Earnings Sentiment Analysis
An equity-research skill that mines SEC filings and earnings materials to produce a cited report on analyst estimates vs guidance, surprise history and consensus revision trends.
What it does
Runs a single-ticker earnings sentiment workup over the trailing 4 fiscal quarters (max 8).
- Covers analyst estimates vs company guidance, beat/miss track record, consensus revision trends, rating changes and whisper-number context.
- Searches unstructured filings (10-K, 10-Q, 8-K) with a three-layer retrieval protocol: document discovery → page map → deep read.
- Writes a structured markdown deliverable to
{ticker}/{YYYY-MM-DD_HHMM}_earnings-sentiment_analyst-sentiment.md, with a clickable/v/citation immediately after every material fact and a roll-up Citations index. - Classifies findings as
[FACT]/[DEDUCTED]/[VIEW], emits FR-090 output frontmatter, and archives the run to session memory. - Ships an explicit error-handling table (missing data, partial coverage, sector-mismatched peers, sub-3-year listing history, MCP unreachable).
Who it's for
- Equity research analysts and buy-side research teams
- Anyone who repeatedly parses SEC filings to write earnings notes
- Users who already run the agentii MCP data plane (or an equivalent SEC/XBRL tool set)
Note: without tools like
search_xbrl_factsandsearch_earnings_calendar, the skill halts at preflight.
Examples
- "Analyze earnings sentiment for NVDA" → 4-quarter guidance-vs-actual and consensus revision report.
- "Compare earnings sentiment across peers" → enables the
include_peersblock; off-sector peers are auto-filtered out. - Invoke with
--mode=allto run the full analyst mode set instead of the default essentials subset.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/agentii-ai/agentii-investment-intelligence/HEAD/plugins/agent-plugins/agentii-equity-agent/skills/agentii/earnings-sentiment/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the plugins/agent-plugins/agentii-equity-agent/skills/agentii/earnings-sentiment folder from the GitHub repo agentii-ai/agentii-investment-intelligence into my ~/.claude/skills/earnings-sentiment/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/agentii-ai/agentii-investment-intelligence.git && mkdir -p ~/.claude/skills && cp -r agentii-investment-intelligence/plugins/agent-plugins/agentii-equity-agent/skills/agentii/earnings-sentiment ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal in a working directory.
- Clone the repo:
git clone https://github.com/agentii-ai/agentii-investment-intelligence.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r agentii-investment-intelligence/plugins/agent-plugins/agentii-equity-agent/skills/agentii/earnings-sentiment ~/.claude/skills/ - Because the skill references
references/andcontracts/documents, copying the wholeagentii-equity-agentplugin folder is recommended. - Connect the agentii MCP server to Claude Code (see the repo README); without it the preflight probe fails and the skill stops.
- Restart Claude Code and test with a prompt such as "Analyze earnings sentiment for AAPL".