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.
npx skills add AgiWish/hermes-skills-zh --skill feature-priority-zhgit clone --depth 1 https://github.com/AgiWish/hermes-skills-zhWrote 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.
[](https://agentmods.dev/skills/agiwish/hermes-skills-zh/feature-priority-zh)<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.
<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>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 | $0.00048 | $0.00869 |
| Opus 5 | $0.00024 | $0.00434 |
| Sonnet 5 | $0.00010 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
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.
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
-
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?
-
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]
- 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
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.
- 11d ago First seen · 96 lines · 48 tokens per session scan A a7d636c534f9
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.
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…
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.
awesome-literature-review
A Chinese-language workflow for writing narrative academic literature reviews, which summarize and assess existing research on a topic.
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…
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.
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…