{"slug":"earnings-sentiment","title":"earnings-sentiment","summary":"Earnings sentiment analysis, analyst estimates vs guidance, earnings surprise history, consensus sentiment, earnings revision trends, analyst rating changes, earnings beat miss track record, guidance accuracy, whisper numbers, pre-announcement sentiment","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-15T18:28:43.83709Z","repo":{"url":"https://github.com/agentii-ai/agentii-investment-intelligence","stars":206,"forks":16,"license":"Apache-2.0","updatedAt":"2026-09-29T07:17:16Z"},"bodyHtml":"<hr>\n<p>name: earnings-sentiment\nmulti_ticker_semantics: single_target\ndescription: Earnings sentiment analysis, analyst estimates vs guidance, earnings surprise history, consensus sentiment, earnings revision trends, analyst rating changes, earnings beat miss track record, guidance accuracy, whisper numbers, pre-announcement sentiment\nessentials_modes: [analyst-sentiment-assessment-current-quarter, fy0-analyst-estimates-extraction, current-quarter-fiscal-year-analyst-estimates]\ntemporal_scope:\ndefault_quarters: 4\nmax_quarters: 8\ndescription: \"Typical lookback: 4 quarters, max: 8\"\nallowed_tools:</p>\n<ul>\n<li>search_companies</li>\n<li>search_xbrl_facts</li>\n<li>search_documents</li>\n<li>read_source_outline</li>\n<li>read_source_deep_outline</li>\n<li>read_source_pages</li>\n<li>search_earnings_calendar</li>\n<li>get_company_financials</li>\n<li>get_company_profile</li>\n<li>list_xbrl_concepts</li>\n<li>search_keyword_in_source</li>\n<li>search_knowledge_entries</li>\n<li>get_knowledge_entry</li>\n<li>search_by_analogue\nretrieval_scope: unstructured_document_search\nmin_tool_diversity: 10</li>\n</ul>\n<hr>\n\n<h2>Preflight</h2>\n<p>Run the canonical pre-flight sequence — MCP health probe, ticker resolution, workspace <code>style.md</code> override, memory load, and coverage check. See <code>contracts/preflight.md</code>.</p>\n<p>Include the <code>X-Agentii-Trace</code> header on every tool call per <code>contracts/x-agentii-trace-header.md</code>.</p>\n<h2>Triggers</h2>\n<ul>\n<li>analyze dim earnings sentiment</li>\n<li>run dim earnings sentiment analysis</li>\n<li>produce dim earnings sentiment report</li>\n<li>dim earnings sentiment breakdown</li>\n<li>dim earnings sentiment deep dive</li>\n<li>build a dim earnings sentiment</li>\n<li>assess dim earnings sentiment</li>\n<li>quantify dim earnings sentiment</li>\n<li>compare dim earnings sentiment across peers</li>\n<li>review dim earnings sentiment for</li>\n<li>generate dim earnings sentiment on</li>\n<li>dim earnings sentiment for investment decision</li>\n</ul>\n<h2>Defaults</h2>\n<table>\n<thead>\n<tr>\n<th>Parameter</th>\n<th>Default</th>\n<th>Notes</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>lookback_years</td>\n<td>3</td>\n<td>Historical data window</td>\n</tr>\n<tr>\n<td>include_peers</td>\n<td>false</td>\n<td>Whether to surface a peer comparison block</td>\n</tr>\n</tbody>\n</table>\n\n<h2>Methodology</h2>\n<h3>Retrieval Scope</h3>\n<p>This skill performs unstructured document search at scale (10-K, 10-Q, 8-K filings and earnings call transcripts spanning multiple fiscal periods). The three-layer agent-use-ready retrieval protocol (Document Discovery → Page Map → Deep Read) applies to all unstructured document search at scale.