A review tool for completed Tencent Meeting requirements or technical-plan meetings. It turns the meeting notes and transcript into a verdict, such as approved, conditionally approved, rejected, or lacking enough information.

Use it after a requirements or technical review meeting to identify objections, answers, blockers, conditions, and supporting quotes. It can also check whether the requested meeting changes were added to a PRD.

It provides evidence for the decision instead of relying on an informal summary. It also compares the meeting conclusions with a PRD, a document describing what a product should do, to find missing or conflicting requirements.

reviewcourt — Skill for Claude Code and Codex by Chris1Wang3

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 Chris1Wang3/Idea-on-Trial --skill reviewcourt

Clone the repo

git clone --depth 1 https://github.com/Chris1Wang3/Idea-on-Trial

Made for: Claude Code, Codex.

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/chris1wang3/idea-on-trial/reviewcourt/github.svg)](https://agentmods.dev/skills/chris1wang3/idea-on-trial/reviewcourt)

Your own site

<a href="https://agentmods.dev/skills/chris1wang3/idea-on-trial/reviewcourt"><img src="https://agentmods.dev/badge/skills/chris1wang3/idea-on-trial/reviewcourt/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/chris1wang3/idea-on-trial/reviewcourt"><img src="https://agentmods.dev/badge/skills/chris1wang3/idea-on-trial/reviewcourt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,773 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	$0.00150	$0.02773
Opus 5	$0.00075	$0.01386
Sonnet 5	$0.00030	$0.00555
Haiku 4.5	$0.00015	$0.00277

Measured 12d ago against content hash 1de82bbc5854, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reviewcourt 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 12d 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.

reviewcourt/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

需求评审庭 · ReviewCourt

EN Turn a completed Tencent Meeting review into an evidence-backed verdict.
中文把需求评审会转成有原话、有限定条件、可执行的评审建议。

When / 何时用： 会后需求裁决 · 阻塞项核对 · 会议与 PRD 双源审查
Not / 不用： 通用纪要 · 会前模拟 · 实时监听 · 员工评价 · 替团队拍板

把今天下午的支付改版需求评审结一下，告诉我能不能进入开发。
对照这份 PRD，检查昨晚评审会上要求修改的内容有没有漏。

可直接触发的说法

以下口语输入都应触发本技能：

把刚结束的需求评审结一下。
这场腾讯会议里的需求到底过没过？
找出研发、设计和测试提出的阻塞项及答复。
给每条评审结论附上会议原话。
把会议结论整理成进入开发前的条件清单。
对照这份 PRD，检查会上要求改的内容有没有写进去。
找出 PRD 与需求评审会之间的遗漏和冲突。

最小可用输入

场景 A｜会议单源裁决：会议号，或足以定位会议的主题 + 大致时间。

场景 B｜会议与 PRD 双源核对：场景 A 的输入 + 可读取的 PRD 文件、链接或正文。

可兼容输入：

用户只说“刚才那场”：在合理时间窗口查询已结束会议；多结果时让用户选择。
用户直接提供逐字稿：跳过 tmeet 数据获取，按同一证据规则评审并声明数据来源。
用户只提供 PRD：说明本技能需要会议证据；若用户想做会前预演，改用需求评审模拟类 Skill。
用户要求“直接判断”：仍不得跳过证据核验。

场景路由

有会议，无 PRD   → 场景 A：会议单源裁决
有会议，有 PRD   → 场景 B：会议与 PRD 双源核对
有逐字稿，无会议 → 降级执行场景 A，并标明“用户提供材料”
只有 PRD         → 不执行会后裁决；引导至会前评审或请用户补充会议

执行任一场景前，读取 references/review-playbook.md。场景 B 必须同时读取其中「F. 场景 B：会议与 PRD 双源核对」规则。

工作流

1) 检查运行环境与授权
2) 定位已结束会议
3) 获取智能纪要、逐段转写与参会信息
4) 建立证据链并按场景评审
5) 输出裁决单或信息不足说明

第一步：检查运行环境与授权

ReviewCourt 运行在支持 Skill 且能执行本地命令的 Agent 中，直接调用 tmeet CLI；不要求用户另外安装 tmeet-skill。

检查 tmeet 命令是否存在。
若不存在，说明缺少腾讯会议 CLI，并在用户确认后安装：
```
npm install -g @tencentcloud/tmeet@latest
```
执行 tmeet auth status 检查授权；禁止展示 AccessToken 或 RefreshToken。
未登录时，设置当前 Agent 与模型对应的 TMEET_AGENT、TMEET_MODEL，再按宿主支持的后台任务方式执行 tmeet auth login，完整展示授权 URL 并等待用户完成授权。
Agent 无法执行本地命令时，不假装已连接腾讯会议；请用户改为提供逐字稿或换到支持命令执行的 Agent。

不得静默安装、绕过 OAuth 或把登录凭证写入报告。

第二步：定位已结束会议

使用 ISO 8601 时间和用户所在时区查询：

tmeet meeting list-ended --start "<start>" --end "<end>" --compact

有会议号时优先按会议号核实详情。
只有主题或相对时间时，先缩小查询窗口，再按主题匹配。
返回多场合理候选时，展示主题、开始时间和 meeting_code，让用户选择；不得自行猜测。
meeting_id 只允许作为命令参数在内部传递，禁止向用户展示。
只处理已结束会议；发现会议仍在进行时，说明本技能不支持实时裁决。

第三步：获取会议证据

按官方链路读取数据，查询类命令优先使用 --compact：

tmeet meeting get --meeting-id "<meeting_id>" --compact
tmeet record list --meeting-id "<meeting_id>" --compact
tmeet record address --meeting-record-id "<meeting_record_id>" --compact
tmeet record smart-minutes --record-file-id "<record_file_id>" --compact
tmeet record transcript-paragraphs --record-file-id "<record_file_id>" --meeting-id "<meeting_id>" --compact
tmeet report participants --meeting-id "<meeting_id>" --compact

Read the full file on GitHub · 207 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 207 lines · 150 tokens per session scan A 1de82bbc5854

Subscribe to this mod's changes

reviewcourt is a skill published in the GitHub repository Chris1Wang3/Idea-on-Trial (4 stars, last pushed 24d ago), licensed MIT. It adds 150 tokens to every session and 2,773 once invoked, about $0.0007 per session on Opus 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 2026-08-31.

Project management agent-skills ai-skills clawhub competitive-analysis cursor openclaw

jira-bug-reporter

Create detailed bug reports from session evidence — auto-populate Jira tickets with session URLs, error messages, device info, and reproduction steps. Use when the user wants to file a bug from a Fullstory session.

reatlat/fullstory-claude-plugin · 48 tokens

asc-submission

Prepare an app for App Store submission or TestFlight distribution using the App Store Connect MCP server. Use when user says "prepare submission", "submit to app store", "prepare for review", "update metadata", "set what's new", "check submission readiness", "distribute to testflight", or wants to manage App Store…

markdavidgan/apple-dev-skills · 78 tokens

influencer-marketing-manager

Provides business judgment and management for influencer and creator partnerships. Use for goals, creator strategy, cross-stage decisions, SOPs, or automation. Also use for concise, stage-specific operator-tool guidance, even without tool execution, when operational evidence must support the next marketing decision.…

NoxInfluencer/skills · 86 tokens

reviewcourt