1.4万 件 ・ 関連度順
概要と使いどころ
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
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 spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.
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。
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has been paged at 3am for a factory class that wrapped one function: question whether the task needs to exist at all, reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full, ultra. The default is full. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests such as general knowledge, prose, translation, summaries, recipes.
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。
Interview the user in rounds until no branch of the design tree stays open.
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。
Core coding guidelines for iOS, iPadOS, macOS, watchOS, tvOS, and visionOS app development using SwiftUI and Swift. Use when implementing Views, working with @State/@Binding/@Observable/@StateObject, using NavigationStack/List/LazyVStack, designing components, or asking about SwiftUI patterns (infinite scroll, pull-to-refresh, search). Covers best practices, implementation patterns, and anti-patterns to avoid.
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。
Single Source of Truth (SSOT) guidelines for SwiftUI state management. Use when designing state architecture, choosing between @State/@Binding/@StateObject/@ObservedObject/@EnvironmentObject, fixing state synchronization issues, refactoring duplicated state, or reviewing state management in PRs. Covers SSOT principles, property wrapper selection, state lifting, and common violations.
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。
Code review checklist for SwiftUI and Swift PRs. Use when reviewing pull requests, checking code quality, verifying Swift/SwiftUI implementations, or conducting PR reviews. Provides prioritized checklist covering state management, performance, component design, data flow, async handling, UI/UX, accessibility, security, and 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。
Android data layer implementation guide. Provides comprehensive patterns for Room Database (Entity, DAO, Migration), DataStore (Preferences), Repository layer design, and common pitfalls. Use when implementing local data storage, cache strategies, or data source integration in Android projects.
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。
Extract and maintain a cross-portfolio catalyst calendar from all thesis notes. Use when user says "catalyst", "calendar", "what's coming up", "upcoming events", or "what could move the portfolio".
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。
Pull an earnings call (or investor-event) transcript from Quartr (FMP fallback), extract qualitative signal (management commentary deltas, hedging shifts, Q&A tone), and produce a thesis-delta-first Research note. Use when user says "transcript", "pull earnings call", "transcript diff", or "ingest [TICKER] earnings".
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。
Pull an earnings call transcript from Financial Modeling Prep, extract qualitative signal (management commentary deltas, hedging shifts, Q&A tone), and produce a thesis-delta-first Research note. Use when user says "transcript", "pull earnings call", "transcript diff", or "ingest [TICKER] earnings".
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。
Tag a thesis's implicit macro bets — the macro variables its bull case is secretly levered to (AI capex, rates, FX, China decoupling, memory/HBM cycle, energy, regulation) with direction and magnitude. Use when user says "macro exposure", "what macro is [TICKER] betting on", "macro bets", or "rate exposure for [TICKER]".
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。
Restore a thesis, sector, or macro note from a snapshot in _Archive/Snapshots/. Use when user says "rollback", "restore", "revert", "undo sync", or "go back to the previous version".
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。
Map a thesis's position in its value chain — who it buys from, sells to, and competes with; where the bottleneck and pricing power sit; and whether it owns a critical layer. Use when user says "value chain", "supply chain position", "where does [TICKER] sit", or "who are [TICKER]'s suppliers/customers".
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。
Audit whether a thesis's stated conviction matches its evidence, and whether any Conviction Trigger has silently fired without being actioned. Use when user says "conviction audit", "is my conviction right on [TICKER]", "did a trigger fire", or "should I re-rate [TICKER]".
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。
Extract a thesis's dependency fingerprint — the external variables its bull case actually rests on (key customers, suppliers/inputs, technology transitions, macro drivers, single points of failure). Use when user says "dependency map", "what does [TICKER] depend on", "dependency fingerprint", or "map exposures for [TICKER]".
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。
Change conviction level or status on a single thesis. Use when user says "change conviction", "downgrade", "upgrade", "move to monitoring", "close [TICKER]", or "set [TICKER] to [level]".
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。
Conviction-trigger surveillance via Quartr keyword alerts — parse every active thesis's Conviction Triggers for named observables, propose keyword alerts scoped to the Vault Active watchlist (or market-wide for macro observables), create them ONLY on explicit user confirmation, and reconcile the alert set against the book as theses open/close. Use when user says "monitor", "set up alerts", "keyword alerts", "watch for X", or "reconcile alerts".
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。
Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by dependency wave.
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。
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
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。
End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative writing, and citation verification.
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。
Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".
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。
Supply chain investigation, evidence recovery, and forensic analysis for GitHub repositories. Covers deleted commit recovery, force-push detection, IOC extraction, multi-source evidence collection, hypothesis formation/validation, and structured forensic reporting. Inspired by RAPTOR's 1800+ line OSS Forensics system.
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 PRIMARY development workflow for the Archon project (remote-coding-agent). Use this skill instead of any PRP skills when working on Archon code. Routes to 10 specialized cookbooks based on what the user is trying to do: RESEARCH — "how does the orchestrator work?", "where is session state defined?", "trace the workflow execution flow", "what is IWorkflowStore?" INVESTIGATE — "should we use Drizzle or Prisma?", "what's the best way to add WebSockets?", "can we migrate to Turso?", "how do other projects handle rate limiting?" PRD — "write a PRD for dark mode", "spec out the notification feature", "product requirements for webhook retry" PLAN — "plan the auth refactor", "design the caching layer", "create an implementation plan for #42" IMPLEMENT — "implement the plan", "execute .claude/archon/plans/auth.plan.md", "build the feature from the plan", "code this up" REVIEW — "review PR #123", "review my changes", "code review the diff" DEBUG — "debug the failing test", "why is streaming broken?", "root cause analysis on the timeout issue" COMMIT — "commit these changes", "commit the auth refactor" PR — "create a PR", "open a pull request for this branch" ISSUE — "report this to gh", "create a gh issue", "log it in github", "file a bug for this", "create a feature request" This skill triggers on ANY development task: researching, investigating, planning, building, reviewing, debugging, committing, or shipping code. NOT for: Running Archon CLI workflows in worktrees (use /archon instead).
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。