Revelata DeepKPI Financial Analysis Agent

Financial and operational KPI research for US public companies using Revelata's deepKPI database. Pulls structured metrics from SEC filings (10-K, 10-Q, 8-K)...

Security Scan

The skill's requests and runtime instructions are coherent with its stated purpose: it only needs a Revelata deepKPI API key and curl to call the documented REST endpoints and the docs constrain behaviour to deepKPI-sourced data and provenance links.

Purpose & Capability

Name/description (deepKPI KPI pulls, derivations, seasonality, Excel exports) match the declared requirements: a single API key (DEEPKPI_API_KEY) and curl. No unrelated credentials, binaries, or config paths are requested. The Claude/MCP vs OpenClaw fallback is documented and explains why the API key is required in some runtimes.

Instruction Scope

All runtime instructions in the SKILL.md and subsidiary docs are narrowly focused on querying deepKPI endpoints, deriving metrics from deepKPI-sourced operands, preserving provenance URLs, and formatting/exporting results. The docs do not instruct reading unrelated system files or environment variables, nor do they direct data to unexpected external endpoints beyond the documented deepkpi-api.revelata.com base URL. The workflow is prescriptive (e.g., always list_kpis, preserve provenance, offer Excel) but stays within the stated purpose.

Install Mechanism

Instruction-only skill with no install spec and no code files; this minimizes disk-write and supply-chain risk. Required binary is only curl, which is reasonable for making REST calls. No external downloads, package installs, or extract operations are present.

Credentials

Only one required environment variable (DEEPKPI_API_KEY) is declared and used. That is proportionate and expected for a REST API integration; no unrelated secrets or elevated credentials are requested.

Persistence & Privilege

The skill is not always-included (always:false) and does not request system persistence or to modify other skills. It can be invoked autonomously by the agent (platform default), which is expected for a data-access skill; this increases blast radius only in the sense that the agent could make API calls with the provided key if permitted by policy, but that is normal and documented.

Assessment

This skill appears internally consistent and low-risk because it is instruction-only and only requires a single API key plus curl. Before enabling it, ensure the DEEPKPI_API_KEY you provide is a legitimate Revelata key with appropriate (least) privilege and monitoring enabled—API keys grant access/credits and could be used to make calls on your behalf. Confirm you trust the source (Revelata) for billing/credits and provenance URLs. Note the skill will construct .xlsx files if you accept the file offer; ensure your agent/file-handling policies allow creating and sharing such files. If you prefer tighter control, consider providing a scoped or read-only API key, setting usage limits on the Revelata account, or enabling instrumentation/audit logs so you can review API requests and credit usage. Finally, because the skill enforces strict provenance and derivation rules, expect it to always attempt Q4 imputations for flow metrics and to require deepKPI evidence for numeric figures—this is by design but may affect how the agent responds if the API key is missing or credits are low.

deepKPI Financial Analysis and Research Tools

Query structured KPIs extracted from SEC filings for US public companies. Powered by Revelata.

This skill suite covers different aspects of financial analysis workflows. This includes data access via MCP for Claude or REST API for OpenClaw, data retrieval, metric derivation, seasonality analysis, and Excel export. Sub-skills are organized so that each layer can be loaded independently — only read what the task requires.

Data access — Claude vs. OpenClaw

The three deepKPI operations (query_company_id, list_kpis, search_kpis) are available two ways depending on the runtime:

Runtime	How to call deepKPI
Claude (MCP tools available)	Use the native MCP tools directly — no API key or deepkpi-api skill needed
OpenClaw (no MCP)	Read deepkpi-api/deepkpi-api.md and call the REST endpoints using $DEEPKPI_API_KEY

retrieve-kpi-data/retrieve-kpi-data.md contains the full context-detection table and will direct you to the right method. The DEEPKPI_API_KEY env var and deepkpi-api reference doc are only needed in OpenClaw (or as an env-var fallback when MCP is unavailable).

Sub-skill routing

Read the relevant reference doc(s) before doing any work. Multiple docs may apply to a single request — load all that are relevant.

User need	File to read
Pull historical KPIs / financials from deepKPI	retrieve-kpi-data/retrieve-kpi-data.md
Derive missing Q4 numbers, a segment remainder, or per-unit economics (ASP, ARPU, AUV, take rate)	derive-implied-metric/derive-implied-metric.md
Split annual forecasts into quarterly estimates / seasonality patterns	analyze-seasonality/analyze-seasonality.md
Produce an Excel workbook (.xlsx) from deepKPI data	format-deepkpi-for-excel/format-deepkpi-for-excel.md
REST API calls (OpenClaw / env-var fallback only)	deepkpi-api/deepkpi-api.md

Default entry point: Start with retrieve-kpi-data/retrieve-kpi-data.md for almost every request. It orchestrates the full retrieval workflow and references the other docs as needed (e.g. it will direct you to derive-implied-metric for Q4 gaps and to format-deepkpi-for-excel for Excel output).

Sub-skill summary

deepkpi-api — Raw REST access to the three deepKPI endpoints: query_company_id, list_kpis, search_kpis. OpenClaw / env-var fallback only — in Claude, use the native MCP tools instead.

retrieve-kpi-data — The primary data-pull workflow. Covers company ID resolution, KPI discovery, search strategy, gap handling (including Q4 derivation), provenance rules, in-chat table layout, and the mandatory post-pull Excel offer.

derive-implied-metric — Compute metrics that deepKPI doesn't report directly from data that IS reported: Q4 = FY − (Q1+Q2+Q3), missing segment = total − known segments, per-unit economics (revenue per store, ARPU, ASP), take rates, penetration rates, and geographic mix percentages.

analyze-seasonality — Compute each quarter's typical share of the full fiscal year from 2–3 years of actuals, then apply those ratios to split an annual projection into quarterly estimates.

format-deepkpi-for-excel — Canonical layout and styling spec for any .xlsx export built from deepKPI data: wide layout with periods as columns (annual block → blank column → quarterly block), Calibri font, green input cells, clickable hyperlinks in cells, numeric date headers, freeze panes, column grouping, and no redundant Source rows.