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 feedback-polish-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/feedback-polish-zh)<a href="https://agentmods.dev/skills/agiwish/hermes-skills-zh/feedback-polish-zh"><img src="https://agentmods.dev/badge/skills/agiwish/hermes-skills-zh/feedback-polish-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/feedback-polish-zh"><img src="https://agentmods.dev/badge/skills/agiwish/hermes-skills-zh/feedback-polish-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 | $0.00041 | $0.00800 |
| Opus 5 | $0.00020 | $0.00400 |
| Sonnet 5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
feedback-polish-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 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.
What it actually says
职场反馈润色 (feedback-polish-zh)
When to Use
- "这句话太直接了，帮我改一下"
- "我想说 XX 但不知道怎么说不伤人"
- 绩效反馈、代码 Review 评论、邮件回复需要更专业的表达
/feedback-polish-zh [你想说的话]
Quick Reference
/feedback-polish-zh [原始表述]
可选参数：
--tone=建设性 # 保留批评，改为建设性表达（默认）
--tone=委婉 # 大幅软化，适合敏感场景
--tone=直接 # 保持直接但去除攻击性
--context=绩效 # 绩效评估场景
--context=codereview # 代码审查场景
--context=邮件 # 邮件回复场景
Procedure
-
理解原始意图
- 核心反馈是什么？（事实 / 行为 / 影响）
- 目的是什么？（帮对方改进 / 拒绝 / 表达不满）
- 关系背景？（平级 / 上下级 / 跨部门）
-
改写原则（SBI 框架）
- Situation（情境）：在什么具体情况下
- Behavior（行为）：观察到的具体行为
- Impact（影响）：这个行为带来的影响
-
输出对比格式
**原始表述**：
[引用原文]
**问题诊断**：
- [为什么这样说有问题：太情绪化 / 攻击性 / 模糊 / 失焦]
**润色后**：
[改写版本]
**改动说明**：
- [改动点1]：把"[原话]"改为"[新表述]"，因为 [原因]
- [改动点2]：...
**可选的更[委婉/直接]版本**：
[备选表述]
常见场景示例
代码 Review
- 原始：「这代码写的什么玩意，完全不可读」
- 润色：「这块逻辑比较复杂，可以考虑提取方法名或加注释，方便后续维护。」
绩效反馈
- 原始：「他总是拖延，影响团队」
- 润色：「在 [具体项目] 中，任务交付时间多次超出约定节点，影响了下游环节的推进，建议在时间管理上重点关注。」
Pitfalls
- 不要把实质性批评全部删掉，润色不是掩盖问题
- 保留事实性描述，只软化情绪表达
- 不要生成空洞的"积极语言"代替真实反馈
Verification
- 改写后核心意思没有丢失
- 去除了情绪化和攻击性词汇
- 包含具体行为描述，不是泛化评价
- 对方看了能知道需要做什么改变
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 · 90 lines · 41 tokens per session scan A 200b15ec3a75
feedback-polish-zh is a skill published in the GitHub repository AgiWish/hermes-skills-zh (5 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 800 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…