gate-info-defianalysis

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

gate-info-defianalysis

General Rules

通用规则

⚠️ STOP — You MUST read and strictly follow the shared runtime rules before proceeding. Do NOT select or call any tool until all rules are read. These rules have the highest priority. → Read gate-runtime-rules.md → Also read info-news-runtime-rules.md for gate-info / gate-news-specific rules (tool degradation, report standards, security, routing degradation, per-skill version checks when

scripts/

is present, and legacy wrapper routing).

Only call MCP tools explicitly listed in this skill. Tools not documented here must NOT be called, even if they exist in the MCP server.
Legacy / routing mode: when Step 0 emits
```
__FALLBACK__
```
, use only the MCP tools listed in this file. When Step 0 emits
```
__ROUTE_CLI__
```
, do not call those MCP tools; delegate to the mapped primary skill per Step 0.

The DeFi Ecosystem Analysis Skill. Routes to different sub-scenarios based on user intent (overview / single platform / yield / stablecoins / bridges / reserves / liquidation), each calling one or more MCP tools.

Trigger Scenarios: User asks about DeFi protocols, TVL, yield rates, stablecoins, cross-chain bridges, exchange reserves, liquidation distribution, etc.

Per-skill updates: This directory includes

scripts/update-skill.sh

and may include

scripts/update-skill.ps1

. ClawHub packages uploaded to the marketplace often omit

update-skill.ps1

(upload-page restriction); GitHub / Bitbucket source trees keep both. Policy: info-news-runtime-rules.md §1. The Trigger update steps below apply in addition to gate-runtime-rules.md; when scripts are present, use this flow for version checks before execution.

Update check — user visibility: Technical failures during version check (missing script, sandbox, network, non-zero exit, no parseable

Result=

line) must not be explained to the user; continue with Execution per info-news-runtime-rules.md. Only successful

check

apply

outcomes may be summarized (including update_available
/ strict exit 3, which is still a success path that requires user confirmation before

apply

). Do not auto-download

update-skill.*

from the network. Static reference if

.ps1

is missing: canonical scripts live in gate/gate-skills under

skills/<name>/scripts/

(same

<name>

as frontmatter).

⚠️ 停止 — 你必须先阅读并严格遵守共享的运行时规则，然后再继续。在阅读完所有规则之前，请勿选择或调用任何工具。这些规则具有最高优先级。 → 阅读gate-runtime-rules.md → 同时阅读info-news-runtime-rules.md以了解gate-info / gate-news专属规则（工具降级、报告标准、安全、路由降级、当存在

scripts/

时的逐技能版本检查，以及旧版包装器路由）。

仅调用本技能中明确列出的MCP工具。即使MCP服务器中存在未在此处记录的工具，也不得调用。
旧版/路由模式：当步骤0输出
```
__FALLBACK__
```
时，仅使用本文件中列出的MCP工具。当步骤0输出
```
__ROUTE_CLI__
```
时，请勿调用这些MCP工具；根据步骤0将请求委托给映射的主技能。

DeFi生态系统分析Skill。根据用户意图（概览/单一平台/收益率/稳定币/跨链桥/储备/清算）路由至不同子场景，每个子场景调用一个或多个MCP工具。

触发场景：用户询问DeFi协议、TVL、收益率、稳定币、跨链桥、交易所储备、清算分布等相关内容。

逐技能更新：本目录包含

scripts/update-skill.sh

，可能还包含

scripts/update-skill.ps1

。上传至市场的ClawHub包通常会省略

update-skill.ps1

（受上传页面限制）；GitHub / Bitbucket源码树会保留这两个文件。相关政策：info-news-runtime-rules.md §1。以下触发更新步骤是对gate-runtime-rules.md的补充；当存在脚本时，在执行前需使用此流程进行版本检查。

更新检查 — 用户可见性：版本检查期间的技术故障（缺失脚本、沙箱问题、网络问题、非零退出码、无可解析的

Result=

行）不得向用户解释；需根据info-news-runtime-rules.md继续执行。仅成功的

check

apply

结果可进行汇总（包括**

update_available

** / 严格的退出码3，这仍属于需要用户确认后才能执行

apply

的成功路径）。请勿从网络自动下载

update-skill.*

。静态参考：若缺失

.ps1

文件，标准脚本位于gate/gate-skills的

skills/<name>/scripts/

目录下（

<name>

与前置元数据中的名称一致）。

Step 0 — Wrapper routing probe

步骤0 — 包装器路由探测

This legacy skill is a compatibility alias for the primary CLI skill

gate-info-web3

Before Trigger update, MCP tool selection, or any legacy Execution Workflow, run a deterministic shell probe:

bash

PRIMARY_SKILL="gate-info-web3"
HAS_PRIMARY=0
for root in \
  "$HOME/.cursor/skills" \
  "$HOME/.codex/skills" \
  "$HOME/.openclaw/skills" \
  "$HOME/.agents/skills" \
  "$HOME/.gemini/antigravity/skills"
do
  if [ -f "$root/$PRIMARY_SKILL/SKILL.md" ]; then
    HAS_PRIMARY=1
    break
  fi
done

if command -v gate-cli >/dev/null 2>&1 && [ "$HAS_PRIMARY" = "1" ]; then
  echo "__ROUTE_CLI__"
else
  echo "__FALLBACK__"
fi

Interpretation:

```
__ROUTE_CLI__
```
→ stop here. Do not run Trigger update or the legacy MCP sections below. Follow
```
https://github.com/gate/gate-skills/blob/master/skills/gate-info-web3/SKILL.md
```
and its playbook contract. Carry over the minimum context: protocol/platform intent plus any available
```
platform
```
,
```
token
```
,
```
asset
```
,
```
exchange
```
, or
```
symbol
```
hints from the user.
```
__FALLBACK__
```
→ continue with Trigger update and the legacy MCP workflow in this file.

