fix(skills): 去除束缚 Agent 自主判断的机械数字策略 (#58)

## 摘要 / Summary

### 中文

去除技能里束缚执行 Agent 自主判断的**机械数字策略**:create 需求收集的「每轮最多问 2 个」、discover
排序的「最多展示 5 个候选」。改为交由 Agent 按情况自主把握追问节奏与展示数量,保留「别让用户负担 /
别一次刷屏」的原则意图——把控制权交还给判断力更强的执行者,而非用固定上限约束。create 2.5.3 / discover
2.6.3,manifest 1.2.14,中英双份同步、重算 source_hash(validate-i18n 通过)。

### English

Remove mechanical numeric limits that constrain the executing Agent's
judgment: create's "at most 2 questions per turn" and discover's "show
at most 5 candidates". Both become "the Agent decides the pacing/count
by situation", keeping the principle intent (don't burden the user /
don't flood the screen) while handing control back to the more capable
executor instead of a fixed cap. create 2.5.3 / discover 2.6.3, manifest
1.2.14, both locales synced, hashes recomputed (validate-i18n passes).
This commit is contained in:
2026-07-19 17:05:41 +08:00
committed by GitHub
parent 74be106952
commit 14b6a02c48
7 changed files with 19 additions and 11 deletions

View File

@@ -1,6 +1,6 @@
{
"name": "DesireCore Official Market",
"version": "1.2.13",
"version": "1.2.14",
"schemaVersion": "1.1.0",
"supportedLocales": ["zh-CN", "en-US"],
"defaultLocale": "en-US",

View File

@@ -1,5 +1,9 @@
# Changelog
## [2.5.3] - 2026-07-19
- 去除束缚执行 Agent 自主判断的机械数字策略create 追问'每轮最多 2 个'、discover'最多展示 5 个候选'),改为交由 Agent 按情况自主把握节奏与数量,保留'别让用户负担/别刷屏'的原则意图。
## [2.5.2] - 2026-07-19
- 复盘补回改写压缩时误删的实质信息create 的 AgentFS v2/git 版本管理定位、基础创建name+description 自动填充 persona L0、需求收集引导问题示例update/delete/discover 的使用场景与版本管理定位。功能对齐原始意图,仍保留结构性压缩。

View File

@@ -2,7 +2,7 @@
name: create-agent
description: >-
通过多轮对话收集需求,调用 ManageAgent 内置工具创建新的 AgentFS v2 智能体,支持自定义 persona 和 principles。Use when 用户要求创建新智能体、培养某领域助手、或快速基于模板生成可治理 Agent。
version: 2.5.2
version: 2.5.3
type: meta
risk_level: low
status: enabled
@@ -26,7 +26,7 @@ metadata:
description: >-
通过多轮对话收集需求,调用 ManageAgent 内置工具创建新的 AgentFS v2 智能体,支持自定义 persona 和 principles。Use when 用户要求创建新智能体、培养某领域助手、或快速基于模板生成可治理 Agent。
body: ./SKILL.zh-CN.md
source_hash: sha256:fa447cd4d5a5b336
source_hash: sha256:72090265f12a8da0
translated_by: human
en-US:
name: Create Agent
@@ -34,7 +34,7 @@ metadata:
description: >-
Collect requirements through multi-turn conversation and call the ManageAgent builtin tool to create a new AgentFS v2 Agent, with customizable persona and principles. Use when the user asks to create a new Agent, raise a domain assistant, or quickly produce a governable Agent from a template.
body: ./SKILL.md
source_hash: sha256:fa447cd4d5a5b336
source_hash: sha256:72090265f12a8da0
translated_by: ai:claude-fable-5
translated_at: '2026-07-19'
market:
@@ -82,7 +82,7 @@ Trigger (any): user explicitly says "create an Agent / make me an assistant"; de
- Required (parenthesized = example prompt question): `name` ("what to name it?"), `role` ("what does it mainly do?"), `target_users` ("who will use it?"), `domain` ("what expertise does it need?").
- Optional: `style` (communication tone), `boundaries` (red lines), `language` (default Chinese) — defaults derived from the domain template.
- Strategy: prefer inferring from the user's natural description; only ask for missing required fields; at most 2 questions per turn.
- Strategy: prefer inferring from the user's natural description; only ask for missing required fields; you decide how many to ask and the pacing — don't ask too many at once so as not to burden the user.
### Stage 3: Content Generation

View File

@@ -22,7 +22,7 @@
- 必填(括号内为引导问题示例):`name`"起什么名字?")、`role`"主要负责什么工作?")、`target_users`"谁会使用它?")、`domain`"需要哪些专业知识?")。
- 选填:`style`(沟通风格)、`boundaries`(禁区/红线)、`language`(默认中文)——缺省由领域模板决定。
- 策略:优先从用户自然描述推断,只追问未提及的必填项,每轮最多问 2 个
- 策略:优先从用户自然描述推断,只追问未提及的必填项;追问的数量与节奏由你自主把握,一次不要问太多以免用户负担
### 阶段 3内容生成

View File

@@ -1,5 +1,9 @@
# Changelog
## [2.6.3] - 2026-07-19
- 去除束缚执行 Agent 自主判断的机械数字策略create 追问'每轮最多 2 个'、discover'最多展示 5 个候选'),改为交由 Agent 按情况自主把握节奏与数量,保留'别让用户负担/别刷屏'的原则意图。
## [2.6.2] - 2026-07-19
- 复盘补回改写压缩时误删的实质信息create 的 AgentFS v2/git 版本管理定位、基础创建name+description 自动填充 persona L0、需求收集引导问题示例update/delete/discover 的使用场景与版本管理定位。功能对齐原始意图,仍保留结构性压缩。

View File

@@ -1,7 +1,7 @@
---
name: discover-agent
description: 根据用户需求推荐最匹配的智能体展示候选列表并引导选择。Use when 用户描述需求但不确定该找哪个智能体帮忙,或想浏览可用的智能体。
version: 2.6.2
version: 2.6.3
type: procedural
risk_level: low
status: enabled
@@ -24,7 +24,7 @@ metadata:
short_desc: 根据需求描述智能推荐最匹配的智能体,引导快速选择
description: 根据用户需求推荐最匹配的智能体展示候选列表并引导选择。Use when 用户描述需求但不确定该找哪个智能体帮忙,或想浏览可用的智能体。
body: ./SKILL.zh-CN.md
source_hash: sha256:0a1c7b0b1b60e399
source_hash: sha256:72159b331107dfb6
translated_by: human
en-US:
name: Discover Agent
@@ -32,7 +32,7 @@ metadata:
description: >-
Recommend the best-matching Agent based on the users needs, show a candidate list, and guide selection. Use when the user describes a need but is unsure which Agent to ask for help, or wants to browse available Agents.
body: ./SKILL.md
source_hash: sha256:0a1c7b0b1b60e399
source_hash: sha256:72159b331107dfb6
translated_by: ai:claude-fable-5
translated_at: '2026-07-19'
market:
@@ -84,7 +84,7 @@ Judge match with LLM semantic understanding (not a formula): relevance of descri
### Stage 4: Ranking
Descending by overall score; ties broken by online status; show at most 5 candidates.
Descending by overall score; ties broken by online status; show the most relevant few — you decide how many by relevance, avoiding flooding the screen.
### Stage 5: Presentation

View File

@@ -28,7 +28,7 @@
### 阶段 4排序
综合得分降序;同分 online 优先;最多展示 5 个候选
综合得分降序;同分 online 优先;展示最相关的若干个即可,数量由你按相关性自主把握,避免一次刷屏过多
### 阶段 5结果展示