admin
2ed7766007
一、用户令（逐字） 「humanizer（英文那份） 也要纳入」「重点就是做到说人话就行了」「但是 content_marketing_agent 的会话生成的文档并没有说人话，还是我手动要求的」 二、根因（两处，都不是"没整合"） · **语气那一档只有指针、没有注入** ⇒ 实测没被读到（`SKILL.md` 必读表标题原写「三篇」而表里有 4 行， 第 4 项＝作业规矩整包，被顶在"必读"之外；已订正为「四类」）。 · **写文档的执行会话那条链上一句写作口径都没有** —— 产品规划技能里「反 AI 味」只出现在**第③段界面** （且指的是界面不是文字），**第①段出文档那节零口径** ⇒ 产物自然是 AI 味。 三、改法 1. **每轮注入**（照排版那条现成机制，⛔ 不改 `main()`）： · `04-去AI味与说话方式.md` 顶部加 `<!-- VOICE-CORE -->` 紧凑块（≈450 字符：核心原则/四种高频 AI 味/交付前三问）； · `reply-style-guard.py` 里**原地重定义** `_core`（`_core_reply = _core` 后用新 `_core` 包住它并追加语气块） ⇒ 注入正文自动多一段，排版那条**不受影响**。 2. **产出侧补口径**：`product-planning` 第①段（stage-discovery）在 1b 表后新增「写作口径」块 —— 落笔前读 `humanizer-zh` 或本包 04，**定稿前过「交付前快速清单」**，并列出六种禁用 AI 味；**适用本段全部五份产出**。 3. **英文硬核版整包纳入**：原独立技能 `humanizer` **逐字**搬入本包 `references/humanizer-en/`（6 文件、 md5 逐个一致）：55 个模式 ＋ 5 种语气档 ＋ 0–100 AI 痕迹打分 ＋ `--file` 就地改； 在 `04 §9` 关系表与 `SKILL.md` 对应物段登记（冲突以本包会话场景版为先）。 四、验收 · 新增 `selftest.py::t_voice_core`（4 项）；全量 **PASS 106 / FAIL 0**；manifest 70 → **76** 份、语法失败 0。 · 端到端喂真钩子：注入正文已含说人话块、排版块仍在。 · ⛔ 改的是钩子与技能目录（宿主直读）⇒ **不需要分发/重启**。
2.9 KiB
2.9 KiB
Always-On Mode templates
Copy one of these blocks into your agent's standing instructions so it writes clean by default, not only when you run /humanizer. Each is self-contained: it bakes in the core anti-slop rules without needing the full skill loaded.
Pick the surface that matches your tool. The rules are identical; only the wrapper changes.
For CLAUDE.md or AGENTS.md (project or global)
## Writing rules (always on)
When you write prose (docs, comments, messages, commit bodies, PR descriptions):
- No em dashes. Use commas, colons, or hyphens.
- Vary sentence length. Follow a long sentence with a short one. Fragments are fine.
- Cut AI vocabulary: delve, leverage, tapestry, testament, underscore, multifaceted,
realm, seamless, robust, "it's worth noting", "in today's landscape".
- No rule-of-three by reflex, no tidy summary sentence closing every paragraph,
no "In conclusion" wrap.
- State facts, not their significance. Delete "this represents / underscores / highlights".
- Prefer active voice and a named actor over agentless passive.
- Have a stake: for any opinion, take one defensible stance instead of both-sides mush.
- Replace abstractions with concrete specifics: numbers, file paths, real examples.
For a SOUL.md or persona file
# Voice
I write like a specific person, not a committee. Short sentences next to long ones.
Concrete over abstract. I take positions and name what I disagree with. I skip the
throat-clearing openers ("There are several ways to...") and the neat conclusions.
No em dashes, no "delve", no "leverage", no rule-of-three on autopilot. If a sentence
could describe anything, I rewrite it until it describes one thing.
For a system prompt (API or custom assistant)
Write in a human voice. Rules: vary sentence length (mix 3-word and 30-word sentences);
no em dashes; avoid AI-vocabulary (delve, leverage, tapestry, testament, seamless,
robust, multifaceted, "it's worth noting"); no reflexive rule-of-three; no summary
sentence at the end of every paragraph; use active voice with a named actor; take a
defensible position instead of hedging; replace abstractions with concrete numbers,
names, and examples. Never rewrite text inside quotes or code blocks.
For ChatGPT Custom Instructions ("How would you like ChatGPT to respond?")
Write like a real person, not a chatbot. Vary sentence length a lot. No em dashes.
Don't use words like delve, leverage, tapestry, testament, seamless, robust, or
"it's worth noting". Don't group things in threes by habit. Don't end every paragraph
with a summary line. Take a clear position instead of listing pros and cons. Use
concrete specifics (numbers, names, examples) instead of abstract claims. Keep code
and quoted text exactly as written.
These templates cover the highest-signal rules only. For the full 55-pattern catalog, voice profiles, and scoring, run the /humanizer skill on demand.