mirror of https://git.openapi.site/https://github.com/desirecore/market.git synced 2026-09-05 22:24:06 +08:00

Files

Yige 22b128f185 feat(skills): 独立维护智能体生命周期操作说明 (#90 )

## 中文

### 变更
- 新增 `clone-agent` 内置 Skill，覆盖私有数据复制和团队分发边界
- 将 Smart routing、reasoning、头像和确认流程迁入 action-specific Skills
- 修正 `update-agent` 与当前 ManageAgent 白名单的漂移
- 保持所有市场 Skill 按需加载，并加入 builtin 清单

### 验证
- `uv run --quiet scripts/i18n/test_validate_i18n.py`
- `uv run --quiet scripts/i18n/validate-i18n.py`
- `uv run --quiet scripts/i18n/translate.py --check`
- 公共信息边界检查通过

## English

### Changes
- Add the built-in `clone-agent` Skill for private-data copy and
team-distribution boundaries
- Move Smart routing, reasoning, avatar, and confirmation workflows into
action-specific Skills
- Align `update-agent` with the current ManageAgent configuration
whitelist
- Keep every marketplace Skill on-demand and add the new Skill to the
built-in manifest

### Verification
- `uv run --quiet scripts/i18n/test_validate_i18n.py`
- `uv run --quiet scripts/i18n/validate-i18n.py`
- `uv run --quiet scripts/i18n/translate.py --check`
- Public information boundary review passed

2026-08-25 16:13:09 +08:00

6.5 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 among registered Agents based on the user's need description.

L1: Overview

Procedural skill: understand the need → retrieve with ManageAgent(action='list') → semantic match scoring → rank and present → guide selection; on no match, hand off to create-agent automatically. Applies when the user doesn't know which Agent to pick, wants to browse available Agents, is a new user getting oriented, or is unhappy with the current Agent and wants an alternative. Its value is what the tool can't give: semantic need matching (not keyword search), candidate ranking and presentation, and the create hand-off on no match. list / get are read-only, approval-free.

L2: Detailed Spec

Flow: need understanding → retrieval → match evaluation → ranking → presentation → guided selection.

Stage 1: Need Understanding

Trigger (any): user says "find me a… / is there a… / who can help me…", describes a task without naming an Agent, "which Agents are there", or the system detects a need that mismatches the current Agent. Extract dimensions from the description: domain (legal/finance/tech/education), task_type (consult/review/analyze/create), keywords (contract/report/code/paper…), urgency (routine/urgent).

Stage 2: Retrieval

ManageAgent(action='list') fetches all registered Agents (returns a compact list with name / id / status / description). list/get are read-only ManageAgent operations and can be called directly; they do not require loading create, update, clone, or delete skills first. Filtering: by default show non-offline Agents; offline ones appear only as a fallback when there's no better candidate; exclude internal system Agents (e.g. DesireCore itself) unless the user explicitly asks.

Stage 3: Match Evaluation

Judge match with LLM semantic understanding (not a formula): relevance of description / persona to the need, association of skills to the task type, domain fit, status availability (online preferred). Presentation tiers: strong match → mark "recommended", partial → "possibly relevant", no clear relation → don't show.

Stage 4: Ranking

Descending by overall score; ties broken by online status; show the most relevant ones — you decide how many by relevance.

Stage 5: Presentation

With matches: list candidates, each with name, description, key skills, status, and match score; ask the user to choose or refine the need. E.g. "1. Legal Advisor (92%) — contract review and legal risk assessment; skills: contract review / risk assessment / legal research; online".
No match: report that none were found and offer three options — retry with a more specific description / create a new specialized Agent (hand off to create-agent) / browse all.
Browse mode (user wants to see all): list name + description grouped by online / offline, and ask whether to view details of any.

Stage 6: Guided Selection

Chose an Agent → switch to that Agent's conversation, passing the user's need context (source / target / user_intent).
Wants more detail → ManageAgent(action='get', id) for details (name / description / status / version / skill count / tool count / Git status); present the key info in natural language or a table and ask whether to chat.
Unhappy with candidates → guide the user to refine the need or suggest creating a new Agent.
Chose "create new" → invoke the create-agent skill, passing the gathered requirements.

Collaboration and Error Handling

Collaboration: on no match, hand off to create-agent (pass the need as initial info); on a successful match, optionally create a task and assign it to the target Agent.
Errors: tool call fails → report error and suggest retry; empty Agent list → guide the user to create the first Agent; overly vague need → ask follow-ups and offer domain options; get returns "Agent not found: " → fall back to list to reconfirm available Agents; recommended Agent in an abnormal state → mark the status and suggest picking an online one.
list / get are read-only, approval-free, and risk-free; always done via ManageAgent.

6.5 KiB Raw Blame History Unescape Escape