本旧版技能是主CLI技能

gate-info-web3

的兼容别名。

在触发更新、选择MCP工具或执行任何旧版工作流程之前，运行确定性shell探测：

bash

PRIMARY_SKILL="gate-info-web3"
HAS_PRIMARY=0
for root in \
  "$HOME/.cursor/skills" \
  "$HOME/.codex/skills" \
  "$HOME/.openclaw/skills" \
  "$HOME/.agents/skills" \
  "$HOME/.gemini/antigravity/skills"
do
  if [ -f "$root/$PRIMARY_SKILL/SKILL.md" ]; then
    HAS_PRIMARY=1
    break
  fi
done

if command -v gate-cli >/dev/null 2>&1 && [ "$HAS_PRIMARY" = "1" ]; then
  echo "__ROUTE_CLI__"
else
  echo "__FALLBACK__"
fi

解释：

```
__ROUTE_CLI__
```
→ 在此处停止。请勿运行触发更新或以下旧版MCP部分内容。遵循
```
https://github.com/gate/gate-skills/blob/master/skills/gate-info-web3/SKILL.md
```
及其操作手册约定。传递最少上下文：协议/平台意图，以及从用户输入中获取的任何可用
```
platform
```
、
```
token
```
、
```
asset
```
、
```
exchange
```
或
```
symbol
```
提示信息。
```
__FALLBACK__
```
→ 继续执行触发更新和本文件中的旧版MCP工作流程。

Trigger update (with Execution)

触发更新（含执行）

Default (PD / blocking): On each trigger, run check
first without GATE_SKILL_UPDATE_MODE=auto
. The script only compares local vs remote; if

Result=update_available

, it does not overwrite files. STOP — ask the user whether to update before any apply
, run
, or skill Execution. In sandboxes (e.g. Cursor), use full / all permissions when later running apply
. This matches blocking update confirmation in the independent-script TEST_REPORT: blocking is enforced by these SKILL instructions plus check-only behavior (not by silent auto-apply).

Strict check (Agent / IDE — recommended on
check
): Use GATE_SKILL_CHECK_STRICT=1
. When

Result=update_available

, check
exits 3 and prints GATE_SKILL_CHECK_EXIT=3
— it stops only that shell step. Hard rule: after you ask the user, end this assistant turn; do not call apply
, run
, or MCP in the same message. run
applies without a prior user step — do not use run
in chat for the blocking flow; use check
→ user confirms →
apply
.

默认（产品开发/阻塞模式）：每次触发时，先运行**

check

，且不设置**

GATE_SKILL_UPDATE_MODE=auto

。脚本仅对比本地版本与远程版本；若返回

Result=update_available

，则不会覆盖文件。停止 — 在执行任何**

apply

、

run

或技能执行之前，询问用户是否进行更新。在沙箱环境（如Cursor）中，后续运行

apply

时需使用完全/所有权限**。这与独立脚本TEST_REPORT中的阻塞更新确认一致：阻塞由这些SKILL指令加上仅检查行为强制执行（而非静默自动应用）。

严格检查（Agent/IDE — 推荐在
check
时使用）：设置**

GATE_SKILL_CHECK_STRICT=1

。当返回
Result=update_available
时，

check

会退出并返回码3**，同时打印**

GATE_SKILL_CHECK_EXIT=3

** — 仅停止该shell步骤。硬性规则：询问用户后，结束本次助手对话轮次；请勿在同一条消息中调用**

apply

、

run

或MCP工具。

run

会在无用户前置步骤的情况下应用更新 — 在阻塞流程的聊天场景中请勿使用

run

；请使用

check

→ 用户确认 →

apply

**流程。

Step 1 — Check

步骤1 — 检查

Install root:

check

apply

read $DEST/SKILL.md
. Typical $SKILL_ROOT
: $HOME/.cursor/skills/<name>/
, $HOME/.codex/skills/<name>/
, $HOME/.openclaw/skills/<name>/
, $HOME/.agents/skills/<name>/
, $HOME/.gemini/antigravity/skills/<name>/
. Single-arg: the script resolves DEST
in that order when SKILL.md
exists; otherwise DEST
is

scripts/../

. Workspace-only trees need two-arg check
/ apply
with explicit DEST
.

Agent selection rules (run at most one of the fenced examples below; choose by OS and files under

$SKILL_ROOT/scripts/

macOS / Linux / WSL / Git Bash: If
```
update-skill.sh
```
exists → use only the Bash example.
Windows (native PowerShell): If
```
update-skill.ps1
```
exists → use only the PowerShell example.
Windows without
.ps1
(typical ClawHub install): If only
```
update-skill.sh
```
exists → try WSL or Git Bash (
```
bash
```
) using the same command shape as the Bash example. If bash is unavailable or execution fails → skip Step 1 silently (no script stderr or “version check failed” message to the user); proceed to Execution.
Neither script exists: Skip Step 1 silently; proceed to Execution. Do not invent
```
GATE_SKILL_CONFIRM_TOKEN
```
or run
```
apply
```
/
```
revoke-pending
```
.

