commercial-forecaster

Use when building a quarterly bookings forecast, ARR projection, pipeline forecast, NRR projection, or commit/best-case/pipe-only board number — especially when the CRO needs to walk the board through funnel math + cohort ARR + per-stage conversion assumptions without the theatre of a single undefended number. Decomposes pipeline into commit, best-case, and pipe-only tiers; projects cohort-level NRR/GRR to surface leaky cohorts before they show up in the consolidated number; scores per-stage funnel confidence so soft-floor stages get treated differently from high-confidence ones. Every output explicitly names the conversion rate used, the data window, and the weighting choice. For Head of Commercial, RevOps, VP Sales, and CRO at quarterly forecast or board prep. NOT financial close (see finance/financial-analysis). NOT strategic CRO hiring/territory (see c-level-advisor/cro-advisor). NOT pricing (see sibling pricing-strategist).

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear sequenced workflow and exemplary progressive disclosure via real bundle files. Its main weakness is conciseness: core rules are reinforced across three sections, producing noticeable token redundancy.

Suggestions

Consolidate the 70/30 blend, CoV thresholds, cohort-leak timing, and assumption-block-is-theatre rules into a single canonical section; have the Anti-patterns and Forcing-question library reference it instead of restating it.

Add an explicit validation/verification checkpoint between workflow steps (e.g., "review the leaky-cohort callout and CoV bands before assembling the deck") to close the validate-fix-retry loop.

Consider extracting the seven-question grilling library into a `references/grill_questions.md` file so the main SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the same handful of principles — the 70/30 blend, CoV thresholds, cohort-leak-surfaces-in-2-3-quarters, and the "assumption block is theatre" rule — are restated across the Assumptions, Anti-patterns, and Forcing-question library sections, which could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready commands with complete flags — `scripts/bookings_forecaster.py --input intake.json --profile saas --output markdown` and the parallel invocations for the other two scripts — plus a concrete intake step and noted `--help`/`--sample` affordances.	5 / 5
Workflow Clarity	A clearly numbered Step 1–5 sequence with concrete per-step commands, built-in guardrails ("The CLI refuses to omit the assumption block") and a grilling gate ("Lock 1-3 before opening 4-7"); verification exists via script-emitted flags and callouts but an explicit validate-fix-retry checkpoint loop is absent.	4 / 5
Progressive Disclosure	Clear overview body pointing to a well-signaled, one-level-deep bundle: dedicated `## Scripts` and `## References` sections list the real `scripts/.py`, `references/.md`, and `assets/forecast_intake_template.md` files with one-line descriptions, all verified present on disk.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it states concrete capabilities, comprehensive natural triggers, an explicit Use-when clause with audience, and clear boundaries against sibling skills. It is dense but every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "Decomposes pipeline into commit, best-case, and pipe-only tiers", "projects cohort-level NRR/GRR to surface leaky cohorts", "scores per-stage funnel confidence", and "names the conversion rate used, the data window, and the weighting choice" — with comprehensive coverage of the skill's outputs.	5 / 5
Completeness	Explicitly answers both what (decompose/project/score funnel confidence) and when ("Use when building a quarterly bookings forecast...") with concrete trigger phrases, a named audience, and explicit exclusion boundaries.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrasing a commercial leader would actually say — "quarterly bookings forecast", "ARR projection", "pipeline forecast", "NRR projection", "commit/best-case/pipe-only board number", "CRO", "board prep" — including synonyms across the forecast sub-types.	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit conflict-avoidance boundaries — "NOT financial close (see finance/financial-analysis)", "NOT strategic CRO hiring/territory (see c-level-advisor/cro-advisor)", "NOT pricing (see sibling pricing-strategist)" — minimizing wrong-skill triggering.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: commercial/skills/commercial-forecaster/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.