スキルを探す

A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph. Ingest documents once — the LLM writes wiki pages, extracts entities/relations into the graph, and stores raw content for evidence retrieval. Knowledge accumulates and cross-references; it is never re-derived from scratch. Use when building a knowledge base from many documents that should accumulate and cross-reference over time instead of being re-read each session.

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。

PostgreSQL-specific code review assistant focusing on PostgreSQL best practices, anti-patterns, and unique quality standards. Covers JSONB operations, array usage, custom types, schema design, function optimization, and PostgreSQL-exclusive security features like Row Level Security (RLS). Use when reviewing SQL, schema, or functions written for PostgreSQL.

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。

Triggers on keywords RAG, GraphRAG, vector database, agentic RAG, semantic search

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 comparing basic, enhanced, GraphRAG, or agentic RAG designs, evaluating domain-specific RAG quality, tuning retrieval components, or deciding whether agentic RAG is worth its cost.

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。

Also use for async Python patterns, Pydantic schemas for LLM structured outputs, retry strategies for LLM calls, background AI jobs, or any service combining FastAPI and LLMs. If Python + AI backend is in scope — use this 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。

Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.

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。

Structural simplicity review based on Rich Hickey's "Simple Made Easy" framework. Trigger when: - Reviewing code for complected concerns, analyzing coupling, or simplifying code architecture. - Prompt contains: /hickey, simple made easy, complect, decouple, compose.

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。

Volatility-based decomposition review. Trigger when: - Evaluating module boundaries against axes of change and business volatility. - Prompt contains: /lowy, volatility, axis of change, design decomposition, 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。

SOP for the architect-tier campaign workflow (/campaign): exhaustive survey, mitigation planning, tiered orchestration, and reconciliation. Trigger when: - Running a multi-workstream initiative where an expensive architect-tier council surveys, plans, emits worker prompts, and judges landed work. - Conducting production-readiness assessments that fan out into autonomous mitigation dispatches across model tiers. - Prompt contains: /campaign, campaign workflow, survey, orchestrate, reconcile, premise freshness, tier routing, worker IBC, scratch.

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。

Discipline for repairing a false claim once it has propagated: select what depends on it, produce a replacement, and accept with an expiring verdict. Trigger when: - A claim, citation, premise, or documented fact is found wrong and its downstream consequences must be traced and fixed. - A refutation, a failed re-run, a retracted external source, or a human correction lands against something already closed or already promoted. - Prompt contains: /remediation, remediation, retraction, false claim, propagated error, scrub, correction propagation, born-false, became-false, currency verdict, impeachment queue.

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。

Structured Domain Modeling Architecture (SDMA) principles. Trigger when: - Designing domain models, building ologs (ontological graphs), verifying protocol equivalence, selecting schemas, or measuring architectural entropy. - Modeling structures using Category Theory, Coalgebra, or Information Theory. - Prompt contains keywords: sdma, olog, Category Theory, Coalgebra, Information Theory, entropy, schema, pullback, functor, monad.

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。

Formatting, structure, and execution rules for Quarto markdown documents. Trigger when: - Writing, editing, or rendering Quarto documents, reports, presentations, or websites. - Files matching the pattern **/*.qmd are in the workspace or referenced. - Tasks involve: quarto render, quarto preview, knitr, jupyter. - Prompt contains keywords: quarto, qmd, yaml header, code chunk, callout, cross-reference.

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。

Project-orientation workflow (/orient): installs predicate's enforcement into a target project, maps its structure and goal, and authors the persistent conditioning layer (AGENTS.md goal-hierarchy) so every subsequent walk is anchored and gated. Trigger when: - Onboarding a new project into predicate for the first time. - Refreshing an existing project's AGENTS.md hierarchy against the current state of the repository (re-run = refresh). - Prompt contains: /orient, orient workflow, onboard project, project orientation, AGENTS.md hierarchy, persistent conditioning layer.

