dcf-model

Build institutional-quality DCF valuation models in Excel — revenue projections, FCF build, WACC, terminal value, Bear/Base/Bull scenarios, 5x5 sensitivity tables. Pairs with excel-author. Use for intrinsic-value equity analysis.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

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

A highly detailed, actionable DCF build guide with strong workflow sequencing and validation loops. Its main weaknesses are heavy internal repetition across sections and a monolithic structure with a missing referenced file.

Suggestions

De-duplicate the sensitivity-table, cell-comment, and consolidation-column guidance into a single canonical section and reference it elsewhere instead of restating it four or more times.

Move the large <correct_patterns> and <common_mistakes> catalogs into separate reference files (e.g. references/correct-patterns.md, references/common-mistakes.md) so the main SKILL.md stays a lean overview.

Either add the referenced TROUBLESHOOTING.md to the bundle or remove the dead links pointing to it.

Dimension	Reasoning	Score
Conciseness	The ~1250-line body restates the same guidance many times — sensitivity-table requirements, cell-comment format, and the consolidation/INDEX pattern each appear across four or more sections — so it could be tightened substantially even though it avoids explaining basic concepts.	2 / 3
Actionability	Provides concrete executable formulas (`ws["D20"] = "=D19*(1+$B$8)"`), specific commands (`python recalc.py model.xlsx 30`), exact RGB color codes, and full cell-layout tables that are largely copy-paste ready.	3 / 3
Workflow Clarity	Sequenced 10-step workflow with explicit validation checkpoints ('Verify Step-by-Step With the User'), a recalc→fix→re-run feedback loop, and a Final Output Checklist, matching the anchor for clear sequence with validation and error recovery.	3 / 3
Progressive Disclosure	The body is a monolithic wall of text with the large <correct_patterns>/<common_mistakes> catalogs and full Excel layouts inline rather than split into reference files, and it references a TROUBLESHOOTING.md that does not exist in the bundle.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, third-person description that names concrete capabilities and provides an explicit use-trigger for intrinsic-value equity analysis. It is distinct from sibling valuation skills and free of fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'revenue projections, FCF build, WACC, terminal value, Bear/Base/Bull scenarios, 5x5 sensitivity tables' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Build institutional-quality DCF valuation models in Excel') and when ('Use for intrinsic-value equity analysis'), with an explicit 'Use for' trigger clause.	3 / 3
Trigger Term Quality	Contains natural domain terms a finance user would say — 'DCF valuation models', 'equity analysis', 'Excel' — giving good coverage of natural trigger language.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (DCF equity valuation in Excel) and signals its boundary by noting it 'Pairs with excel-author', making it unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1271 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	11 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/finance/dcf-model/SKILL.md
Commit: 4c9628e

Reviewed: about 14 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.