</p>\n<h3>Retrieval Strategy</h3>\n<p><strong>Ownership &amp; insider signals</strong>: <code>search_institutional_holdings</code> (top-10 holders + whale portfolios, <code>direction=accumulating|reducing|new|exited</code>) and <code>search_insider_trades</code> (Form-4 transactions with SEC URLs) are available as signal inputs.</p>\n<p>See <code>contracts/retrieval.md</code> for the canonical decision tree; skill-specific retrieval detail is in <code>references/methodology.md</code>.</p>\n<h3>Temporal Scope</h3>\n<p>Default: 4 fiscal quarters (max 8). Earnings sentiment: trailing 4 quarters for earnings-call tone and guidance trends</p>\n<h3>Tool Allowlist</h3>\n<p>See frontmatter <code>allowed_tools</code>.</p>\n<h3>Protocol</h3>\n<p>Step-by-step execution detail is in <code>references/methodology.md</code>.</p>\n<h3>Analyst Modes</h3>\n<p>This skill exposes addressable analysis modes (<code>--mode=&lt;slug&gt;</code> / <code>--modes=&lt;s1&gt;,&lt;s2&gt;</code> / <code>--mode=all</code>; see <a href=\"../../../../docs/commands/MODE_SYNTAX.md\">Mode syntax</a>). The full mode definitions and their output templates live in <code>references/modes.md</code>. The default invocation runs the essentials subset.</p>\n<h2>Tool Fallbacks</h2>\n<p>Per-tool failure modes and fallback actions are tabulated in <code>references/tool-fallbacks.md</code>.</p>\n<h2>Output File</h2>\n<p>Write the final deliverable to <code>{ticker}/{YYYY-MM-DD_HHMM}_earnings-sentiment_analyst-sentiment.md</code> .</p>\n<h2>Output Structure</h2>\n<p>The deliverable is a structured markdown report written to the path in <code>## Output File</code>. Full section-by-section template (headings, tables, and field definitions) lives in <code>references/output-structure.md</code>. Required elements:</p>\n<ol>\n<li><strong>Executive Summary</strong> — headline conclusions (≤200 words).</li>\n<li><strong>Core analysis sections</strong> — per this skill's methodology and analyst modes.</li>\n<li><strong>Data classification</strong> — tag findings <code>[FACT]</code> / <code>[DEDUCTED]</code> / <code>[VIEW]</code> per <code>contracts/snapshot-synthesis.md</code>.</li>\n<li><strong>Coverage Gaps &amp; Citations</strong> — inline <code>/v/</code> citations are PRIMARY (immediately after each fact); the bottom <strong>Citations</strong> section is a non-duplicative roll-up index.</li>\n<li><strong>Output frontmatter</strong> — emit the FR-090 structured block per <code>contracts/output-frontmatter-schema.md</code>.</li>\n</ol>\n<p><strong>Citations &amp; memory</strong>: follow <code>contracts/citation-and-memory.md</code> — ≥1 citation per 200 words; every material fact, table row, and metric is immediately followed by its inline clickable <code>https://agentii.ai/v/{ticker}/{citation_id}/{N}</code> link; a bottom <strong>Citations</strong> section provides a non-duplicative roll-up index; the closing TUI reply includes a compact <strong>Key Citations</strong> list (headline 5–10 facts) of clickable <code>/v/</code> URLs; and append the run to <code>agentii.md</code> per <code>contracts/agentii-md-schema.md</code>.</p>\n<h2>Memory &amp; Snapshot</h2>\n<ul>\n<li><strong>Memory load</strong> (pre-flight): load prior workspace context for the ticker before retrieval — see <code>contracts/memory-load.md</code>.</li>\n<li><strong>Structured output frontmatter</strong>: emit the FR-090 block (<code>key_metrics</code>, <code>conclusions</code>, <code>facts_count</code>, <code>deducted_count</code>, <code>views_count</code>, <code>citation_count</code>) per <code>contracts/output-frontmatter-schema.md</code>.