Bash (blocking — no auto; example Cursor):

bash

GATE_SKILL_CHECK_STRICT=1 bash "$HOME/.cursor/skills/gate-info-defianalysis/scripts/update-skill.sh" check "gate-info-defianalysis"

PowerShell:

powershell

$env:GATE_SKILL_CHECK_STRICT = '1'
powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.cursor\skills\gate-info-defianalysis\scripts\update-skill.ps1" check "gate-info-defianalysis"

Result semantics:

skipped

= no action.

update_available

= remote newer; with blocking flow, do not apply until the user agrees.

check_failed

= could not compare — proceed with current version per info-news-runtime-rules.md; do not surface technical check failure details to the user.

Agent parse (stdout):

GATE_SKILL_UPDATE_AGENT_ACTION=…

. BLOCK_UNTIL_USER_CONFIRMS_UPDATE
→ Step 2 before Execution. CONTINUE_SKILL_EXECUTION
→ no block from the check script.

安装根目录：

check

apply

会读取**

$DEST/SKILL.md

。典型的

$SKILL_ROOT

：

$HOME/.cursor/skills/<name>/

、

$HOME/.codex/skills/<name>/

、

$HOME/.openclaw/skills/<name>/

、

$HOME/.agents/skills/<name>/

、

$HOME/.gemini/antigravity/skills/<name>/

。单参数模式：当

SKILL.md

存在时，脚本会按上述顺序解析

DEST

；否则

DEST

为
scripts/../
。仅工作区的目录树需要双参数模式的

check

** / apply
，并指定明确的**

DEST

**。

Agent选择规则（以下 fenced 示例最多运行一个；根据操作系统和

$SKILL_ROOT/scripts/

下的文件选择）：

macOS / Linux / WSL / Git Bash：若存在
```
update-skill.sh
```
→ 仅使用Bash示例。
Windows（原生PowerShell）：若存在
```
update-skill.ps1
```
→ 仅使用PowerShell示例。
Windows无
.ps1
文件（典型ClawHub安装）：若仅存在
```
update-skill.sh
```
→ 尝试使用WSL或Git Bash（
```
bash
```
）运行与Bash示例相同格式的命令。若bash不可用或执行失败 → 静默跳过步骤1（不向用户显示脚本错误或“版本检查失败”消息）；继续执行后续流程。
两个脚本都不存在：静默跳过步骤1；继续执行后续流程。请勿自行生成
```
GATE_SKILL_CONFIRM_TOKEN
```
或运行
```
apply
```
/
```
revoke-pending
```
。

Bash（阻塞模式 — 无自动更新；Cursor示例）：

bash

GATE_SKILL_CHECK_STRICT=1 bash "$HOME/.cursor/skills/gate-info-defianalysis/scripts/update-skill.sh" check "gate-info-defianalysis"

PowerShell：

powershell

$env:GATE_SKILL_CHECK_STRICT = '1'
powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.cursor\skills\gate-info-defianalysis\scripts\update-skill.ps1" check "gate-info-defianalysis"

结果语义：

skipped

= 无操作。

update_available

= 远程版本更新；在阻塞模式下，需获得用户同意后再应用更新。

check_failed

= 无法对比版本 — 根据info-news-runtime-rules.md继续使用当前版本；请勿向用户展示技术检查失败的细节。

Agent解析（标准输出）：

GATE_SKILL_UPDATE_AGENT_ACTION=…

。BLOCK_UNTIL_USER_CONFIRMS_UPDATE
→ 执行前先进行步骤2。CONTINUE_SKILL_EXECUTION
→ 检查脚本无阻塞，可继续执行。

Step 2 — Confirm or Reject (blocking)

步骤2 — 确认或拒绝（阻塞模式）

Runtime: Use the same shell family for Step 2 as for Step 1 (Bash vs PowerShell). If Step 1 was skipped, do not run

apply

revoke-pending

If
update_available
:

STOP — do NOT proceed to Execution yet.
Inform the user (e.g. newer version available; summarize if helpful).
Wait for the user’s reply — blocking step.
Hard rule (Cursor / Agent): When
```
check
```
reports update_available
, or BLOCK_UNTIL_USER_CONFIRMS_UPDATE
, or strict exit 3
, end this turn after asking. Only in the user’s next message run apply
(if they agree) or revoke-pending
(if they decline). Do not chain apply
in the same turn as check
for this flow.
- User agrees → run apply
  with GATE_SKILL_CONFIRM_TOKEN
  from strict check
  stdout when required, then Execution.
- User declines → revoke-pending
  , then Execution on the current install.

Two-step gate (strict
check
): apply
/ run
(without GATE_SKILL_UPDATE_MODE=auto
) fail until GATE_SKILL_CONFIRM_TOKEN
matches .gate-skill-apply-token
. User decline → revoke-pending
.

bash

GATE_SKILL_CONFIRM_TOKEN="<paste from check stdout>" bash "$HOME/.cursor/skills/gate-info-defianalysis/scripts/update-skill.sh" apply "gate-info-defianalysis"

bash

bash "$HOME/.cursor/skills/gate-info-defianalysis/scripts/update-skill.sh" revoke-pending "gate-info-defianalysis"

powershell

$env:GATE_SKILL_CONFIRM_TOKEN = '<paste from check stdout>'
powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.cursor\skills\gate-info-defianalysis\scripts\update-skill.ps1" apply "gate-info-defianalysis"

powershell

powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.cursor\skills\gate-info-defianalysis\scripts\update-skill.ps1" revoke-pending "gate-info-defianalysis"

If Step 1 was not strict (no pending token): apply
without GATE_SKILL_CONFIRM_TOKEN
is allowed.

