@gtmagents/forecast-modeling
AUse when designing, tuning, or auditing revenue forecast models.
Install
agr install @gtmagents/forecast-modeling --target claudeWrites 1 file into .claude/skills/, pinned to git-d20722c7.
- .claude/skills/forecast-modeling/SKILL.md
Document
name: forecast-modeling description: Use when designing, tuning, or auditing revenue forecast models.
Forecast Modeling System Skill
When to Use
- Launching new forecasting cadences or revisiting methodology.
- Running scenario planning ahead of board meetings or budget cycles.
- Auditing deviations between forecast, pipeline, and actuals.
Framework
- Method Selection – pick bottom-up CRM, top-down macro, cohort, or blended models and document assumptions.
- Driver Mapping – define win rates, velocity, expansion, churn, pricing, and seasonality inputs.
- Scenario Logic – establish base/upside/downside cases with tunable levers for sensitivity analysis.
- Model Governance – list data sources, refresh cadence, validation checks, and ownership.
- Output Packaging – standardize tables, charts, and narrative prompts for exec review.
Templates
- Driver tree diagram connecting levers to KPIs.
- Scenario sheet (assumption → base/upside/downside values).
- Model QA checklist (data freshness, formula audits, version history).
Tips
- Keep raw inputs + assumptions in version control for auditability.
- Pair with
variance-analysisskill to recalibrate after each cycle. - Automate sensitivity runs to answer "what-if" questions during reviews.
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-d20722c77add2026-07-31