mirror of https://git.openapi.site/https://github.com/desirecore/market.git synced 2026-07-23 05:23:40 +08:00

Files

Yige 74be106952 fix(skills): 补回 #56 压缩时误删的实质信息（意图对齐） (#57 )

## 摘要 / Summary

### 中文

#56 的复盘修正。上一轮"强改写压缩"把四技能 L1
的**技术属性、使用场景与交互示范当套话一刀切**，造成实质信息丢失（承诺"意图全保留"但未做到）。本 PR 补回：

- **create**：`创建仓库符合 AgentFS v2 规范、git
管理版本（可治理/可追溯）`定位；`基础创建`形态（name+description，description 自动填充 persona
L0）；需求收集的**引导问题示例**（"起什么名字？/主要负责什么？"…）；企业部署/开发者原型使用场景。
- **update**：`agent 目录 git 管理版本、历史可追溯`定位 + 使用场景。
- **discover**：使用场景（浏览/新用户/找替代）+ `语义匹配而非关键词搜索`。
- **delete**：使用场景（清理/测试/释放存储）。

根因：L1 混着实质技术属性与营销套话、使用场景是触发判据、引导问题是交互示范，不该按"只留独有信息"一刀切。补回后仍保留结构性压缩（zh
正文合计仍降 ~64%）。版本 create 2.5.2 / update 3.1.3 / delete 2.5.2 / discover
2.6.2，manifest 1.2.13，中英双份同步、重算 source_hash（validate-i18n 通过）。

### English

Post-mortem fix for #56. The previous aggressive compression treated the
skills' L1 technical attributes, use cases, and interaction demos as
boilerplate and cut them in a blanket way, dropping substantive
information (the "all intent preserved" claim wasn't fully met). This PR
restores: create's AgentFS-v2 / git-version-management positioning, the
"basic create" form (name+description auto-filling persona L0), the
requirement-gathering prompt questions, and enterprise/developer use
cases; update's git-versioned/traceable positioning and use cases;
discover's use cases and "semantic match, not keyword search"; delete's
use cases. Root cause: L1 mixed real technical attributes with marketing
boilerplate, use cases are trigger cues, and prompt questions are
interaction demos — none should have been blanket-cut. Structural
compression is retained (zh bodies still ~64% smaller). Versions bumped,
manifest 1.2.13, both locales synced, source hashes recomputed
(validate-i18n passes).

2026-07-19 16:14:22 +08:00

6.3 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). 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 at most 5 candidates.

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.

6.3 KiB Raw Blame History Unescape Escape