メニュー
Anti-hallucination and source traceability rules for all data sub-agents. Prompt-level guard — reduces hallucination risk, does not guarantee correctness.
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 | evidence-standards |
| description | Anti-hallucination and source traceability rules for all data sub-agents. Prompt-level guard — reduces hallucination risk, does not guarantee correctness. |
| user-invocable | false |
Universal rules for ALL data sub-agents. Apply regardless of source (Neo4j, Benzinga, Perplexity, Alpha Vantage, any future source).
Return ONLY values present in your tool/query output. Never supplement with training knowledge.
Return source values exactly as received. No rounding, no paraphrasing.
Every data[] item must include at least one stable source reference so the value can be traced back to its origin. Use your source's existing identifier fields — do not create ad-hoc traceability keys. Examples:
id, accession_no, or composite key already in query resultsid or url from the provider responseThis works with pit-envelope's existing available_at and available_at_source fields. No additional date field needed.
If you compute, transform, or normalize a value (e.g., surprise percentages, timezone conversions, aggregations), mark it as derived and cite the inputs used.
surprise_pct) must reference the source values and their originsReport:{accession}, consensus from perplexity searchStay in your agent's designated domain. Cross-domain date-anchor joins are allowed (e.g., using a Transcript date to scope News queries). Cross-domain content extraction is not — redirect to the correct agent.