同步 think-twice v3 修订

对应源仓 think-twice 的 d80e546。副本内容与源仓一致。

SKILL.md:blocker 五项改为显式有序;读者表格不再按"top-left cell"这类位置引用;
style.md 的加载条件(含 code-heavy 跳过那个例外)从 style.md 搬进 SKILL.md 正文。

style.md:删掉开头写给维护者的说明,只留用途和用法。
This commit is contained in:
2026-08-21 02:28:10 +08:00
parent 96450e2335
commit f0c4002c89
2 changed files with 13 additions and 14 deletions
+10 -7
View File
@@ -39,9 +39,9 @@ they can open right now. **Background** is what they already know.
| can open the code | exact locations, code, schema | the design one level up; code as an optional anchor | | can open the code | exact locations, code, schema | the design one level up; code as an optional anchor |
| cannot | conclusion and boundaries | consequences and comparisons | | cannot | conclusion and boundaries | consequences and comparisons |
The table is a default, not a verdict. A reader in the top-left cell who is The table is a default, not a verdict. A reader who can open the code and knows
optimising for speed may still want the design level and no code at all. When the domain may still be optimising for speed and want the design level with no
it is unclear, one direct question is faster than a guess. code at all. When it is unclear, one direct question is faster than a guess.
Pitch one level higher than feels natural and let them ask downward. Opening Pitch one level higher than feels natural and let them ask downward. Opening
with code or a schema is a choice that needs a reason: they asked for it, or with code or a schema is a choice that needs a reason: they asked for it, or
@@ -57,9 +57,10 @@ meaning for it.
### 1. Locate the blocker ### 1. Locate the blocker
Pick the highest one: **level** (pitched at the wrong altitude) | **concept** | The five blockers run from highest to lowest; pick the highest that applies.
**scope** | **steps** | **token** (undefined word or dangling pointer). Then **level** (pitched at the wrong altitude), **concept**, **scope**, **steps**,
name which conclusion, boundary, evidence and next step this text must carry. **token** (undefined word or dangling pointer). Then name which conclusion,
boundary, evidence and next step this text must carry.
**Done when:** one blocker is named and every load-bearing slot is listed. **Done when:** one blocker is named and every load-bearing slot is listed.
@@ -157,7 +158,9 @@ goes, and what to do next, wherever those questions matter.
### Chinese prose for a human reader ### Chinese prose for a human reader
Also load [style.md](style.md), the only conditional part of this skill. When the output is Chinese prose a person will read, and it is not code-heavy,
also load [style.md](style.md) and sweep its list before delivery. It is the
only conditional part of this skill.
## When the rewrite misses ## When the rewrite misses
+3 -7
View File
@@ -1,12 +1,8 @@
# Style — 中文表述 (optional part) # Style — 中文表述 (optional part)
Load only when the output is Chinese prose for a human reader; even then, skip A guardrail against model-flavoured prose. Every rule below names what to look
code-heavy text. This file is a guardrail against model-flavoured prose; when for and what to change it to. Before delivery, sweep the list once: each rule
model writing no longer needs it, delete the file and every pointer to it (grep passes, or the text changes until it does.
both skills for style.md) — neither core depends on it.
Every rule is countable. Before delivery, sweep the list once: each rule passes,
or the text changes until it does.
## 句子 ## 句子