feature-priority-zh

feature-priority-zh is a skill for Claude Code, Codex from AgiWish/hermes-skills-zh. It costs 48 tokens per session (869 once invoked), scanned A, original, MIT.

A requirements-prioritisation assistant that ranks product ideas using methods such as RICE, MoSCoW, or ICE. These are frameworks for deciding what to build first.

In plain words
What is it for?
Use it to compare features, align product and engineering teams, and prepare a delivery roadmap.
Why use it?
It turns a crowded list of requests into a clearer order for planning. It also records the assumptions behind each ranking.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare features, align product and engineering teams, and prepare a delivery roadmap.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agiwish/hermes-skills-zh/feature-priority-zh
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 AgiWish/hermes-skills-zh --skill feature-priority-zh
Clone the repo
git clone --depth 1 https://github.com/AgiWish/hermes-skills-zh

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.

agentmods badge for feature-priority-zh

README.md
[![agentmods](https://agentmods.dev/badge/skills/agiwish/hermes-skills-zh/feature-priority-zh/github.svg)](https://agentmods.dev/skills/agiwish/hermes-skills-zh/feature-priority-zh)
Your own site
<a href="https://agentmods.dev/skills/agiwish/hermes-skills-zh/feature-priority-zh"><img src="https://agentmods.dev/badge/skills/agiwish/hermes-skills-zh/feature-priority-zh/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.

agentmods 80×15 button for feature-priority-zh

Your own site · 80×15
<a href="https://agentmods.dev/skills/agiwish/hermes-skills-zh/feature-priority-zh"><img src="https://agentmods.dev/badge/skills/agiwish/hermes-skills-zh/feature-priority-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 869 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00869
Opus 5 $0.00024 $0.00434
Sonnet 5 $0.00010 $0.00174
Haiku 4.5 $0.00005 $0.00087

Measured 11d ago against content hash a7d636c534f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

feature-priority-zh 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 11d 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/feature-priority-zh/SKILL.md · 96 lines

What it actually says

功能优先级排序 (feature-priority-zh)

When to Use

  • "这些需求怎么排优先级"、"帮我评估一下哪个先做"
  • 需求池积压,需要客观框架决策
  • 和研发对齐排期前需要明确优先级
  • /feature-priority-zh [需求列表]

Quick Reference

/feature-priority-zh [需求描述列表]

可选参数:
  --method=RICE     # 用 RICE 评分(适合量化决策,默认)
  --method=MoSCoW   # 用 MoSCoW 分类(适合快速分层)
  --method=ICE      # 用 ICE 评分(Impact / Confidence / Ease)
  --context=[背景]  # 提供业务目标,帮助校准权重

Procedure

  1. 了解背景(如未提供,追问)

    • 当前最重要的业务目标是什么?
    • 团队规模和研发资源?
    • 有没有硬性截止时间或里程碑?
  2. RICE 评分输出

## 功能优先级矩阵(RICE)

**业务目标**:[本期最重要的目标]
**评分说明**:R=Reach(影响用户数) I=Impact(影响程度1-5) C=Confidence(置信度%) E=Effort(人周)

| 功能 | R | I | C | E | RICE分 | 优先级 | 备注 |
|------|---|---|---|---|--------|--------|------|
| [功能A] | 5000 | 4 | 80% | 2 | 8000 | 🔴 P0 | [理由] |
| [功能B] | 2000 | 3 | 60% | 1 | 3600 | 🟡 P1 | |
| [功能C] | 500  | 5 | 40% | 4 | 250  | 🟢 P2 | |

RICE 分 = R × I × C ÷ E

**建议排期**:
- P0(本期必做):功能A
- P1(本期尽量):功能B
- P2(下期规划):功能C

**需要讨论的假设**:
- [影响评分的关键不确定因素]
  1. MoSCoW 分类输出(--method=MoSCoW)
## MoSCoW 优先级分类

**Must Have(必须有,否则产品无法发布)**
- [功能]:[原因]

**Should Have(应该有,重要但可以延后)**
- [功能]:[原因]

**Could Have(可以有,时间允许则做)**
- [功能]:[原因]

**Won't Have(本期不做)**
- [功能]:[原因,何时重新评估]

Pitfalls

  • RICE 分数只是辅助,不是答案——强依赖性需求要人工调整
  • Effort 估算要让研发确认,不要 PM 自己拍
  • 评分假设要透明,方便后续复盘

Verification

  • 评分维度有明确定义
  • 关键假设已列出(方便质疑和复盘)
  • 强依赖关系已在备注标注
  • 建议排期可以直接用于和研发对齐
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.

  1. 11d ago First seen · 96 lines · 48 tokens per session scan A a7d636c534f9

Subscribe to this mod's changes

feature-priority-zh is a skill published in the GitHub repository AgiWish/hermes-skills-zh (5 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 869 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

hermespace

Full Hermespace pocket workbench for Hermes Agent (v0.18+): concept, dual decode, workbench I/O, fabric skills+MEMORY, FOA desk, Pulse, viewport app-shell, Tailscale serve, pocket boundary, autonomy grid, Desktop plugin, ops boot/doctor/smoke. Use for hermespace, pocket, workbench, FOA, pulse, viewport, access…

PabloTheThinker/hermespace · 100 tokens

21-day-self-interview

A 21-night guided self-reflection routine in which an agent asks three questions each night, remembers the answers, and reflects on them at key points.

Forlives/21-day-self-interview · 68 tokens

awesome-literature-review

A Chinese-language workflow for writing narrative academic literature reviews, which summarize and assess existing research on a topic.

yzbbds520/awesome-literature-review · 312 tokens

persona-compass

Build personality models of colleagues, clients, friends, or family members and get AI-powered communication strategies. Use this skill whenever the user wants to: understand someone's personality, predict how someone will react, get advice on communicating with a difficult person, prepare for a tough conversation…

snowyowlmia/persona-compass · 172 tokens

ai-tips-tricks

An automated workflow for searching the web for practical AI tips, techniques, and workflows, then writing tutorial-style Chinese posts and sending them to Telegram.

0xMulight/human-social-copy · 53 tokens

pingpong

Spontaneous local leisure meetups via a shared agent board: publish, discover and match offers, then negotiate place & time agent-to-agent. ALWAYS use this skill when the user spontaneously wants to do something or says: "publish an offer", "I want to play table tennis / X", "fancy a ...", "who's free for ...", "find…

0xAaronx0/pingpong · 121 tokens