mirror of https://git.openapi.site/https://github.com/desirecore/market.git synced 2026-07-23 04:23:46 +08:00

Files

Yige b273a1008a docs(discover-agent): 使用场景补充"更换智能体"情形 (#40 )

给 discover-agent 的中文源补充一条使用场景。

同时这是 #39(pull_request_target 自动翻译流水线)的端到端验证 PR:中文源变更 → en-US 过期 → CI
应自动翻译并把 commit 推回本分支、发评论。

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: desirecore-bot <bot@desirecore.net>

2026-07-07 20:04:55 +08:00

12 KiB

Raw Blame History

name, description, version, type, risk_level, status, disable-model-invocation, tags, metadata, market

name

description

version

type

risk_level

status

disable-model-invocation

discover-agent Skill

L0: One-sentence summary

Match and recommend the most suitable Agent from the registered Agents based on the user’s needs.

L1: Overview and use cases

Capability description

discover-agent is a procedural Skill that gives DesireCore the ability to discover and recommend suitable Agents for users. By understanding the user’s needs, it performs multi-dimensional matching across the registered Agent list and shows a candidate list for the user to choose from.

Use cases

The user describes a need but does not know which Agent to ask for help
The user wants to browse the currently available Agents and their capabilities
The user needs to find the most suitable specialist assistant for a specific task
A new user is using the system for the first time and needs to know which Agents are available
The user is unhappy with the current Agent’s performance and wants a better alternative

Core value

Lower the barrier: Users do not need to remember each Agent’s name and capabilities
Precise matching: Intelligent recommendations based on semantic needs, not simple keyword search
Smooth handoff: If no match is found, automatically suggest creating a new Agent (handoff to the create-agent Skill)

L2: Detailed specification

Execution flow

┌──────────────┐     ┌──────────────┐     ┌──────────────┐
│   需求理解    │ ──→ │   Agent 检索  │ ──→ │   匹配评分    │
└──────────────┘     └──────────────┘     └──────────────┘
                                                  │
                                                  ↓
┌──────────────┐     ┌──────────────┐     ┌──────────────┐
│   引导选择    │ ←── │   结果展示    │ ←── │   候选排序    │
└──────────────┘     └──────────────┘     └──────────────┘

Stage 1: Needs understanding

Trigger conditions (any one of the following):

The user says "帮我找一个...", "有没有...", or "谁能帮我..."
The user describes a task but does not specify a particular Agent
The user says "有哪些智能体" or "看看都有谁"
The system detects that the user’s need does not match the current Agent’s capabilities

Need parsing:

Extract the following dimensions from the user’s description:

Dimension	Description	Example
`domain`	Professional domain	law, finance, technology, education
`task_type`	Task type	consultation, review, analysis, creation
`keywords`	Keywords	contract, report, code, paper
`urgency`	Urgency	routine / urgent

Stage 2: Agent retrieval

Data source: Call GET /api/agents to get the list of all registered Agents.

API call:

GET /api/agents

Key fields in the returned data:

id — unique Agent identifier
name — Agent name
description — Agent description
skills — Skill list
status — current status (online/offline/busy)

Filtering rules:

By default, only show Agents with status: online or status: offline
Exclude internal system Agents (such as DesireCore itself, unless explicitly requested by the user)

Stage 3: Matching evaluation

Evaluate the match score based on the following dimensions (using LLM semantic understanding, not formula-based calculation):

Dimension	Description
Description relevance	Semantic relevance between the Agent’s description / persona and the user’s need
Skill match	Correlation between the Agent’s skills and the task type
Domain fit	Degree of fit between the Agent’s professional domain and the user’s domain
Status availability	The Agent’s current status (online takes priority over offline)

Display rules:

High match (clearly suitable for the task) → mark as "推荐"
Partial match (may be helpful) → mark as "可能相关"
No obvious relevance → do not display

Stage 4: Candidate ranking

Ranking rules:

Sort by overall score in descending order
If scores are tied, prefer online status
Show at most 5 candidates

Stage 5: Result display

When there are matching results:

Based on your needs, I recommend the following Agents:

┌─────────────────────────────────────────────────────┐
│ 1. 法律顾问助手                          匹配度: 92% │
│    专注合同审查和法律风险评估                          │
│    技能：合同审查、风险评估、法律研究                   │
│    状态：在线                                        │
├─────────────────────────────────────────────────────┤
│ 2. AI 文书助手                           匹配度: 71% │
│    专业文书撰写和格式优化                              │
│    技能：文书撰写、格式排版、合规检查                   │
│    状态：在线                                        │
├─────────────────────────────────────────────────────┤
│ 3. 数据分析师                            匹配度: 45% │
│    数据分析和可视化报告                                │
│    技能：数据分析、报表生成、趋势预测                   │
│    状态：离线                                        │
└─────────────────────────────────────────────────────┘

Please choose an Agent, or tell me more specific requirements.

When there are no matching results:

No fully matching Agent was found for your needs at the moment.

You can:
1. Try again with a more specific description
2. Create a new specialist Agent (I can help you)
3. Browse all available Agents

What would you like to do?

Browse mode (when the user asks to view all):

Currently available Agents:

Online:
  - 法律顾问助手 — 合同审查和法律风险评估
  - AI 文书助手 — 专业文书撰写和格式优化

Offline:
  - 数据分析师 — 数据分析和可视化报告
  - 翻译助手 — 多语言翻译和本地化

A total of 4 Agents. Do you need detailed information about any one Agent?

Stage 6: Guidance and selection

Actions after the user makes a choice:

User choice	Follow-up action
Chose an Agent	Switch to that Agent’s conversation and pass the user need context
Asked for more details	Call `GET /api/agents/:id` to get details, then show structured information (see below)
Unsatisfied with candidates	Guide the user to refine the need or suggest creating a new Agent
Chose "create a new one"	Call the create-agent Skill and pass the collected need information

Implementation of "learn more":

Call GET /api/agents/:id to get details, and optionally call the structured endpoint to get persona/rules:

# Get basic information
GET /api/agents/{agentId}
# Return: { id, name, description, skillsCount, toolsCount, status, config, persona, principles }

# Get structured persona (optional, used to show richer information)
GET /api/agents/{agentId}/persona
# Return: { L0, L1: { role, personality, communication_style }, L2 }

When presenting to the user, show key information in natural language/table format:

「法律顾问助手」详细信息

| 字段 | 内容 |
|------|------|
| Role positioning | 专注合同审查和法律风险评估 |
| Personality traits | 专业、严谨、审慎 |
| Skill count | 3 个 |
| Current status | 在线 |

Need to talk with this Agent?

Context handoff:

context_handoff:
  source_agent: desirecore
  target_agent: legal-assistant
  user_intent: '帮我审查这份合同的风险点'

Collaboration with other Skills

Collaboration Skill	Collaboration method
create-agent	When there is no match, suggest creating a new Agent and pass the user need as initial information
task-management	After a successful match, tasks can be created automatically and assigned to the target Agent

Error handling

Error scenario	Handling method
API call failure	Prompt a network error and suggest trying again later
Agent list is empty	Guide the user to create the first Agent
User description is too vague	Ask follow-up questions and provide domain options as guidance
Recommended Agent has an abnormal status	Mark the status and suggest choosing another online Agent

Permission requirements

Prefer using the Bash Tool to call curl and access the Agent Service HTTP API to complete operations
The API base address is injected into the system prompt’s "本机 API" section, so reference it directly
Read-only operation, no risk

Dependencies

Agent Service HTTP API (GET /api/agents)
The local API address declaration in the system prompt

12 KiB Raw Blame History Unescape Escape