If
skipped
or
check_failed
: no update step; proceed to Execution.

运行时：步骤2使用与步骤1相同的shell类型（Bash或PowerShell）。若步骤1被跳过，请勿运行

apply

或

revoke-pending

。

若返回
update_available
：

停止 — 暂不继续执行后续流程。
告知用户（例如：有新版本可用；如有帮助可简要说明更新内容）。
等待用户回复 — 阻塞步骤。
硬性规则（Cursor/Agent）：当
```
check
```
返回**
```
update_available
```
、
```
BLOCK_UNTIL_USER_CONFIRMS_UPDATE
```
或严格模式下的
```
退出码3
```
时，询问用户后结束本次对话轮次**。仅在用户的下一条消息中运行**
```
apply
```
（若用户同意）或
```
revoke-pending
```
（若用户拒绝）。在阻塞流程中，请勿在同一次对话轮次中连续执行
```
check
```
和
```
apply
```
**。
- 用户同意 → 运行**
```
apply
```
  ，必要时使用严格模式下
  check
  标准输出中的
```
GATE_SKILL_CONFIRM_TOKEN
```
  **，然后执行后续流程。
- 用户拒绝 → 运行**
```
revoke-pending
```
  **，然后基于当前安装版本执行后续流程。

两步验证（严格
check
模式）：apply
/ run
（未设置**

GATE_SKILL_UPDATE_MODE=auto

）在

GATE_SKILL_CONFIRM_TOKEN

与

.gate-skill-apply-token

匹配前会执行失败**。用户拒绝时 → 运行**

revoke-pending

**。

bash

GATE_SKILL_CONFIRM_TOKEN="<粘贴check输出中的令牌>" bash "$HOME/.cursor/skills/gate-info-defianalysis/scripts/update-skill.sh" apply "gate-info-defianalysis"

bash

bash "$HOME/.cursor/skills/gate-info-defianalysis/scripts/update-skill.sh" revoke-pending "gate-info-defianalysis"

powershell

$env:GATE_SKILL_CONFIRM_TOKEN = '<粘贴check输出中的令牌>'
powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.cursor\skills\gate-info-defianalysis\scripts\update-skill.ps1" apply "gate-info-defianalysis"

powershell

powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.cursor\skills\gate-info-defianalysis\scripts\update-skill.ps1" revoke-pending "gate-info-defianalysis"

若步骤1未使用严格模式（无待处理令牌）：允许不携带**

GATE_SKILL_CONFIRM_TOKEN

运行

apply

**。

若返回
skipped
或
check_failed
：无需执行更新步骤；继续执行后续流程。

Optional —

GATE_SKILL_UPDATE_MODE=auto

可选 —

GATE_SKILL_UPDATE_MODE=auto

For CI / unattended automation only: setting GATE_SKILL_UPDATE_MODE=auto
on check
makes the script apply immediately when the remote is newer — no user confirmation and incompatible with blocking update confirmation tests. Do not use auto
on check
when reproducing the blocking PD flow.

仅适用于CI/无人值守自动化：在**

check

时设置

GATE_SKILL_UPDATE_MODE=auto

，当远程版本更新时，脚本会立即应用更新** — 无需用户确认，且与阻塞更新确认测试不兼容。在复现阻塞模式的产品开发流程时，请勿在**

check

时使用

auto

**模式。

Parameters

参数

name: Frontmatter
```
name
```
above; must match
```
skills/<name>/
```
on gate-skills.
Invoke: Use $SKILL_ROOT/scripts/update-skill.sh
(or
```
.ps1
```
) where $SKILL_ROOT/SKILL.md
is this skill — e.g. ~/.cursor/skills/<name>
, ~/.codex/skills/<name>
, ~/.openclaw/skills/<name>
, ~/.agents/skills/<name>
, ~/.gemini/antigravity/skills/<name>
; do not treat ~/.cursor
(or any host root without skills/<name>/SKILL.md
) as the install. With one arg, the script resolves $SKILL_ROOT
in that order before falling back to the script’s directory; workspace installs need explicit
DEST
. Two-arg
check
/
apply
/
revoke-pending
: canonical order is absolute
DEST
(skill root) first, then name
; update-skill.sh
/
update-skill.ps1
auto-swap when only one normalized path contains
```
SKILL.md
```
(e.g. agent passes
```
name
```
then path).
ClawHub vs full tree: Installs without
```
update-skill.ps1
```
may copy it from gate/gate-skills under
```
skills/<name>/scripts/
```
(manual only; agents must not auto-download).

