mcpbeat Sign in

Comps Agent Skill

Comparable company analysis, trading comps, peer multiples, EV/EBITDA comparison, P/E benchmarking, comps table, relative valuation, industry multiples, precedent transactions, trading comparable analysis

4k tokens
context cost
the whole folder, loaded on every use
7
files
instructions only
0
copies elsewhere
how many repositories repackaged it
108
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/agentii-ai/agentii-investment-intelligence --skill comps

What comes with it

6 550 bytes besides the instruction
references/formula-sheet.md
references/institutional-defaults.md
references/methodology.md
references/output-structure.md
references/tool-fallbacks.md
references/validation-checklist.md

The instruction itself

17 sections, as written by the author

Preflight

Run the canonical pre-flight sequence — MCP health probe, ticker resolution, workspace style.md override, memory load, and coverage check. See contracts/preflight.md.

Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md.

Triggers

  • analyze comps analysis
  • run comps analysis analysis
  • produce comps analysis report
  • comps analysis breakdown
  • comps analysis deep dive
  • build a comps analysis
  • assess comps analysis
  • quantify comps analysis
  • compare comps analysis across peers
  • review comps analysis for
  • generate comps analysis on
  • comps analysis for investment decision

Defaults

| Parameter | Default | Notes |

|---|---|---|

| lookback_years | 3 | Historical data window |

| include_peers | false | Whether to surface a peer comparison block |

Methodology

Retrieval Scope

This skill performs unstructured document search at scale across SEC filings (10-K, 10-Q, 8-K). The three-layer agent-use-ready retrieval protocol (Document Discovery → Page Map → Deep Read) applies to all unstructured document search at scale.

Retrieval Strategy

See contracts/retrieval.md for the canonical decision tree; skill-specific retrieval detail is in references/methodology.md.

Temporal Scope

Default: 12 fiscal quarters (max 20). Financial modeling: trailing 12 quarters (3 fiscal years) for long-range projection inputs.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

Step-by-step execution detail is in references/methodology.md.

Deliverable Chain

InputsBuildValidateOutputNext

  • Inputs: resolved ticker + peers via search_companies + search_xbrl_facts for all tickers (revenue, EBITDA, EPS, multiples) + get_company_financials.
  • Build: write a self-contained Python script using openpyxl that creates the comps workbook (peer profiles, trading multiples, valuation summary) per ## Output Structure. Execute via Bash: python3 script.py. Verify the .xlsx exists. If import openpyxl fails, fall back to .md summary with data_availability: degraded (see contracts/office-tooling.md).
  • Validate: run LibreOffice recalc; audit per ## Validation Gates.
  • Output: write the artifact path per ## Output File.
  • Next: append to agentii.md; hand off to a downstream pitch/review skill if requested.

Validation Gates

  • peer count: between 4 and 8. *If failed*: If < 4: flag in Coverage Gaps, proceed with available peers. If > 8: trim to top 8 by sector proximity.
  • trading multiples: include EV/EBITDA + P/E at minimum. *If failed*: If either missing: flag which multiple is unavailable and why.
  • comps statistics table: present with mean, median, high, low for each multiple. *If failed*: If statistics table missing: refuse delivery.
  • tool diversity: distinct MCP tools used in this invocation >= min_tool_diversity (5). *If failed*: flag as depth-insufficient in Coverage Gaps, listing which tool categories were unused (structured data / document retrieval / company metadata / earnings calendar / coverage). This gate does NOT block analysis completion — it is a quality signal for your review.

Tool Fallbacks

Per-tool failure modes and fallback actions are tabulated in references/tool-fallbacks.md.

Output File

Write the final deliverable to _cross/{descriptive-slug}_{YYYY-MM-DD_HHMM}_comps_{affix}.md or _sector/{sector_name}/{YYYY-MM-DD_HHMM}_comps_{affix}.md .

Output Structure

The deliverable is a structured markdown report written to the path in ## Output File. Full section-by-section template (headings, tables, and field definitions) lives in references/output-structure.md. Required elements:

  • Executive Summary — headline conclusions (≤200 words).
  • Core analysis sections — per this skill's methodology and analyst modes.
  • Data classification — tag findings [FACT] / [DEDUCTED] / [VIEW] per contracts/snapshot-synthesis.md.
  • Coverage Gaps & Citations — inline /v/ citations are PRIMARY (immediately after each fact); the bottom Citations section is a non-duplicative roll-up index.
  • Output frontmatter — emit the FR-090 structured block per contracts/output-frontmatter-schema.md.

Citations & memory: follow contracts/citation-and-memory.md — ≥1 citation per 200 words; every material fact, table row, and metric is immediately followed by its inline clickable https://agentii.ai/v/{ticker}/{citation_id}/{N} link; a bottom Citations section provides a non-duplicative roll-up index; the closing TUI reply includes a compact Key Citations list (headline 5–10 facts) of clickable /v/ URLs; and append the run to agentii.md per contracts/agentii-md-schema.md.

Memory & Snapshot

  • Memory load (pre-flight): load prior workspace context for the ticker before retrieval — see contracts/memory-load.md.
  • Structured output frontmatter: emit the FR-090 block (key_metrics, conclusions, facts_count, deducted_count, views_count, citation_count) per contracts/output-frontmatter-schema.md.
  • Snapshot synthesis: after writing the deliverable, update the two-tier snapshot and classify findings as [FACT]/[DEDUCTED]/[VIEW] — see contracts/snapshot-synthesis.md.
  • Session archival: record the run under sessions/{YYYY-MM-DD}/ and update sessions/INDEX.md per contracts/session-format.md.

Final Summary (TUI)

End the closing chat reply with a compact Key Citations list (headline 5–10 facts), each a clickable https://agentii.ai/v/{ticker}/{citation_id}/{N} link, so the user can cmd+click straight to the exact SEC page. See contracts/citation-and-memory.md.

Error Handling

| Failure Mode | Detection | Action | User-Facing Message |

|---|---|---|---|

| Missing data | Data API returns empty result set | Widen date range and retry once | "No data available for {ticker} in requested window." |

| Partial data | Data API returns <80% expected records | Proceed with coverage gaps section | "Analysis based on partial data; see Coverage Gaps section." |

| Sector mismatch | Peer sector != target sector | Filter out mismatched peers | "Removed {n} peer(s) due to sector mismatch." |

| Insufficient history | Ticker <3 years on public markets | Downgrade to limited-history profile | "Limited historical data; analysis adjusted accordingly." |

| MCP unreachable | Preflight probe fails | Halt with actionable error | "agentii data plane unreachable; check connection." |

How to use it

Copy the folder

Take agentii-ai/comps from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.