A requirements-clarification workflow written in Chinese for confirming new tasks and matching requested fields with existing database fields.

Use it to create a task confirmation document, review the request, identify field matches or gaps, and run the required validation gate.

It reduces misunderstandings before design or implementation, especially when a request must fit existing tables and naming rules.

grill-task — Skill for Claude Code by BlueprintOS/analysis-to-delivery

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add BlueprintOS/analysis-to-delivery --skill grill-task

Clone the repo

git clone --depth 1 https://github.com/BlueprintOS/analysis-to-delivery

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/grill-task/github.svg)](https://agentmods.dev/skills/blueprintos/analysis-to-delivery/grill-task)

Your own site

<a href="https://agentmods.dev/skills/blueprintos/analysis-to-delivery/grill-task"><img src="https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/grill-task/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/blueprintos/analysis-to-delivery/grill-task"><img src="https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/grill-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,338 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.01338
Opus 5.5	$0.00024	$0.00535
Sonnet 5.5	$0.00012	$0.00268
Haiku 4.5	$0.00006	$0.00134

Measured 1mo ago against content hash d9ed0e65ca2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

grill-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/user-invoked/grill-task/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill-Task — 需求澄清 + 字段对齐

Contract

输入: TASK_CONFIRM_*.md、paths/knowledge-path.md、用户需求笔记
输出: REVIEW_需求确认书.md、REVIEW_字段对齐分析.md
门控: python3 scripts/task-confirm-check.py --strict TASK_CONFIRM_*.md REVIEW_需求确认书.md REVIEW_字段对齐分析.md 通过;用户白名单话术签字
Required rules: stage-gate, no-field-guessing, context-pointer, goal-boundary
Required paths: knowledge-path, doc-naming-path
下一步: /to-brd

适用场景

用户提出新需求时
需求涉及现有表查询/维护类功能
团队对需求理解不一致时

流程步骤

1. 生成《需求确认表》

加载 templates/TASK_CONFIRM.md
替换项目名、日期,生成 TASK_CONFIRM_{项目名}.md 到工作目录
告知用户填写并保存

2. 用户填写后,生成《需求确认书》

读取用户填写的 TASK_CONFIRM_*.md
加载 templates/REVIEW_需求确认书.md
逐项标注 AI 助手的理解,列出待确认的设计假设
输出 REVIEW_需求确认书.md

3. 字段对齐分析(涉及现有表时强制)

提取需求中提到的所有表名和字段名
与 knowledge-path.md 引用的知识库核对
输出 REVIEW_字段对齐分析.md,分类标注:
- ✅ 已对齐
- ⚠️ 需 JOIN
- ❓ 待确认(业务同义不同名)
- 🔴 缺失

4. 阶段 2 出口门控(唯一脚本)

跑 python3 scripts/task-confirm-check.py --strict TASK_CONFIRM_*.md REVIEW_需求确认书.md REVIEW_字段对齐分析.md
task-confirm-check.py 是阶段 2 唯一门控脚本
field-alignment-check.py 不接 TASK_CONFIRM / REVIEW 文档,不得用于阶段 2 出口门控

关键纪律

用户填写完 TASK_CONFIRM 后,严禁直接跳进设计
必须先出确认书让用户审阅
用户确认通过 → 进入 /to-brd
字段对齐有 🔴 或 ❓ → task-confirm-check.py --strict 必须失败,严禁进入下一步

调用的 rule

rules/no-field-guessing — 严禁猜测字段名
rules/no-self-invent — 严禁自创字段
rules/context-pointer — 三层知识库加载

关键纪律（2026-06-24 更新）

❌ 删除"4 章节"表述——实际为 5 章节（一~五）
阶段 2 只允许 scripts/task-confirm-check.py 作为出口门控脚本
field-alignment-check.py 只校验 PRD/FSD/设计文档字段引用,不接 TASK_CONFIRM / REVIEW
🟡 删除：状态字段不再有 🟡 中间态，仅 ⬜/✅ 二态
🔒 HARD GATE：用户必须用白名单话术之一明确签字，LLM 不接受隐式同意

结束条件

TASK_CONFIRM 状态字段 = ✅ 已确认（二态，无 🟡）
TASK_CONFIRM 5 个必备章节（一~五）填完
TASK_CONFIRM 无 12 词 TBD（见 scripts/task-confirm-check.py TBD_KEYWORDS）
REVIEW_需求确认书第八节"待明确事项"为空
REVIEW_字段对齐分析对齐结论表中 ❓=0 且 🔴=0（⚠️ 可保留，状态字段可为 ✅ 或 ⚠️）
python3 scripts/task-confirm-check.py --strict TASK_CONFIRM_*.md REVIEW_需求确认书.md REVIEW_字段对齐分析.md exit 0
用户白名单话术签字（详见 templates/TASK_CONFIRM.md L48-55）

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 97 lines · 60 tokens per session scan A d9ed0e65ca2d

Subscribe to this mod's changes

grill-task is a skill published in the GitHub repository BlueprintOS/analysis-to-delivery (26 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 1,338 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Databases Planning anthropic claude-skills documentation-tool hermes prd

elasticsearch-best-practices

Elasticsearch development best practices for indexing, querying, and search optimization.

Mindrally/skills · 20 tokens

kysely

Guidelines for developing with Kysely, a type-safe TypeScript SQL query builder with autocompletion support.

Mindrally/skills · 26 tokens

pyspark-etl

Best practices for building performant, testable PySpark ETL pipelines with Spark SQL and Apache Iceberg. Use when writing or reviewing PySpark jobs, designing joins and window functions, working with map/array higher-order functions, or building idempotent cumulative/snapshot table merges.

Mindrally/skills · 62 tokens

grill-task