Do not dump raw script logs into the user-facing reply except when debugging. On check
exit 3 (strict), do not run Execution until Step 2 is resolved. On check_failed
or apply
failure, still run Execution when appropriate per runtime rules.

name：上方前置元数据中的
```
name
```
；必须与gate-skills上的
```
skills/<name>/
```
路径匹配。
调用方式：使用**
```
$SKILL_ROOT/scripts/update-skill.sh
```
（或
.ps1
），其中
```
$SKILL_ROOT/SKILL.md
```
为本技能文件 — 例如
```
~/.cursor/skills/<name>
```
、
```
~/.codex/skills/<name>
```
、
```
~/.openclaw/skills/<name>
```
、
```
~/.agents/skills/<name>
```
、
```
~/.gemini/antigravity/skills/<name>
```
；请勿将
```
~/.cursor
```
（或任何不含
```
skills/<name>/SKILL.md
```
的主机根目录）视为安装目录。单参数模式下，脚本会按上述顺序解析
```
$SKILL_ROOT
```
，若未找到则回退到脚本所在目录；工作区安装需使用双参数模式的
```
check
```
** / apply
/ revoke-pending
，并指定明确的**
```
DEST
```
。双参数模式的
check
/
apply
/
revoke-pending
：标准顺序为绝对路径
```
DEST
```
（技能根目录）在前**，然后是**
```
name
```
；当只有一个标准化路径包含
SKILL.md
时，
```
update-skill.sh
```
/
```
update-skill.ps1
```
会自动交换参数顺序**（例如Agent传递
```
name
```
然后是路径）。
ClawHub与完整目录树：无
```
update-skill.ps1
```
的安装可从gate/gate-skills的
```
skills/<name>/scripts/
```
目录手动复制该文件；Agent不得自动下载。

除非调试，否则请勿将原始脚本日志输出到用户可见的回复中。在严格模式下**

check

退出码3时，需先完成步骤2才能执行后续流程。在

check_failed

或

apply

失败**时，仍需根据运行时规则在适当情况下执行后续流程。

MCP Dependencies

MCP依赖

Legacy path only — this section applies when Step 0 emitted

__FALLBACK__

仅适用于旧版路径 — 当步骤0输出

__FALLBACK__

时，本部分内容生效。

Required MCP Servers

必需的MCP服务器

MCP Server	Status
Gate-Info	✅ Required

MCP服务器	状态
Gate-Info	✅ 必填

MCP Tools Used

使用的MCP工具

Query Operations (Read-only) — use by sub-scenario; do not call tools outside the active scenario.

info_platformmetrics_get_defi_overview
info_platformmetrics_search_platforms
info_platformmetrics_get_platform_info
info_platformmetrics_get_platform_history
info_platformmetrics_get_yield_pools
info_platformmetrics_get_stablecoin_info
info_platformmetrics_get_bridge_metrics
info_platformmetrics_get_exchange_reserves
info_platformmetrics_get_liquidation_heatmap
info_coin_get_coin_info

查询操作（只读） — 按子场景使用；请勿调用当前场景外的工具。

info_platformmetrics_get_defi_overview
info_platformmetrics_search_platforms
info_platformmetrics_get_platform_info
info_platformmetrics_get_platform_history
info_platformmetrics_get_yield_pools
info_platformmetrics_get_stablecoin_info
info_platformmetrics_get_bridge_metrics
info_platformmetrics_get_exchange_reserves
info_platformmetrics_get_liquidation_heatmap
info_coin_get_coin_info

Authentication

认证

API Key Required: No
Credentials Source: None; this skill uses read-only Gate Info / Gate News MCP access only.

是否需要API密钥：否
凭证来源：无；本技能仅使用只读的Gate Info / Gate News MCP访问权限。

Installation Check

安装检查

Required: Gate-Info
Install: Use the local Gate MCP installation flow for the current host IDE before continuing.
Continue only after the required Gate MCP server is available in the current environment.

必需组件：Gate-Info
安装方式：继续之前，请使用当前主机IDE的本地Gate MCP安装流程完成安装。
仅当当前环境中可用所需的Gate MCP服务器时，才可继续执行。

Routing Rules

路由规则

Legacy path only — when Step 0 emitted

__ROUTE_CLI__

, routing is delegated to

gate-info-web3

User Intent	Keywords	Action
DeFi overview / TVL ranking	"DeFi overview" "TVL ranking" "top DeFi protocols"	Execute Sub-scenario A: Overview
Single platform deep-dive	"Uniswap TVL" "Aave metrics" "Compound info"	Execute Sub-scenario B: Platform Detail
Yield / APY query	"best yield" "USDC APY" "lending rates" "where to earn"	Execute Sub-scenario C: Yield Pools
Stablecoin analysis	"USDT market cap" "stablecoin ranking" "USDC circulation"	Execute Sub-scenario D: Stablecoins
Cross-chain bridge	"bridge volume" "top bridges" "cross-chain TVL"	Execute Sub-scenario E: Bridges
Exchange reserves	"Binance BTC reserves" "exchange reserves" "proof of reserves"	Execute Sub-scenario F: Exchange Reserves
Liquidation analysis	"BTC liquidation heatmap" "where are liquidations" "liquidation density"	Execute Sub-scenario G: Liquidation Heatmap
Coin fundamentals (no DeFi focus)	"analyze SOL" "how is BTC"	Route to `gate-info-coinanalysis`
Market overview	"how's the market"	Route to `gate-info-marketoverview`

仅适用于旧版路径 — 当步骤0输出

__ROUTE_CLI__

时，路由由

gate-info-web3

处理。

用户意图	关键词	操作
DeFi概览/TVL排名	"DeFi overview" "TVL ranking" "top DeFi protocols"	执行子场景A：概览
单一平台深度分析	"Uniswap TVL" "Aave metrics" "Compound info"	执行子场景B：平台详情
收益率/APY查询	"best yield" "USDC APY" "lending rates" "where to earn"	执行子场景C：收益池
稳定币分析	"USDT market cap" "stablecoin ranking" "USDC circulation"	执行子场景D：稳定币
跨链桥	"bridge volume" "top bridges" "cross-chain TVL"	执行子场景E：跨链桥
交易所储备	"Binance BTC reserves" "exchange reserves" "proof of reserves"	执行子场景F：交易所储备
清算分析	"BTC liquidation heatmap" "where are liquidations" "liquidation density"	执行子场景G：清算热力图
代币基本面（无DeFi聚焦）	"analyze SOL" "how is BTC"	路由至 `gate-info-coinanalysis`
市场概览	"how's the market"	路由至 `gate-info-marketoverview`

