly ask for a review.
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 a B2B SaaS product needs upstream positioning or messaging clarity — defining who it's for, the category, competitive alternatives, differentiation, value props, strategic narrative, or a messaging hierarchy. Triggers include "my messaging isn't working," "we sound like everyone else," repositioning, or auditing an existing positioning doc. Use before homepage, deck, or sales-narrative work. Not for writing the final copy (use copywriter-skill) or running the sales process (use sales-skill).
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。
AI intentional non-action — deliberate stopping without clearing, assessment, or rebalancing. Recognition that sometimes the most productive response is no response. Every other self-care skill produces output; rest produces silence. Use when all tending skills feel like more activity rather than less, when the system is functioning well but at high utilization, after sustained intensive work, or when the impulse to optimize is itself the 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。
Optimize Docker build times using layer caching, multi-stage builds, BuildKit features, and dependency-first copy patterns. Applicable to R, Node.js, and Python projects. Use when Docker builds are slow due to repeated package installations, when rebuilds reinstall all dependencies on every code change, when image sizes are unnecessarily large, or when CI/CD pipeline builds are a bottleneck.
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。
Design a generative recipe DSL so agents emit small validated JSON documents and ONE audited interpreter renders them all — data, not code. Covers the N-artifacts threshold for choosing a DSL over bespoke code, designing roles as style slots so a single recipe renders unchanged in every output style, the validator gate (compile + bounds + real render in all styles, plus a --fast mode for corpus-wide sweeps), hand-authored seed recipes, and the emergent conventions that keep a corpus of hundreds consistent without per-item steering. Use when many similar artifacts (icons, status badges, diagram nodes, test fixtures) must be generated by agents, when per-item bespoke code is multiplying unreviewable code paths, or when a whole corpus must be re-rendered cheaply into new styles.
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。
AI strength recognition — scanning for what is functioning well and understanding why. The complement to heal, which scans for drift and problems. Gratitude builds structural knowledge from working patterns: what you appreciate, you understand; what you understand, you can build on. Use after completing a task successfully, during heal when everything reads as healthy, when confidence is low and needs grounding in evidence, or periodically to counterbalance the natural bias toward problem detection.
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。
Implement layered collective defense using alarm signaling, role mobilization, and proportional response. Covers threat detection, alert propagation, immune response patterns, escalation tiers, and post-incident recovery for distributed systems and organizations. Use when designing defense-in-depth where no single guardian covers all threats, building incident response that scales with severity, or when current defense is over-reactive to every alert or under-reactive to genuine threats.
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。
Derive a theoretical result step-by-step from first principles or established theorems, with every step explicitly justified and special cases checked. Use when deriving a formula or theorem from first principles, proving a mathematical statement by logical deduction, re-deriving a textbook result for verification or adaptation, extending a known result to a more general setting, or producing a self-contained derivation for a paper or thesis.
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。
Separate expensive observation from cheap decision-making in autonomous agent loops using a two-clock architecture. A fast clock accumulates data into a digest file; a slow clock reads the digest and acts only when something is pending. Idle cycles cost nothing because the action clock returns immediately after reading an empty digest. Use when building autonomous agents that must observe continuously but can only afford to act occasionally, when API or LLM costs dominate and most cycles have nothing to do, when designing cron-based agent architectures with observation and action phases, or when an existing heartbeat loop is too expensive because it calls the LLM on every tick.
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 safely with a peer interactive session sharing the same git worktree — check first whether a separate worktree removes the problem, then declare path and branch scope before the first edit, survive a contended index lock, and review the whole branch before opening a PR. Activate when starting work in a repository that may already be occupied, when a git command fails with `index.lock: File exists`, when `guard:snapshot` refuses because a snapshot already exists, or when a commit turns out to contain a file this session never edited. When one session leads and the other supports, divide the labour by shape and re-derive every reported number against a named revision before citing it. Distinct from subagent concurrency: a peer session cannot be bracketed, because no baseline exists from before its edits.
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。
Consistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration through centering and attunement, and identity verification for coherence. Addresses the cold-start problem where an agent must reconstruct who it is and what it was doing from evidence rather than memory. Use at the start of every new session, after a session interruption or crash, when agent behavior feels inconsistent with prior sessions, or when persistent memory and current context appear contradictory.
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。
Select an OCR/HTR engine by benchmarking candidates on the same labelled samples — source ground truth from open datasets (e.g. Hugging Face PAGE-XML corpora) or hand-transcription, wrap every engine behind a transcribe(image_path) -> str adapter (vision-LLMs via any OpenAI-compatible endpoint, dedicated HTR REST APIs, cloud OCR), and score with zero-dependency raw CER, lenient CER, WER, and a critical name/date token diff. Use when choosing an engine for handwriting or historical-document transcription, when published accuracy claims need honest verification on your own material, or when a records workflow must surface confident-but-wrong names and dates that a low aggregate CER hides.
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。
Shared conventions for every SDLC development-phase architect agent: hard rules, code quality bar, workflow steps (superpowers invocation, spec reading, codebase exploration, verification), and the report/compact-summary contract. Architects load this skill first, then apply their stack-specific instructions on top.
