Smithery is now a part of Arcade.dev! Read more in our announcement here
Single-coin comprehensive analysis. Use this skill ONLY when the user asks to analyze one coin with no additional explicit dimension (e.g., no separate risk check, no separate trend-only request)...
⚠️ 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).
__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 most frequently used Skill. The user inputs a coin name, the system calls 5 MCP Tools in parallel to fetch fundamentals + market data + technicals + news + social sentiment, then the LLM aggregates the results into a structured analysis report.
Trigger Scenarios: User mentions a specific coin + keywords like analyze, how is, worth, look at, fundamentals, market analysis.
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).
This legacy skill is a compatibility alias for the primary CLI skill
gate-info-research.
Before Trigger update, MCP tool selection, or any legacy Execution Workflow, run a deterministic shell probe:
PRIMARY_SKILL="gate-info-research"
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-research/SKILL.md
and its playbook contract. Carry over the minimum context: symbol.__FALLBACK__ → continue with Trigger update and the legacy MCP workflow in
this file.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.
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 $SKILL_ROOT/scripts/):
update-skill.sh exists → use only the Bash example.update-skill.ps1 exists → use only the PowerShell example..ps1 (typical ClawHub install): If only update-skill.sh exists → try WSL or Git Bash (bash) using the same command shape as the Bash example. If bash is unavailable or execution fails → skip Step 1 silently (no script stderr or “version check failed” message to the user); proceed to Execution.GATE_SKILL_CONFIRM_TOKEN or run apply / revoke-pending.Bash (blocking — no auto; example Cursor):
GATE_SKILL_CHECK_STRICT=1 bash "$HOME/.cursor/skills/gate-info-coinanalysis/scripts/update-skill.sh" check "gate-info-coinanalysis"
PowerShell:
$env:GATE_SKILL_CHECK_STRICT = '1'
powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.cursor\skills\gate-info-coinanalysis\scripts\update-skill.ps1" check "gate-info-coinanalysis"
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.
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:
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.
apply with GATE_SKILL_CONFIRM_TOKEN from strict check stdout when required, then Execution.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.
GATE_SKILL_CONFIRM_TOKEN="<paste from check stdout>" bash "$HOME/.cursor/skills/gate-info-coinanalysis/scripts/update-skill.sh" apply "gate-info-coinanalysis"
bash "$HOME/.cursor/skills/gate-info-coinanalysis/scripts/update-skill.sh" revoke-pending "gate-info-coinanalysis"
$env:GATE_SKILL_CONFIRM_TOKEN = '<paste from check stdout>'
powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.cursor\skills\gate-info-coinanalysis\scripts\update-skill.ps1" apply "gate-info-coinanalysis"
powershell -ExecutionPolicy Bypass -File "$env:USERPROFILE\.cursor\skills\gate-info-coinanalysis\scripts\update-skill.ps1" revoke-pending "gate-info-coinanalysis"
If Step 1 was not strict (no pending token): apply without GATE_SKILL_CONFIRM_TOKEN is allowed.
If skipped or check_failed: no update step; proceed to Execution.
GATE_SKILL_UPDATE_MODE=autoFor CI / unattended automation only: setting GATE_SKILL_UPDATE_MODE=auto on check makes the script apply immediately when the remote is newer — no user confirmation and incompatible with blocking update confirmation tests. Do not use auto on check when reproducing the blocking PD flow.
name above; must match skills/<name>/ on gate-skills.$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).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.
Legacy path only — this section applies when Step 0 emitted __FALLBACK__.
| MCP Server | Status |
|---|---|
| Gate-Info | ✅ Required |
Query Operations (Read-only)
Legacy path only — when Step 0 emitted __ROUTE_CLI__, routing is delegated to
gate-info-research.
| User Intent | Keywords | Action |
|---|---|---|
| Single coin comprehensive analysis | "analyze SOL" "how is BTC" "is ETH worth buying" | Execute this Skill's full workflow |
| Price only | "what's BTC price" "ETH current price" | Do NOT use this Skill — call info_marketsnapshot_get_market_snapshot directly |
| Multi-coin comparison | "compare BTC and ETH" | Route to gate-info-coincompare |
| News only | "any SOL news lately" | Route to gate-news-briefing |
| Technicals only | "BTC technical analysis" "what's the RSI" | Route to gate-info-trendanalysis |
Legacy path only — this section applies when Step 0 emitted __FALLBACK__.
