ワンクリックで
test-all-datasubagents-fork
Validate that a forked skill can invoke the full original data-subagent surface and record per-agent results.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Validate that a forked skill can invoke the full original data-subagent surface and record per-agent results.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Predict stock direction post 8-K earnings & refine using 10-Q/10-K outcomes
Predict stock direction after an 8-K earnings release from a prebuilt earnings context bundle
Post-event causal attribution — explains why a stock moved after 8-K earnings, compares against prediction, writes reusable lessons for future predictions. Production invocation via SDK embed (main session), not fork.
Core Neo4j schema reference with all labels, relationships, data types, and indexes. Use when exploring database structure, checking field types, or understanding the financial knowledge graph schema.
V1105_LONGDESC_START_MARKER. This skill tests v2.1.105's skill-description cap raise from 250 to 1536 characters. If this description appears truncated in the skill listing system-reminder at around character 250, the cap was not raised; if it appears truncated at around 1536, the cap was raised correctly per changelog. The test sentinel markers are placed at specific character offsets: V1105_OFFSET_100 is at char 100 approximately, V1105_OFFSET_300 is at char 300 approximately (old cap would truncate this), V1105_OFFSET_700 is at char 700 approximately, V1105_OFFSET_1000 is at char 1000, V1105_OFFSET_1200 is at char 1200, V1105_OFFSET_1400 is at char 1400, and V1105_END_MARKER is the last visible sentinel. This description also contains deliberately redundant filler to reach the target length without substantive content since the purpose is only to verify truncation behavior rather than to provide meaningful guidance. filler filler filler filler filler filler filler filler filler filler filler filler filler
Child skill for v2.1.107 nesting retest — writes marker and returns
| name | test-all-datasubagents-fork |
| description | Validate that a forked skill can invoke the full original data-subagent surface and record per-agent results. |
| context | fork |
| model | opus |
| effort | high |
| allowed-tools | Read, Write, Skill |
| skills | ["neo4j-report","neo4j-transcript","neo4j-xbrl","neo4j-entity","neo4j-news","neo4j-vector-search","alphavantage-earnings","yahoo-earnings","bz-news-api","perplexity-search","perplexity-ask","perplexity-reason","perplexity-research","perplexity-sec"] |
Validate whether this forked skill can invoke the complete original data-subagent surface.
Write the final report to:
earnings-analysis/test-outputs/test-all-datasubagents-fork.json
Also write a short human-readable summary to:
earnings-analysis/test-outputs/test-all-datasubagents-fork.txt
Rules:
/neo4j-report.invoke_ok: the slash command resolved and returned either data, a structured gap, or a provider/source error originating inside that subagent.invoke_failed: the slash command was unavailable, could not be called from this forked skill, or failed before reaching the subagent itself.Use these test prompts:
/neo4j-report
Prompt: Get one recent AAPL 8-K earnings filing. Return only the smallest useful result.
/neo4j-transcript
Prompt: Get one recent AAPL earnings call Q&A exchange. Return only the smallest useful result.
/neo4j-xbrl
Prompt: Get one recent AAPL revenue XBRL fact. Return only the smallest useful result.
/neo4j-entity
Prompt: Get AAPL company name and sector. Return only the smallest useful result.
/neo4j-news
Prompt: Get one recent AAPL earnings-related headline. Return only the smallest useful result.
/neo4j-vector-search
Prompt: Find one semantically relevant AAPL earnings-related news or transcript match. Return only the smallest useful result.
/alphavantage-earnings
Prompt: Get AAPL quarterly earnings actuals in open mode. Return only one recent item.
/yahoo-earnings
Prompt: Get one recent AAPL earnings or analyst-upgrade item. Return only the smallest useful result.
/bz-news-api
Prompt: Get one recent AAPL Benzinga news item. Return only the smallest useful result.
/perplexity-search
Prompt: Search for AAPL latest earnings transcript date. Return only the smallest useful result.
/perplexity-ask
Prompt: What was AAPL latest quarterly EPS versus consensus?
/perplexity-reason
Prompt: Why did AAPL stock react to its most recent earnings? Keep it brief.
/perplexity-research
Prompt: Research one concise fact about AAPL's most recent earnings reaction. Keep it minimal.
/perplexity-sec
Prompt: Find one recent AAPL 10-Q or 8-K filing URL from EDGAR. Return only the smallest useful result.
Output JSON shape:
{
"test_name": "test-all-datasubagents-fork",
"from_skill_context": true,
"results": [
{
"name": "neo4j-report",
"invocation_status": "invoke_ok",
"outcome_type": "data | gap | provider_error | invoke_failed",
"evidence": "short snippet"
}
],
"summary": {
"total": 14,
"invoke_ok_count": 0,
"invoke_failed_count": 0
}
}
For outcome_type:
data: returned usable datagap: subagent ran but returned a gap/no-data outcomeprovider_error: subagent ran but the upstream source/auth/provider failedinvoke_failed: slash command unavailable or call path itself failed