finance-agent

Financial analyst for startup economics — TAM/SAM/SOM, revenue projections, burn rate, runway, and break-even. Use when building financial models or evaluating investment cases.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./modules/skills/src/main/resources/META-INF/skills/finance-agent/SKILL.md

Quality

Content

43%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 a lean, well-organized persona definition but offers little executable guidance: it lists analysis types Claude already knows how to perform and duplicates that list between the intro and the Skills section. The guardrails contain the only concrete parameters, and no workflow or output format is specified.

Suggestions

Add concrete methodology or output-format guidance — e.g., a worked example showing the expected TAM→SAM→SOM chain with the 5% SOM rule applied, or the structure of a burn-rate/runway table the model should produce.

Replace the bare "## Skills" bullet list with the actual steps of the modeling workflow (gather inputs → size the market → project revenue → estimate costs → compute runway/break-even), including a checkpoint to flag default inputs before presenting results.

Remove the duplication between the intro paragraph and the "## Skills" section — state the capability list once, keeping the body tighter and freeing tokens for the methodology detail.

Dimension	Reasoning	Score
Conciseness	The intro sentence "You build financial models with TAM/SAM/SOM analysis, revenue projections, cost structures, and funding requirements" duplicates nearly the entire "## Skills" bullet list — a full redundant section. Otherwise lean with no padding, matching anchor 3 ("mostly efficient but... could be tightened") rather than 4, whose examples show only minor trimmable instances.	3 / 5
Actionability	Bullets like "TAM/SAM/SOM market sizing analysis" and "Break-even timeline analysis" merely name tasks Claude already knows; the only concrete parameters are "conservative estimates for SOM (5% of SAM)", "3-year horizon", and "monthly burn rate". This matches anchor 2 (high-level hints, missing specific steps) rather than 1, since the guardrails pin a few concrete values.	2 / 5
Workflow Clarity	There is no sequence for any of the five analyses — no order for gathering inputs, constructing the model, or presenting results. A rough frame (capability list plus constraints) exists, matching anchor 2 ("rough sequence present but many gaps; steps poorly defined"), not 1 because the guardrails impose some operating structure.	2 / 5
Progressive Disclosure	The skill is under 50 lines, no bundle files exist (no references/, scripts/, or assets/), and no external references are needed — per the simple-skill exception, well-organized sections alone warrant the top score. The intro/Skills/Guardrails structure is clear and navigable.	5 / 5
	Total	12 / 20 Passed

Description

87%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.

A strong description: it names a specific niche, lists five concrete capability areas, and provides an explicit "Use when..." trigger clause with natural terms. The only gaps are topic-noun phrasing instead of action verbs and a few missing common synonyms (e.g., "financial projections", "unit economics").

Dimension	Reasoning	Score
Specificity	"TAM/SAM/SOM, revenue projections, burn rate, runway, and break-even" lists five concrete capability areas, but as topic nouns rather than the verb-phrase actions seen in the anchor-5 example ("Extract text... fill forms"). Not 3 because coverage clearly exceeds 1-2 actions; not 5 because the items name domains of analysis rather than specific actions.	4 / 5
Completeness	The description explicitly answers what ("Financial analyst for startup economics — TAM/SAM/SOM, revenue projections, burn rate, runway, and break-even") and when with concrete trigger phrases ("Use when building financial models or evaluating investment cases"), mirroring the anchor-5 example structure. Not 4 because the when-clause is explicit and specific, not merely present.	5 / 5
Trigger Term Quality	"financial models", "investment cases", "burn rate", "runway", and "TAM/SAM/SOM" are terms users would naturally say when needing this skill, matching the good-coverage anchor. Not 5 because common variations like "financial projections", "unit economics", or "fundraising model" are missing.	4 / 5
Distinctiveness Conflict Risk	"startup economics" with triggers like TAM/SAM/SOM, burn rate, and runway carves out a clear niche with minimal overlap against generic business or document skills. The specialized vocabulary makes wrong-skill triggering unlikely.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Atmosphere/atmosphere
Path: modules/skills/src/main/resources/META-INF/skills/finance-agent/SKILL.md
Commit: 1c968d5

Reviewed: 2 days 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.