AGENT SKILL

grill-with-docs

Interview a plan, record agreed terms and decisions, and return saved document links before questions. Tested with Gemma4 E4B at 16K context and 24 tool rounds.

License 许可
MIT
最近更新
2026-11-13
Stars
★ 677
Forks
73

01 前言 Front Matter

name
grill-with-docs
license
MIT
metadata
{ "source": "mattpocock/skills", "revision": "49dd158d1076134a641b33efb035946536778336" }
description
Interview a plan, record agreed terms and decisions, and return saved document links before questions. Tested with Gemma4 E4B at 16K context and 24 tool rounds.
compatibility
TensorSharp or TensorAgent; workspace file tools required for saved artifacts and code changes. Tested on Gemma4 E4B Q8_0 with 16384-token context and up to 24 tool rounds. E2B failed the earlier eight-round task; E2B at 24 rounds and other models are not validated.

02 资源文件 4

03 SKILL.md 正文

Save decisions and interview

When the user requests a glossary or decision document, save the already-agreed facts first. Immediately copy the exact Markdown artifact link from the successful file-tool result as the first line of your answer; then ask the unresolved frontier questions. A filename or a statement that the document was saved does not deliver it. Keep agreed facts separate from recommendations.

Plan interview

Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.

Work the tree in rounds. The frontier is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.

Format a round like so:

❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

➡️ <your recommended answer>

---

❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

➡️ <your recommended answer>

Word each question so "yes" accepts your recommended answer.

Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.

Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), use the available file tools to find it (delegate only if an agent tool is offered); don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The decisions are the user's: put each to them and wait.

The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.

As terminology and durable decisions are resolved, read skills_read with skill="grill-with-docs", path="domain-modeling.md". Use that guidance to maintain the glossary and ADRs in the session workspace.

Host capabilities

Use only tools offered in this conversation. Read supplied workspace files with read_file; create artifacts with write_file and edit existing files with apply_patch when offered. Do not invent a Skill tool. After creating any file, include its exact Markdown download link from the tool result in your answer, even when the rest of your answer asks the user a decision question. Never replace that link with a filename or a claim that the file exists. If a required file, workspace, executable, or tool is unavailable, explain the limitation and do not claim it ran. A user's already-agreed scope and test interface count as agreement; do not ask the same question again. Apply the workflow directly after reading it; keep progress narration brief.

04 同仓库更多 Skills

zhongkaifu
zhongkaifu/TensorSharp

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

前端开发
★ 677
zhongkaifu
zhongkaifu/TensorSharp

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

视觉设计
★ 677
zhongkaifu
zhongkaifu/TensorSharp

slack-gif-creator

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

邮件与沟通图像与多媒体
★ 677
zhongkaifu
zhongkaifu/TensorSharp

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

邮件与沟通
★ 677
zhongkaifu
zhongkaifu/TensorSharp

frontend-design

Design distinctive UI with intentional aesthetics and typography. Read the workflow first; save HTML with the offered file tool and return its download link.

设计师前端开发视觉设计
★ 677
zhongkaifu
zhongkaifu/TensorSharp

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

设计师文档处理视觉设计
★ 677