{"slug":"supply-chain","title":"supply-chain","summary":"Supply chain mapping, supplier dependency analysis, customer concentration, geographic concentration, bottleneck identification, supply chain risk, logistics network, sourcing strategy, inventory management, vertical integration analysis","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-15T18:28:46.961567Z","repo":{"url":"https://github.com/agentii-ai/agentii-investment-intelligence","stars":203,"forks":16,"license":"Apache-2.0","updatedAt":"2026-09-21T11:07:34Z"},"bodyHtml":"<hr>\n<p>name: supply-chain\nmulti_ticker_semantics: target_with_optional_peers\ndescription: Supply chain mapping, supplier dependency analysis, customer concentration, geographic concentration, bottleneck identification, supply chain risk, logistics network, sourcing strategy, inventory management, vertical integration analysis\ntemporal_scope:\ndefault_quarters: 4\nmax_quarters: 10\ndescription: \"Typical lookback: 4 quarters, max: 10\"\nallowed_tools:</p>\n<ul>\n<li>search_companies</li>\n<li>search_xbrl_facts</li>\n<li>search_documents</li>\n<li>search_sec_filings</li>\n<li>get_company_financials</li>\n<li>list_coverage</li>\n<li>read_source_outline</li>\n<li>read_source_deep_outline</li>\n<li>list_xbrl_concepts</li>\n<li>read_source_pages</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: 8</li>\n</ul>\n<hr>\n<h1>supply-chain</h1>\n<h2>Triggers</h2>\n<ul>\n<li>Supply chain mapping</li>\n<li>supplier dependency analysis</li>\n<li>customer concentration</li>\n<li>geographic concentration</li>\n<li>bottleneck identification</li>\n<li>supply chain risk</li>\n<li>logistics network</li>\n<li>sourcing strategy</li>\n<li>inventory management</li>\n<li>vertical integration analysis</li>\n</ul>\n<h2>Defaults</h2>\n<table>\n<thead>\n<tr>\n<th>Parameter</th>\n<th>Default Value</th>\n<th>Rationale</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>ticker</td>\n<td>(required)</td>\n<td>Stock symbol to analyze</td>\n</tr>\n<tr>\n<td>lookback_quarters</td>\n<td>4</td>\n<td>Standard lookback for this skill type</td>\n</tr>\n</tbody>\n</table>\n<h2>Methodology</h2>\n<h3>1. Retrieval Scope</h3>\n<p>This skill operates with <code>retrieval_scope: unstructured_document_search</code>. It performs unstructured document search at scale via the three-layer retrieval protocol (Layer 1→2→2.5→3), escalating to <code>read_source_deep_outline</code> only when lightweight labels cannot disambiguate pages, plus structured XBRL where needed.</p>\n<h3>2. Retrieval Strategy</h3>\n<p>Follows the retrieval strategy decision tree in <code>contracts/retrieval.md</code>. Primary branch: <strong>(b)/(c) Unstructured Query via the three-layer protocol</strong>. Resolve the canonical ticker first (exact → fuzzy alias → share-class) before any data call.</p>\n<h3>3. Temporal Scope</h3>\n<p>Default lookback: 4 fiscal quarter(s); maximum: 10. The default balances recency against the trend window this analysis requires.</p>\n<h3>4. Tool Allowlist</h3>\n<p>Per frontmatter <code>allowed_tools</code>:</p>\n<ul>\n<li><code>search_companies</code> — ticker resolution + company context (entity-alias fuzzy match)</li>\n<li><code>search_xbrl_facts</code> — primary structured financial facts (is_primary default)</li>\n<li><code>search_documents</code> — Layer 1 document discovery (page-level silver records)</li>\n<li><code>search_sec_filings</code> — Layer 1 SEC filing metadata index</li>\n<li><code>get_company_financials</code> — consolidated IS/BS/CF highlights</li>\n<li><code>list_coverage</code> — universe-level coverage discovery</li>\n<li><code>read_source_outline</code> — Layer 2 lightweight page map (description + keywords)</li>\n<li><code>read_source_deep_outline</code> — Layer 2.5a deep page map (table_titles/drivers/metrics)</li>\n<li><code>list_xbrl_concepts</code> — XBRL concept discovery for non-standard line items (<code>namespace</code> param; default <code>us-gaap</code> — use <code>ifrs-full</code> for foreign filers)</li>\n<li><code>read_source_pages</code> — Layer 3 deep read of selected pages with table markers</li>\n<li><code>search_keyword_in_source</code> — Layer 2.5b keyword page filter for large documents</li>\n</ul>\n<h3>5. Protocol</h3>\n<ol>\n<li><strong>Pre-flight (mandatory)</strong>: <code>get_company_fiscal_calendar/{ticker}</code> then <code>get_ticker_coverage/{ticker}</code>; route on coverage.