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。

Removing signs of AI-generated patterns from text. Trigger when: - Refining documentation, comments, or summaries to sound natural and clear. - Prompt contains: /humanizer, humanize, text cleanup, edit style.

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。

Mathematical foundations, logical structures, and formal verification guidance. Trigger when: - Designing protocol contracts, formal specifications, verifying state spaces, or using proof assistants. - Tasks involve: TLA+, Alloy, Lean, Coq, model checkers, invariants, temporal logic. - Prompt contains keywords: formal verification, alloy, tla+, lean, coq, invariant, state machine, model checker, liveness, safety.

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。

Rules, conventions, and constraints for formatting git commit messages and committing at logical boundaries. Trigger when: - Drafting, revising, or validating git commit messages. - Pausing at commit boundaries under the CORE or CONTINUE workflows. - Evaluating whether a changeset should be split into multiple commits. - Prompt contains keywords: commit message, git commit, conventional commits, commit hygiene, commit guidelines, logical boundary, spaghetti diff, atomic commit, commit 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。

SOP for normative specification and behavioral contracts. Trigger when: - Defining invariants, permitted transitions, and forbidden states. - Navigating steps: Identify, Formalize, Verify, Record, Connect. - Prompt contains: /spec, spec workflow, normative constraint, invariant, BCP 14.

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。

SOP for the micro-execution C.O.R.E. phase. Trigger when: - Implementing plan steps, managing code changes at commit boundaries, and verifying incremental progress. - Navigating states: Absorb, Clarify, Plan, Execute. - Prompt contains: /core, core workflow, absorb, clarify, execution invariants, commit boundary, verify assertion.

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。

SOP for formal mathematical domain modeling. Trigger when: - Creating new formal models or applying mathematical lenses to analyze existing specifications. - Navigating phases: Identify, Select, Construct, Validate, Record, Connect. - Prompt contains: /form, form workflow, categorical, coalgebraic, linear logic, information-theoretic, validation.

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。

System reference for the crouton layout engine (@fyit/crouton-layout) — the LayoutTree/layout_configs data model, the croutonLayoutBlocks registry and sizing contract, the viability metric, the deterministic placer (#709), and how layouts persist and seed. Use when reasoning about WHY a layout renders/composes/persists the way it does, when a question is shaped like "what is a LayoutTree / where do layouts live / why did the placer pick this arrangement / why won't this pane shrink / where does minWidth get read", or when a generated POC boots with the wrong (or no) default layout. Trigger phrases: "layout tree", "layout_configs", "viability check", "composeDefaultLayout", "block sizing contract", "why is my layout not viable". For authoring a block component, use the block-authoring skill 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。

At the close of an epic (or a difficult issue), post a postmortem roundup comment — what went well, what was hard (backed by evidence), and 1–3 concrete proposals to improve the skills/flows — then offer to turn accepted proposals into their own `workflow`-labeled tasks, and end with a `🔭 Next` handoff (a paste-ready next-session prompt + the next epic to start). Use at epic close, after the "verify the whole thing" rollup, or when asked to "do a retro", "postmortem this epic", "what did we learn", "how do we improve the workflow".

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。

Render a crouton collection schema (the field-definition JSON) into a human-readable field table + relationships sketch (HTML + PNG + a terse Markdown table), so a human can sign off on the DATA MODEL before any code is generated. Use when an agent drafts or changes a collection schema (before `crouton config` / `generate_collection`), or when asked to "review a schema", "show the data model", "check these fields".

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。

FOUNDATIONAL SKILL - Analyze every prompt for underlying motivation using Golden Circle (WHY->HOW->WHAT). Runs BEFORE any other skill. No action without understanding WHY.

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。

Data Scientist role within the AID methodology. Activate when working on: EDA, feasibility assessment, experiment planning, ML architecture, model development & validation, or production deployment & monitoring. Stack-agnostic — ask the user for their stack at the start of any new project.

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。