Stefan Teofanovic

Use when a project's conventions need to be written down or extended: starting a codebase from scratch, settling how one tier uses its framework, capturing a design decision that was just made, or turning unwritten patterns in an existing repo into rules. Produces or grows an AGENTS.md / CLAUDE.md. Any language or stack.

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 reviewing a pull request, branch or diff in any language, to produce the analysis a reviewer decides from: what changed, why, how the structure moved, what it can break, and the decisions only a human can make, at five altitudes from code primitives to delivery and intent. Not a bug hunt, and not framework-specific 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 the same remark keeps being made in a repository's pull request reviews, or when someone asks what the reviews keep catching and how to stop catching it. Groups the comment history into recurring findings and decides, for each, the rung that removes it: a design that makes it impossible, a lint or type rule, a test in CI, a convention, a fix to the skill that produced the code. Produces a report in aiview with a recommendation per finding, applied on a yes. Not for reviewing one pull request (pr-review) and not for writing a rule already decided (write-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。

Use before building or changing any screen (a new page, dialog, panel, or a visual rework), to design it first as a prototype in the project's own design language, which the skill extracts from the codebase and writes down once. Not for implementing the screen and not for reviewing its code.

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 about to ask the person a question, answer one of theirs, or explain something to them, about a screen, a region or a component of the interface: in an interview, a plan, a board, a review or plain chat. Also when the person says they do not see what is meant on a screen. Finds the screen's prototype and points the person's viewer at the components concerned, so the question or the answer is given in the prototype's own names with the thing lit in front of them. Not for designing or changing a prototype (design-prototype), and not for a question with no screen in it.

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 the person and the agent go over what was just delivered together, live: on execute-plan's recommendation at a plan's close, or whenever the person asks to walk or rework a delivery with the agent. Runs the project's verify skill with the person guiding it, judging and deciding, the agent proposing what to check. Not for the agent's quality pass alone (the project's verify 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。

Use when a project has no verifier for a focus (what is judged, through what) and an agent should from now on judge, alone, the product quality of what is delivered (done as specified, usable, finished): on request, or from the mandate questions of orchestrate-plan when the person says yes. Produces the project's `verify-<app>-<focus>` skill, proven by one quality pass. Not for a focus that has one (its verify skill adapts itself), running a pass (the project's verify skill), tests, code quality or 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 page is wanted to work on something with the person during development, fed the project's real data (comparing model answers, walking an agent call by call, measuring an output against its template), when such a workbench has to change, be reworked or its feed broke, or mid-session when turns went into aligning with the person on how to do a kind of work that recurs and real project data could show it. Produces the page in aiview, kind `workbench`, and the project's `workbench-<bench>` skill with its feed and operating steps. Not for designing a product screen (design-prototype) or verifying user stories (verification-skill-create).

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。