</li>\n<li><strong>Snapshot synthesis</strong>: after writing the deliverable, update the two-tier snapshot and classify findings as <code>[FACT]</code>/<code>[DEDUCTED]</code>/<code>[VIEW]</code> — see <code>contracts/snapshot-synthesis.md</code>.</li>\n<li><strong>Session archival</strong>: record the run under <code>sessions/{YYYY-MM-DD}/</code> and update <code>sessions/INDEX.md</code> per <code>contracts/session-format.md</code>.</li>\n</ul>\n<h2>Final Summary (TUI)</h2>\n<p>End the closing chat reply with a compact <strong>Key Citations</strong> list (headline 5–10 facts), each a clickable <code>https://agentii.ai/v/{ticker}/{citation_id}/{N}</code> link, so the user can cmd+click straight to the exact SEC page. See <code>contracts/citation-and-memory.md</code>.</p>\n<h2>Error Handling</h2>\n<table>\n<thead>\n<tr>\n<th>Failure Mode</th>\n<th>Detection</th>\n<th>Action</th>\n<th>User-Facing Message</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>Missing data</td>\n<td>Data API returns empty result set</td>\n<td>Widen date range and retry once</td>\n<td>\"No data available for  in requested window.\"</td>\n</tr>\n<tr>\n<td>Partial data</td>\n<td>Data API returns &lt;80% expected records</td>\n<td>Proceed with coverage gaps section</td>\n<td>\"Analysis based on partial data; see Coverage Gaps section.\"</td>\n</tr>\n<tr>\n<td>Sector mismatch</td>\n<td>Peer sector != target sector</td>\n<td>Filter out mismatched peers</td>\n<td>\"Removed  peer(s) due to sector mismatch.\"</td>\n</tr>\n<tr>\n<td>Insufficient history</td>\n<td>Ticker &lt;3 years on public markets</td>\n<td>Downgrade to limited-history profile</td>\n<td>\"Limited historical data; analysis adjusted accordingly.\"</td>\n</tr>\n<tr>\n<td>MCP unreachable</td>\n<td>Preflight probe fails</td>\n<td>Halt with actionable error</td>\n<td>\"agentii data plane unreachable; check connection.\"</td>\n</tr>\n</tbody>\n</table>\n","files":[{"path":"references/knowledge-frameworks.md","sizeBytes":2227,"isText":true},{"path":"references/methodology.md","sizeBytes":2021,"isText":true},{"path":"references/modes.md","sizeBytes":11508,"isText":true},{"path":"references/output-structure.md","sizeBytes":2187,"isText":true},{"path":"references/tool-fallbacks.md","sizeBytes":1847,"isText":true},{"path":"references/wsp-methodology.md","sizeBytes":5439,"isText":true},{"path":"SKILL.md","sizeBytes":7372,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-29T20:56:01.085742Z","sha256":"1EAA68BCA1672630046D5A6B5D7F4196A55859C1FC8B97E50CE3B944B3D9167A","sizeBytes":13683},"review":null,"source":{"repositoryUrl":"https://github.com/agentii-ai/agentii-investment-intelligence","path":"plugins/vertical-plugins/equity-research-core/skills/agentii/earnings-sentiment","license":"Apache-2.0","commit":"86980e14fb983bb4b9a81343009edab65442bbc2","subtreeSha":"AF7AC5956FB68B99EDEF13AD4A063E37EFE2841040670D67FF754ED1ADD1CDA6","lastSyncedAt":"2026-09-29T20:55:34.463295Z"},"reviewedAt":"2026-09-29T20:56:46.786978Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/agentii-ai/agentii-investment-intelligence/tree/main/plugins/vertical-plugins/equity-research-core/skills/agentii/earnings-sentiment"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install agentii-ai-agentii-investment-intelligence@llmmart"},{"target":"git","command":"git clone https://github.com/agentii-ai/agentii-investment-intelligence.git"}]}