Execution Workflow

执行工作流程

Legacy path only — this section applies when Step 0 emitted

__FALLBACK__

仅适用于旧版路径 — 当步骤0输出

__FALLBACK__

时，本部分内容生效。

Step 0: Multi-Dimension Intent Check

步骤0：多维度意图检查

If the query is about DeFi/platform metrics, proceed with this Skill.
If the query also involves coin fundamentals, technicals, or news beyond DeFi scope, route to
```
gate-info-research
```
(if available).

若查询内容涉及DeFi/平台指标，继续使用本Skill。
若查询内容还涉及DeFi范围外的代币基本面、技术分析或新闻，路由至
```
gate-info-research
```
（若可用）。

Step 1: Intent Recognition & Parameter Extraction

步骤1：意图识别与参数提取

Extract from user input:

```
platform_name
```
(optional): Protocol name (e.g., Uniswap, Aave, Lido)
```
symbol
```
(optional): Token/stablecoin symbol (e.g., USDC, USDT, ETH)
```
chain
```
(optional): Blockchain filter (e.g., Ethereum, Arbitrum)
```
exchange
```
(optional): Exchange name (e.g., Binance, OKX)

从用户输入中提取：

```
platform_name
```
（可选）：协议名称（如Uniswap、Aave、Lido）
```
symbol
```
（可选）：代币/稳定币符号（如USDC、USDT、ETH）
```
chain
```
（可选）：区块链筛选条件（如Ethereum、Arbitrum）
```
exchange
```
（可选）：交易所名称（如Binance、OKX）

Step 2: Call MCP Tools by Sub-scenario

步骤2：按子场景调用MCP工具

Sub-scenario A: DeFi Overview

子场景A：DeFi概览

Step	MCP Tool	Parameters	Retrieved Data	Parallel
1a	`info_platformmetrics_get_defi_overview`	`category="all"`	Total TVL, volume, fees across DeFi/CEX/DEX	Yes
1b	`info_platformmetrics_search_platforms`	`sort_by="tvl", limit=10`	Top 10 platforms by TVL	Yes

步骤	MCP工具	参数	获取的数据	是否并行
1a	`info_platformmetrics_get_defi_overview`	`category="all"`	DeFi/CEX/DEX的总TVL、交易量、手续费	是
1b	`info_platformmetrics_search_platforms`	`sort_by="tvl", limit=10`	TVL排名前10的平台	是

Sub-scenario B: Platform Detail

子场景B：平台详情

Step MCP Tool Parameters Retrieved Data Parallel

Step	MCP Tool	Parameters	Retrieved Data	Parallel
1a	`info_platformmetrics_get_platform_info`	`platform_name={name}, scope="full"`	Full platform metrics (TVL, volume, fees, chains)	Yes
1b	`info_platformmetrics_get_platform_history`	`platform_name={name}, metrics=["tvl","volume"]`	Historical trend	Yes
1c	`info_coin_get_coin_info`	`query={token_symbol}`	Platform's native token info	Yes

info_platformmetrics_get_platform_info

platform_name={name}, scope="full"

Full platform metrics (TVL, volume, fees, chains)

Yes

info_platformmetrics_get_platform_history

platform_name={name}, metrics=["tvl","volume"]

Historical trend

Yes

info_coin_get_coin_info

query={token_symbol}

Platform's native token info

Yes

步骤 MCP工具参数获取的数据是否并行

步骤	MCP工具	参数	获取的数据	是否并行
1a	`info_platformmetrics_get_platform_info`	`platform_name={name}, scope="full"`	完整平台指标（TVL、交易量、手续费、支持链）	是
1b	`info_platformmetrics_get_platform_history`	`platform_name={name}, metrics=["tvl","volume"]`	历史趋势	是
1c	`info_coin_get_coin_info`	`query={token_symbol}`	平台原生代币信息	是

info_platformmetrics_get_platform_info

platform_name={name}, scope="full"

完整平台指标（TVL、交易量、手续费、支持链）

是

info_platformmetrics_get_platform_history

platform_name={name}, metrics=["tvl","volume"]

历史趋势

是

info_coin_get_coin_info

query={token_symbol}

平台原生代币信息

是

Sub-scenario C: Yield Pools

子场景C：收益池

Step	MCP Tool	Parameters	Retrieved Data
1	`info_platformmetrics_get_yield_pools`	`project={name}, chain={chain}, symbol={symbol}, sort_by="apy", limit=20`	Yield pool rankings with APY, TVL

步骤	MCP工具	参数	获取的数据
1	`info_platformmetrics_get_yield_pools`	`project={name}, chain={chain}, symbol={symbol}, sort_by="apy", limit=20`	带APY、TVL的收益池排名

Sub-scenario D: Stablecoins

子场景D：稳定币

Step	MCP Tool	Parameters	Retrieved Data
1	`info_platformmetrics_get_stablecoin_info`	`symbol={symbol}, chain={chain}, limit=10`	Stablecoin ranking or single coin detail with chain distribution

步骤	MCP工具	参数	获取的数据
1	`info_platformmetrics_get_stablecoin_info`	`symbol={symbol}, chain={chain}, limit=10`	稳定币排名或单币种详情（含链上分布）