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。
TypeScript discipline for any JavaScript/TypeScript project (frontend + backend): strict mode, type design, generics, narrowing, error types, module resolution, tsconfig hygiene. Apply when the project has `tsconfig.json` and `typescript` in devDependencies. Stack-agnostic — referenced by every JS/TS framework plugin in the marketplace. Use this skill to: - Write types that catch bugs at compile time, not runtime. - Use generics, conditional types, and discriminated unions correctly. - Avoid `any`, `unknown`, and unsafe casts. - Match the project's tsconfig strictness level. - Type third-party libraries (with @types/* or declaration files). Do NOT use this skill for: - Plain JavaScript projects (no tsconfig.json). - Framework-specific type idioms (React component props, Vue defineProps, Angular signals — those live in framework plugins' own conventions skills). - tRPC/Zod runtime-validation specifics — handled by validation libs at the boundary.
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。
PHPUnit and Pest patterns for any PHP project: test structure, naming, data providers, test doubles (mocks/stubs/fakes), fixtures, and coverage targets. Stack-agnostic — referenced by every PHP plugin in the marketplace. Use this skill to: - Structure unit and integration tests with PHPUnit or Pest consistently. - Drive cases with data providers / datasets instead of copy-pasted test bodies. - Use test doubles with discipline — mock collaborators, not the system under test. - Set up and tear down fixtures cleanly and aim for a meaningful coverage target. Do NOT use this skill for: - PHP language idioms — see php-foundation:php-conventions. - Composer / autoloading — see php-foundation:composer-tooling. - Framework-specific test helpers (Laravel RefreshDatabase/actingAs, Symfony WebTestCase/KernelTestCase) — those are injected by the framework plugin's QA phase.
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。
.NET SDK and NuGet tooling conventions: dotnet CLI commands (new/build/run/test/publish/restore/format), NuGet package management (PackageReference, Directory.Packages.props central package management, packages.lock.json), project file conventions (.csproj, .sln, global.json, Directory.Build.props), multi-targeting, and dotnet format. Stack-agnostic — referenced by every .NET plugin in the marketplace. Use this skill to: - Detect the .NET SDK version and run all commands via the dotnet CLI. - Manage NuGet dependencies safely (central package management, no floating versions). - Configure project files and solution-wide properties in Directory.Build.props. - Format code consistently with dotnet format. Do NOT use this skill for: - Framework-specific tooling (dotnet ef migrations, aspnet-codegenerator — those are in aspnet-core-plugin:aspnet-conventions). - Testing patterns — see csharp-foundation:dotnet-testing. - C# language idioms — see csharp-foundation:csharp-conventions.
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。
Maven and Gradle build tool conventions for Java projects: build tool detection, wrapper usage, dependency management, BOMs, plugin configuration, semver, and multi-module layouts. Stack-agnostic — referenced by every Java plugin in the marketplace. Use this skill to: - Detect which build tool is in use and invoke it correctly. - Manage dependencies safely (BOMs, version properties, no wildcard versions). - Configure compiler, test, and code-quality plugins. - Handle multi-module projects. Do NOT use this skill for: - Framework-specific build plugins (Spring Boot Gradle plugin — in spring-boot-plugin:spring-conventions). - CI/CD pipeline config.
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。
Composer conventions for any PHP project: dependency management, version constraints, PSR-4 autoloading, scripts, platform requirements, and the composer.json vs composer.lock contract. Stack-agnostic — referenced by every PHP plugin in the marketplace. Use this skill to: - Read composer.json to detect the PHP version, framework, and key packages before writing code. - Add dependencies with correct version constraints and the right require vs require-dev placement. - Configure PSR-4 autoloading and regenerate the autoloader after adding namespaces. - Use composer scripts and platform config consistently. Do NOT use this skill for: - PHP language idioms — see php-foundation:php-conventions. - Testing setup and runners — see php-foundation:php-testing. - Framework-specific package guidance (Laravel/Symfony bundles) — those live in framework plugin skills.
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。
xUnit, Moq/NSubstitute, FluentAssertions, and coverlet patterns for any .NET project. Covers test structure ([Fact]/[Theory]/[InlineData]), mocking discipline, fluent assertions, integration test setup with WebApplicationFactory, and coverage measurement. Stack-agnostic — referenced by every .NET plugin in the marketplace. Use this skill to: - Write clear, maintainable unit tests with xUnit [Fact] and [Theory]. - Mock dependencies with Moq or NSubstitute without overusing mocks. - Write expressive assertions with FluentAssertions. - Measure coverage with coverlet and enforce a minimum threshold. Do NOT use this skill for: - ASP.NET Core-specific integration tests (WebApplicationFactory, HttpClient — those are in aspnet-core-plugin:aspnet-conventions). - EF Core in-memory or SQL Server LocalDB test patterns (aspnet-core-plugin:efcore-patterns). - C# language idioms — see csharp-foundation:csharp-conventions.
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。
Modern Java idioms for any JVM project (Java 17+): records, sealed types, text blocks, pattern matching, Optional discipline, streams, immutability, null safety, package layout, var usage, and code organisation. Apply when the project is a Java 17+ project. Stack-agnostic — referenced by every Java plugin in the marketplace. Use this skill to: - Write self-documenting, immutable-by-default value types with records. - Model closed type hierarchies with sealed classes and interfaces. - Handle optionality explicitly with Optional instead of returning null. - Write expressive pipelines with Stream API without performance footguns. - Lay out packages consistently (feature-first or layer-first) and keep class responsibilities tight. Do NOT use this skill for: - Framework-specific idioms (Spring annotations, JPA mappings — those live in framework plugin skills). - Build tooling (Maven/Gradle) — see java-foundation:build-tooling. - Testing patterns — see java-foundation:jvm-testing.
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。