gate-news-eventexplain

General Rules

⚠️ 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 "Why is it pumping/dumping?" Skill. When the market experiences abnormal volatility and the user asks why, the system traces the event source through multi-step calls, cross-references market data to verify impact magnitude, and delivers a complete "Event → Impact Chain → Market Reaction" analysis report.

Trigger Scenarios: User expresses curiosity about a market anomaly, e.g., "why did BTC crash", "what just happened", "why did ETH suddenly spike".

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).

Step 0 — Wrapper routing probe

This legacy skill is a compatibility alias for the primary CLI skill gate-news-intel.

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

PRIMARY_SKILL="gate-news-intel"
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-news-intel/SKILL.md and its playbook contract. Carry over the minimum context: symbol, optional timerange, and eventid when the user already references a concrete event.

• FALLBACK → continue with Trigger update and the legacy MCP workflow in

this file.

Trigger update (with Execution)

Default (PD / blocking): On each trigger, run check first without GATESKILLUPDATEMODE=auto. The script only compares local vs remote; if Result=updateavailable, 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 GATESKILLCHECKSTRICT=1. When Result=updateavailable, check exits 3 and prints GATESKILLCHECK_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.

Step 1 — Check

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 GATESKILLCONFIRM_TOKEN or run apply / revoke-pending.

Bash (blocking — no auto; example Cursor):

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

PowerShell:

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

Result semantics: skipped = no action. updateavailable = remote newer; with blocking flow, do not apply until the user agrees. checkfailed = 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): GATESKILLUPDATEAGENTACTION=…. BLOCKUNTILUSERCONFIRMSUPDATE → Step 2 before Execution. CONTINUESKILLEXECUTION → no block from the check script.

Step 2 — Confirm or Reject (blocking)

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 or revoke-pending.

If update_available:

1. STOP — do NOT proceed to Execution yet.
2. Inform the user (e.g. newer version available; summarize if helpful).
3. Wait for the user’s reply — blocking step.

Hard rule (Cursor / Agent): When check reports updateavailable, or BLOCKUNTILUSERCONFIRMS_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 GATESKILLCONFIRM_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 GATESKILLUPDATEMODE=auto) fail until GATESKILLCONFIRMTOKEN matches .gate-skill-apply-token. User decline → revoke-pending.

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

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

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

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

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

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

Optional — GATESKILLUPDATE_MODE=auto

For CI / unattended automation only: setting GATESKILLUPDATE_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.

Parameters

• name: Frontmatter name above; must match skills/<name>/ on gate-skills.
• Invoke: Use $SKILLROOT/scripts/update-skill.sh (or .ps1) where $SKILLROOT/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.

MCP Dependencies

Legacy path only — this section applies when Step 0 emitted FALLBACK.

Required MCP Servers

MCP Tools Used

Query Operations (Read-only)

• infomarketsnapshotgetmarketsnapshot
• infoonchaingettokenonchain
• newseventsgeteventdetail
• newseventsgetlatestevents
• newsfeedsearch_news

Authentication

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

Installation Check

• Required: Gate-News, Gate-Info (for infomarketsnapshotgetmarketsnapshot and infoonchaingettokenonchain in this skill)
• 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.

Routing Rules

Legacy path only — when Step 0 emitted __ROUTE_CLI__, routing is delegated to gate-news-intel.

Execution Workflow

Legacy path only — this section applies when Step 0 emitted FALLBACK.

Step 0: Multi-Dimension Intent Check

Before executing this Skill, check if the user's query involves multiple analysis dimensions:

• If the query is exclusively about the reason behind a price move, proceed with this Skill.
• If the query also mentions fundamentals, risk check, technicals, comparison, or any other analysis dimension beyond event attribution, route to gate-info-research — it handles multi-dimension queries with unified tool deduplication and coherent report aggregation.

Step 1: Intent Recognition & Parameter Extraction

Extract from user input:

• coin: The coin involved (e.g., BTC, ETH; may be empty = overall market)
• direction: Up or down (aids search)
• time_hint: Time clue ("just now", "today", "yesterday"; default: past 24h)

Step 2: Phase 1 — Event Search + Market Verification (Parallel)

Both Tools called in parallel.