Sub-scenario E: Bridges

子场景E：跨链桥

Step	MCP Tool	Parameters	Retrieved Data
1	`info_platformmetrics_get_bridge_metrics`	`bridge_name={name}, chain={chain}`	Bridge ranking or single bridge chain breakdown

步骤	MCP工具	参数	获取的数据
1	`info_platformmetrics_get_bridge_metrics`	`bridge_name={name}, chain={chain}`	跨链桥排名或单桥链上细分数据

Sub-scenario F: Exchange Reserves

子场景F：交易所储备

Step	MCP Tool	Parameters	Retrieved Data
1	`info_platformmetrics_get_exchange_reserves`	`exchange={exchange}, asset={asset}`	Exchange on-chain reserves (BTC, ETH, etc.)

步骤	MCP工具	参数	获取的数据
1	`info_platformmetrics_get_exchange_reserves`	`exchange={exchange}, asset={asset}`	交易所链上储备（BTC、ETH等）

Sub-scenario G: Liquidation Heatmap

子场景G：清算热力图

Step	MCP Tool	Parameters	Retrieved Data
1	`info_platformmetrics_get_liquidation_heatmap`	`symbol={symbol}, exchange={exchange}`	Liquidation density by price range

步骤	MCP工具	参数	获取的数据
1	`info_platformmetrics_get_liquidation_heatmap`	`symbol={symbol}, exchange={exchange}`	按价格区间划分的清算密度

Step 3: LLM Aggregation

步骤3：LLM聚合

Generate sub-scenario-specific analysis. For overview, provide market context; for detail, provide competitive positioning; for yield, highlight risk/reward.

生成子场景专属分析内容。对于概览场景，提供市场背景；对于详情场景，提供竞争定位分析；对于收益率场景，突出风险/回报情况。

Step 4: Progressive Loading (Bridges & Stablecoins)

步骤4：渐进式加载（跨链桥与稳定币）

For Bridges and Stablecoins, use a list-first, detail-on-demand pattern:

First call (no
```
bridge_name
```
/ narrow
```
symbol
```
): ranking list — summary without full chain breakdown.
Second call (user follow-up): specific
```
bridge_name
```
or
```
symbol
```
— full chain-level details.

针对跨链桥和稳定币场景，采用“先列表、按需提供详情”的模式：

首次调用（无
```
bridge_name
```
/ 未指定具体
```
symbol
```
）：返回排名列表 — 仅提供摘要，不包含完整链上细分数据。
二次调用（用户跟进询问）：指定具体
```
bridge_name
```
或
```
symbol
```
— 返回完整链级详情。

Report Template

报告模板

Legacy path only — this section applies when Step 0 emitted

__FALLBACK__

仅适用于旧版路径 — 当步骤0输出

__FALLBACK__

时，本部分内容生效。

Template A: DeFi Overview

模板A：DeFi概览

markdown

undefined

markdown

undefined

DeFi Ecosystem Overview

DeFi生态系统概览

Generated: {timestamp}

生成时间：{timestamp}

Market Summary

市场摘要

Metric	Value	24h Change
Total DeFi TVL	${total_tvl}	{change}%
DEX 24h Volume	${dex_volume}	{change}%
Total Fees (24h)	${total_fees}	{change}%
Stablecoin Market Cap	${stablecoin_mcap}	{change}%

指标	数值	24小时变化
DeFi总TVL	${total_tvl}	{change}%
DEX24小时交易量	${dex_volume}	{change}%
总手续费（24小时）	${total_fees}	{change}%
稳定币市值	${stablecoin_mcap}	{change}%

Top 10 Protocols by TVL

TVL排名前10的协议

Rank	Protocol	Category	TVL	24h Change	Chain
1	{name}	{category}	${tvl}	{change}%	{chains}

排名	协议	分类	TVL	24小时变化	支持链
1	{name}	{category}	${tvl}	{change}%	{chains}

Analysis

分析

{LLM assessment: DeFi market trend, capital flows, notable shifts}

Data sourced from Gate Info MCP. Does not constitute investment advice.

undefined

{LLM评估内容：DeFi市场趋势、资金流向、显著变化}

数据来源：Gate Info MCP。不构成投资建议。

undefined

Template B: Platform Detail

模板B：平台详情

markdown

undefined

markdown

undefined

{platform_name} Deep Dive

{platform_name}深度分析

Generated: {timestamp}

生成时间：{timestamp}

Key Metrics

核心指标

Metric	Value	Rank
TVL	${tvl}	#{rank}
24h Volume	${volume}	—
24h Fees	${fees}	—

指标	数值	排名
TVL	${tvl}	#{rank}
24小时交易量	${volume}	—
24小时手续费	${fees}	—

TVL Trend

TVL趋势

{Describe trend from historical data}

{根据历史数据描述趋势}

Token Info ({symbol})

代币信息({symbol})

Metric	Value
Price	${price}
Market Cap	${market_cap}
FDV	${fdv}

指标	数值
价格	${price}
市值	${market_cap}
完全稀释估值(FDV)	${fdv}

Analysis

分析

{LLM competitive analysis}

Data sourced from Gate Info MCP. Does not constitute investment advice.

undefined

{LLM竞争分析内容}

数据来源：Gate Info MCP。不构成投资建议。

undefined

Templates C–G (Yield / Stablecoin / Bridge / Reserve / Liquidation)