Before executing this Skill, check if the user's query involves multiple analysis dimensions:
gate-info-research — it handles multi-dimension queries with unified tool deduplication and coherent report aggregation.Extract from user input:
symbol: Coin ticker (e.g., BTC, SOL, ETH)If the coin cannot be identified, ask the user to clarify the coin name — do not guess.
| Step | MCP Tool | Parameters | Retrieved Data | Parallel |
|---|---|---|---|---|
| 1a | info_coin_get_coin_info |
query={symbol}, scope="full" |
Fundamentals: project info, team, funding, sector, tokenomics, unlock schedule | Yes |
| 1b | info_marketsnapshot_get_market_snapshot |
symbol={symbol}, timeframe="1d", source="spot" |
Market data: price, 24h/7d change, market cap, OI, funding rate, Fear & Greed Index | Yes |
| 1c | info_markettrend_get_technical_analysis |
symbol={symbol} |
Technicals: multi-timeframe signals (RSI zones, MACD cross, MA alignment, support/resistance) | Yes |
| 1d | news_feed_search_news |
coin={symbol}, limit=5, sort_by="importance" |
News: top 5 most important recent articles | Yes |
| 1e | news_feed_get_social_sentiment |
coin={symbol} |
Social sentiment: Twitter KOL discussion volume, sentiment bias | Yes |
All 5 Tools are called in parallel with no dependencies. If no news MCP is configured, call only the first 3 Gate-info tools; mark sentiment sections as "No data".
Pass all 5 Tool responses to the LLM to generate a structured analysis report.
Legacy path only — this section applies when Step 0 emitted __FALLBACK__.
## {symbol} Comprehensive Analysis
### 1. Fundamentals Overview
| Metric | Value |
|--------|-------|
| Project Name | {project_name} |
| Sector | {category} |
| Market Cap Rank | #{market_cap_rank} |
| Circulating Market Cap | ${market_cap} |
| Fully Diluted Valuation | ${fdv} |
| Total Funding Raised | ${total_funding} |
| Key Investors | {investors} |
{Brief analysis of tokenomics and unlock schedule; flag any upcoming large unlocks}
### 2. Market Data & Technical Analysis
**Current Market Data**
| Metric | Value | Status |
|--------|-------|--------|
| Price | ${price} | — |
| 24h Change | {change_24h}% | {Up/Down/Sideways} |
| 7d Change | {change_7d}% | {Up/Down/Sideways} |
| 24h Volume | ${volume_24h} | {High/Low/Normal} |
| RSI(14) | {rsi} | {Overbought/Oversold/Neutral} |
| Fear & Greed Index | {fear_greed} | {Extreme Fear/Fear/Neutral/Greed/Extreme Greed} |
**Technical Signals**
{Based on info_markettrend_get_technical_analysis multi-timeframe signals, give a Bullish/Bearish/Neutral overall assessment}
- Short-term (1h/4h): {signal}
- Medium-term (1d): {signal}
- Support: ${support}
- Resistance: ${resistance}
### 3. News & Market Sentiment
**Recent Key News**
1. [{title}]({source}) — {summary} ({time})
2. ...
**Social Sentiment**
- Twitter Discussion Volume: {level}
- KOL Sentiment Bias: {Bullish/Bearish/Neutral}
- Sentiment Score: {sentiment_score}
### 4. Overall Assessment
{LLM generates a 3-5 sentence assessment covering:}
- Current market phase for this asset
- Primary drivers (fundamentals / technicals / sentiment)
- Key risks to monitor
### ⚠️ Risk Warnings
{Data-driven risk alerts, e.g.:}
- RSI overbought — elevated short-term pullback risk
- Upcoming large token unlock
- High funding rate — leveraged long crowding
- Low liquidity (if applicable)
> The above analysis is data-driven and does not constitute investment advice. Please make decisions based on your own risk tolerance.
| Condition | Assessment |
|---|---|
| RSI > 70 | Flag "Overbought — elevated short-term pullback risk" |
| RSI < 30 | Flag "Oversold — potential bounce" |
| 24h volume > 7d avg volume x 2 | Flag "Significant volume surge" |
| 24h volume < 7d avg volume x 0.5 | Flag "Notable volume decline" |
| funding_rate > 0.05% | Flag "High funding rate — long crowding" |
| funding_rate < -0.05% | Flag "Negative funding rate — short crowding" |
| fear_greed > 75 | Flag "Extreme Greed — exercise caution" |
| fear_greed < 25 | Flag "Extreme Fear — potential opportunity" |
| Token unlock in next 30 days > 5% of circulating supply | Flag "Large upcoming token unlock — potential sell pressure" |
| Any Tool returns empty/error | Skip that section; note "Data unavailable" in the report |
| Error Type | Handling |
|---|---|
| Coin does not exist | Prompt user to verify the coin name; suggest using info_coin_search_coins |
| A single Tool times out | Skip that dimension; note "This dimension is temporarily unavailable" |
| All Tools fail | Return error message; suggest the user try again later |
| User inputs multiple coins | Route to gate-info-coincompare |
| User inputs an address instead of a coin | Route to gate-info-addresstracker |
| User Follow-up Intent | Route To |
|---|---|
| "Give me a technical analysis" | gate-info-trendanalysis |
| "Any recent news?" | gate-news-briefing |
| "What about on-chain data?" | gate-info-tokenonchain |
| "Is this coin safe?" | gate-info-riskcheck |
| "Compare XX and YY" | gate-info-coincompare |
| "Why is it pumping/dumping?" | gate-news-eventexplain |