Step 3: Decision Branch

events response
    │
    ├── Matching event found (event time aligns with volatility onset)
    │   └── → Step 4a: Get event details
    │
    └── No clear event match
        └── → Step 4b: Expand news search

Step 4a: Event Found → Get Details + On-chain Verification

Step 4b: No Event Found → Expand Search

Step 5: LLM Attribution Reasoning

The LLM must complete the following reasoning chain:

1. Confirm the volatility: Based on the market snapshot, confirm the timing, magnitude, and volume change
2. Identify the trigger event: From events/news, find the event with the closest time alignment
3. Verify causality: Did the event precede the price move? Is there corresponding on-chain activity?
4. Assess the impact chain: Event → Direct impact → Sentiment transmission → Price reaction
5. Evaluate follow-on potential: Based on the event's nature, assess whether the impact is short-term or sustained

Step 6: Output Structured Report

Report Template

Legacy path only — this section applies when Step 0 emitted FALLBACK.

## {coin} {Pump/Dump} Attribution Analysis

> Analysis time: {timestamp}

### 1. Volatility Summary

| Metric | Value |
|--------|-------|
| Current Price | ${price} |
| Move Magnitude | {change}% (within {timeframe}) |
| High | ${high} ({time}) |
| Low | ${low} ({time}) |
| Volume Change | {volume_change}% (vs 24h average) |
| Futures Liquidations | ${liquidation} (if available) |

### 2. Core Triggering Event

🔴 **{event_title}**

- Event Time: {event_time}
- Event Type: {Regulation / Project Development / Market Manipulation / Macro Economic / Technical Failure / Whale Activity}
- Details: {2-3 sentence description}
- Source: {source}

### 3. Event → Impact Chain

{event} │ ├── Direct Impact: {description} │ e.g., SEC lawsuit → Regulatory uncertainty for the token increases │ ├── Sentiment Transmission: {description} │ e.g., Panic spreads → Fear & Greed Index drops from 65 to 35 │ └── Price Reaction: {description} e.g., {coin} dropped from ${high} to ${low} within 2 hours of the event

### 4. On-chain Verification

{If on-chain data is available:}

| On-chain Metric | Anomaly |
|----------------|---------|
| Exchange Inflows | {increase/decrease}, {description} |
| Large Transfers | {count} transfers exceeding ${threshold} |
| Whale Activity | {description} |
| Futures Funding Rate | {change description} |

{Does the on-chain data corroborate the event narrative?}

### 5. Ripple Effects

{Did this event affect other coins/sectors?}

- {Related coin 1}: {impact description}
- {Related coin 2}: {impact description}
- Sector impact: {e.g., L1 sector declined across the market, DeFi sector affected}

### 6. Forward Outlook

{Based on the event's nature, assess the follow-on impact:}

| Dimension | Assessment |
|-----------|------------|
| Impact Duration | {One-time shock / Short-term (1-3 days) / Medium-term (1-2 weeks) / Long-term} |
| What to Watch Next | {Items to monitor: court ruling, policy details, project response, etc.} |
| Historical Precedent | {Similar past events and their outcomes, if any} |

### ⚠️ Important Notes

- Market moves may be caused by multiple overlapping factors; the above analysis is based on currently available information
- Long-term impact of the event remains uncertain

> The above analysis is based on public information and on-chain data. It does not constitute investment advice.

Template When No Event Can Be Identified

## {coin} Volatility Analysis

> Analysis time: {timestamp}

### Volatility Summary

{Same as above}

### Possible Cause Analysis

⚠️ No single clear triggering event was identified. The following is a composite analysis:

**Possible Factor 1: {description}**
- Evidence: {related news/data}
- Likelihood: {High/Medium/Low}

**Possible Factor 2: {description}**
- Evidence: ...
- Likelihood: ...

**On-chain Clues**
{Any anomalous on-chain data that could help explain the move?}

### Composite Assessment

{LLM's composite analysis, with uncertainty explicitly acknowledged}

> Note: No single clear triggering event was found for this move. The above analysis is an informed assessment based on available data.

Reasoning Logic

Event Matching Logic

Volatility Magnitude Assessment

On-chain Anomaly Assessment

Error Handling

Cross-Skill Routing

Safety Rules

1. No definitive causal claims: Use language like "likely caused by", "the most closely related event is" — avoid absolute causal assertions
2. No follow-on predictions: Do not output "it will continue to rise/fall" style predictions
3. No investment advice: Do not give buy/sell recommendations based on event analysis
4. Acknowledge uncertainty: When the causal link between event and move is uncertain, explicitly state it
5. Source attribution: Events and news must cite their sources
6. Flag missing data: When on-chain data or event details are unavailable, explicitly state it
7. Avoid amplifying panic: When describing crashes or black-swan events, maintain objective, neutral language — no sensationalist rhetoric