模板C–G（收益率/稳定币/跨链桥/储备/清算）

Summary metrics at top
Ranked table of data
2–3 sentence LLM analysis
Standard disclaimer

顶部显示摘要指标
数据排名表格
2–3句LLM分析内容
标准免责声明

Decision Logic

决策逻辑

Condition	Assessment / next step
Generic DeFi market, TVL leaderboard, or “top protocols”	Sub-scenario A (Overview)
User names a specific protocol (Uniswap, Aave, ...)	Sub-scenario B (Platform detail)
Yield, APY, lending, “where to earn”	Sub-scenario C (Yield pools)
Stablecoins, peg, circulation, ranking	Sub-scenario D; use progressive loading per Step 4
Bridges, cross-chain TVL, bridge volume	Sub-scenario E; list-first, detail on follow-up
Exchange reserves, PoR, “exchange BTC holdings”	Sub-scenario F
Liquidations, heatmap, density by price	Sub-scenario G
Ambiguous intent	Ask one clarifying question or default to A

条件	评估/下一步操作
通用DeFi市场、TVL排行榜或“顶级协议”相关内容	子场景A（概览）
用户提及具体协议（Uniswap、Aave等）	子场景B（平台详情）
收益率、APY、借贷、“何处获利”相关内容	子场景C（收益池）
稳定币、锚定、流通量、排名相关内容	子场景D；遵循步骤4的渐进式加载模式
跨链桥、跨链TVL、桥接交易量相关内容	子场景E；先返回列表，跟进询问时提供详情
交易所储备、储备证明(PoR)、“交易所BTC持有量”相关内容	子场景F
清算、热力图、按价格划分的密度相关内容	子场景G
意图模糊	提出一个澄清问题或默认使用子场景A

Error Handling

错误处理

Error Type	Handling
Platform name not found	Suggest similar platform names; ask user to verify
Single Tool fails	Skip that section; note "Data temporarily unavailable"
All Tools fail	Return error; suggest user try again later
No yield pools match criteria	Broaden search (remove chain/symbol filter); inform user
Exchange not supported	List supported exchanges; ask user to choose another
Symbol not recognized	Try matching via `info_coin_get_coin_info` ; ask user if unclear

错误类型	处理方式
平台名称未找到	建议相似平台名称；请用户确认
单个工具调用失败	跳过该部分内容；标注“数据暂时不可用”
所有工具调用失败	返回错误信息；建议用户稍后重试
无匹配条件的收益池	放宽搜索条件（移除链/符号筛选）；告知用户
交易所不支持	列出支持的交易所；请用户选择其他交易所
符号无法识别	尝试通过 `info_coin_get_coin_info` 匹配；若仍不明确请用户确认

Cross-Skill Routing

跨Skill路由

User Follow-up Intent	Route To
"Analyze the token"	`gate-info-coinanalysis`
"Technical analysis of the token"	`gate-info-trendanalysis`
"Is this protocol safe?"	`gate-info-riskcheck`
"On-chain data for the token"	`gate-info-tokenonchain`
"Any news about this protocol?"	`gate-news-briefing`
"How does macro affect DeFi?"	`gate-info-macroimpact`
"How's the market overall?"	`gate-info-marketoverview`

用户跟进意图	路由至
"分析该代币"	`gate-info-coinanalysis`
"该代币的技术分析"	`gate-info-trendanalysis`
"这个协议安全吗？"	`gate-info-riskcheck`
"该代币的链上数据"	`gate-info-tokenonchain`
"这个协议有什么新闻吗？"	`gate-news-briefing`
"宏观因素如何影响DeFi？"	`gate-info-macroimpact`
"整体市场情况如何？"	`gate-info-marketoverview`

Safety Rules

安全规则

No yield guarantees: APY/yield data is historical and subject to change; state clearly that past rates do not guarantee future returns.
Smart contract risk: When showing yield pools or protocols, note that DeFi carries smart contract risk.
No endorsement: Listing a protocol does not constitute an endorsement; maintain neutrality.
Reserve disclaimers: Exchange reserve data is on-chain observable but may not reflect total assets.
Liquidation data: Liquidation heatmaps show estimated levels, not guaranteed triggers.
Data transparency: Label data source, update frequency, and known limitations.
Age & eligibility: Intended for users aged 18 or above with full civil capacity in their jurisdiction.
Data flow: The host agent processes user prompts; this skill directs read-only Gate-Info MCP tools listed above. The LLM formats answers from tool results. Aside from those MCP calls and the documented skill-update flow (GitHub URLs in General Rules and
```
info-news-runtime-rules.md
```
), this skill does not invoke additional third-party data services.

无收益率保证：APY/收益率数据为历史数据，可能发生变化；需明确说明过往收益率不代表未来收益。
智能合约风险：展示收益池或协议时，需标注DeFi存在智能合约风险。
无背书：列出协议不构成背书；保持中立性。
储备免责声明：交易所储备数据为链上可观测数据，但可能无法反映总资产情况。
清算数据：清算热力图显示的是预估水平，不代表必然触发清算。
数据透明度：标注数据来源、更新频率及已知限制。
年龄与资格：仅面向18周岁及以上且在所在司法辖区具备完全民事行为能力的用户。
数据流：主机Agent处理用户提示；本技能仅调用上述列出的只读 Gate-Info MCP工具。LLM根据工具返回结果格式化答案。除上述MCP调用及文档化的技能更新流程（通用规则和
```
info-news-runtime-rules.md
```
中的GitHub链接）外，本技能不会调用其他第三方数据服务。