Daily portfolio monitoring

Skill ternary-ai/skills/skills/advanced/daily-portfolio-monitoring

A collection of agent skills for investment finance

Install

npx -y skills add ternary-ai/skills --skill daily-portfolio-monitoring

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Monitors thesis drift across holdings using daily news, earnings releases, price moves, and regulatory filings; outputs thesis status and action recommendations. Use during the daily execution cycle.

SKILL.md

2.5 KB, 512 tokens by cl100k_base, as published. Nobody here has run it

Daily Portfolio Monitoring

Purpose: Detect thesis drift in real time.

Trigger: Daily execution cycle.

Inputs:

News flow
Earnings releases
Price moves
Regulatory filings

Data Sources

Follow this order — do not ask the user which source to use:

Context first: Check <stock_context> and <acquired_data> for holdings list, yesterday's prices, and any recent news or earnings already fetched. If today's price moves and recent news are present → proceed directly to Process.
Fetch if missing: Call for each holding:
- GLOBAL_QUOTE — current price and daily % change
- NEWS_SENTIMENT — last 24-hour news and sentiment for each ticker
- EARNINGS — check for surprise if an earnings release was today
Ask only if both fail: Call request_user_input asking for the specific missing field only (e.g. "Please provide your current holdings list").

Process:

Map news to thesis assumptions.
Detect deviation from KPIs.
Identify volatility-driven opportunities.
Flag structural risk changes.

Output:

Thesis intact / weakened / broken classification
Action recommendation

Output Format

Write a daily monitoring report in markdown format:

## Daily Portfolio Monitoring Report
**Report Date**: {Date}

### Holdings Review
[For each monitored position:]

#### {TICKER} — {Position Size}%
- **Price**: $X (±Y% today)
- **Thesis Status**: [INTACT / WEAKENED / BROKEN]
- **Action**: [Hold / Review / Alert]

**Material Developments**:
- [News headline or event, if any]
- [Earnings surprise, guidance change, regulatory filing]
- [Insider transaction, analyst action]

**Thesis Impact**:  
[One sentence: Does this reinforce or contradict the original investment case?]

---

### Action Required
[List any positions requiring immediate attention with specific next steps]

### Monitoring Queue
[List positions with upcoming catalysts or events to track]

Thesis Field Rule: Always populate the thesis field in the JSON output with the complete daily monitoring report. This is an advanced skill — thesis upserting is mandatory. ⚠️ Extended thinking is discarded — copy the complete analysis into the thesis field; it is the ONLY output that reaches the Thesis panel.

Gives 0 of the 12 instructions most monitoring observability skills give in 512 tokens

Counted across 481 of the 483 authors here whose files we hold, read 2026-08-06

link every alert to a runbookin 43 of 481, across 35 files
use structured json loggingin 36 of 481, across 31 files
alert on user-facing symptomsin 20 of 481, across 15 files
emit structured JSON logs with stable event namesin 18 of 481, across 13 files
propagate trace context across boundariesin 16 of 481
use histograms for latency trackingin 14 of 481, across 9 files
use OpenTelemetry for distributed tracingin 13 of 481, across 8 files
include a correlation ID on every log linein 13 of 481, across 8 files
Define service level objectivesin 10 of 481, across 7 files
Call useAzureMonitor before importing other modulesin 9 of 481, across 2 files
stop and ask for clarification if inputs are missingin 9 of 481, across 2 files
define on-call questions before adding telemetryin 9 of 481, across 4 files

Said here and by no other author read

fetch missing current prices via global quote
fetch news and sentiment via news sentiment
check earnings surprise if released today
ask the user for specific missing fields if sources fail
map news flow to thesis assumptions
detect deviation from KPIs

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.