Forecast Analysis

What it does

When your agent uses it

• Tasks that involve Statistics

Example prompts

• “forecast”
• “prediction”
• “probability”
• “/forecast-analysis”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Separate evidence into anchors, supporting factors, opposing factors, uncertainty drivers, and monitoring indicators.
2. 2Prefer explicit anchors from sources, such as prediction-market prices, base rates, latest measured values, official projections, analyst…
3. 3Use execute for any arithmetic: probability conversion, expected value, weighted scenario averages, interval arithmetic, or base-rate…
4. 4Do not invent a final forecast when the assigned ResearchQuery only asks for evidence. Capture what the evidence implies and preserve…
5. 5Include compact forecast inputs in your ResearchNotes only after any calculation has succeeded.
6. 6In ResearchNotes, cite original source IDs for every forecast anchor and material factor.

What it can do on your machine

Read from SKILL.md and the folder at commit 951a1a1. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json and python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Forecast Analysis loads about 820 tokens when it runs. Until then it costs about 139 tokens; SKILL.md has 232 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~139

When it runs · the whole SKILL.md, loaded when a task matches

~820

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA-AI-Blueprints/deep-researcher-agent at commit 951a1a1, republished under its Apache-2.0 licence (© NVIDIA-AI-Blueprints). 232 words, ~820 tokens.

name

forecast-analysis

description

Use this skill during research for lightweight forecast evidence analysis: base-rate checks, prediction-market anchors, scenario ranges, directional factor summaries, implied probabilities, and monitoring indicators. Triggers: "forecast", "prediction", "probability", "odds", "base rate", "scenario", "Polymarket", "prediction market", "will happen", "market-implied", "confidence interval", "price target", "expected value". Outputs: forecast evidence notes or compact forecast inputs returned in your ResearchNotes for writer synthesis.

{
  "forecast_question": "...",
  "target_variable": "probability | value | date | threshold | option",
  "anchors": [
    {
      "label": "Prediction market price",
      "value": "62%",
      "source_ref": "source id or URL",
      "timestamp_or_date": "..."
    }
  ],
  "supporting_factors": ["..."],
  "opposing_factors": ["..."],
  "uncertainties": ["..."],
  "monitoring_indicators": ["..."],
  "calculation_notes": "..."
}

scenarios = [
    {"name": "upside", "probability": 0.25, "value": 80},
    {"name": "base", "probability": 0.50, "value": 55},
    {"name": "downside", "probability": 0.25, "value": 30},
]

probability_sum = sum(item["probability"] for item in scenarios)
expected_value = sum(item["probability"] * item["value"] for item in scenarios)

print(f"Probability sum: {probability_sum:.3f}")
print(f"Scenario-weighted expected value: {expected_value:.2f}")
for item in scenarios:
    contribution = item["probability"] * item["value"]
    print(f"- {item['name']}: contribution {contribution:.2f}")

© NVIDIA-AI-Blueprints, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in src/deep_researcher_agent/agents/deep_researcher/skills/research/forecast-analysis of NVIDIA-AI-Blueprints/deep-researcher-agent.

Open the folder on GitHubat commit 951a1a1