</li>\n<li><strong>Layer 1 — discovery</strong>: <code>search_documents</code> / <code>search_sec_filings</code> to find candidate filings by ticker/form_type/date.</li>\n<li><strong>Layer 2 — page map</strong>: <code>read_source_outline/{ticker}/{citation_id}</code>; skip NULL-description pages; escalate to <code>read_source_deep_outline</code> only when labels can't disambiguate.</li>\n<li><strong>Layer 2.5 (optional)</strong>: <code>search_keyword_in_source</code> to narrow documents &gt;50 pages.</li>\n<li><strong>Layer 3 — deep read</strong>: <code>read_source_pages/{ticker}/{citation_id}?pages=page&lt;N&gt;,...</code> for the 3–5 selected pages only.</li>\n<li><strong>Multi-period</strong> (if applicable): <code>search_cross_period</code> after fiscal-calendar resolution.</li>\n<li><strong>Output</strong>: write the deliverable per <code>## Output File</code>, then append to <code>agentii.md</code>.</li>\n</ol>\n<h2>Output File</h2>\n<p>Write the final deliverable to <code>_cross/{descriptive-slug}_{YYYY-MM-DD_HHMM}_supply-chain_{affix}.md</code> or <code>_sector/{sector_name}/{YYYY-MM-DD_HHMM}_supply-chain_{affix}.md</code> .</p>\n<h2>Output Structure</h2>\n<ol>\n<li><strong>Executive Summary</strong> (≤200 words) — headline conclusions for the analysis.</li>\n<li><strong>Data Sources</strong> — filings + structured endpoints used, with <code>{ticker} {citation_id} page&lt;N&gt;</code> citations.</li>\n<li><strong>Analysis</strong> — the core findings, tables, and commentary for this dimension.</li>\n<li><strong>Key Metrics</strong> — the quantitative results with QoQ/YoY context where relevant.</li>\n<li><strong>Coverage Gaps &amp; Citations</strong> — data not retrievable + citation index.</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>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>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>Error</th>\n<th>Action</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>Ticker not found</td>\n<td>Suggest checking spelling or trying list_coverage</td>\n</tr>\n<tr>\n<td>No data available</td>\n<td>Flag in Coverage Gaps, proceed with available data</td>\n</tr>\n<tr>\n<td>API key invalid</td>\n<td>Direct user to agentii.ai/api-keys</td>\n</tr>\n<tr>\n<td>MCP server unreachable</td>\n<td>Retry once; if persistent, halt with AGENTII_MCP_UNREACHABLE</td>\n</tr>\n</tbody>\n</table>\n<h2>References</h2>\n<ul>\n<li><strong>Methodology</strong>: <a href=\"references/methodology.md\"><code>references/methodology.md</code></a> — tool fallbacks, retrieval strategy, analysis framework</li>\n<li><strong>Output Structure</strong>: <a href=\"references/output-structure.md\"><code>references/output-structure.md</code></a> — detailed deliverable sections and ordering</li>\n</ul>\n","files":[{"path":"references/knowledge-frameworks.md","sizeBytes":775,"isText":true},{"path":"references/methodology.md","sizeBytes":1106,"isText":true},{"path":"references/modes.md","sizeBytes":712,"isText":true},{"path":"references/output-structure.md","sizeBytes":963,"isText":true},{"path":"SKILL.md","sizeBytes":6993,"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":"2026-09-15T18:29:21.277882Z","sha256":"2CC472881FD712CE5ECD46065657DD7B3EE23D83F3B07CDB37347371831B70E3","sizeBytes":5413},"review":null,"source":{"repositoryUrl":"https://github.com/agentii-ai/agentii-investment-intelligence","path":"plugins/vertical-plugins/industry-analysis/skills/agentii/supply-chain","license":"Apache-2.0","commit":"1a2d679a82960cb0033b30da7fc895b2674337a3","subtreeSha":"E8860FBE605BBFE27B39E888B8C834ADF8A4141796A059A5479C504BDFD12289","lastSyncedAt":"2026-09-21T13:50:39.960822Z"},"reviewedAt":"2026-09-15T18:38:52.341625Z","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/industry-analysis/skills/agentii/supply-chain"},{"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"}]}