CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lbo-model

Build leveraged buyout workbooks with IRR/MOIC in Excel.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/finance/lbo-model/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 provides dense, executable, domain-specific guidance — exact colors, formats, formula patterns, and LBO-specific pitfalls (plugs, circularity, odd-dimension sensitivity tables) — wrapped in an exceptionally clear gated workflow with validation, feedback loops, and checklists. Its weaknesses are repetition (recalc command, template mandate, and checkpoint rules each stated multiple times), a dangling intro line about MCP passages that were removed, and zero progressive disclosure: everything is inlined in one file while the paths it references don't exist in the bundle.

Suggestions

Deduplicate repeated guidance: state the recalc command once in the verification section, collapse the TEMPLATE REQUIREMENT triple-mandate into one instruction, and fold the 'Work section by section' Core Principle into the WORKING WITH THE USER checkpoints section.

Remove or rewrite the 'Data sources' opener 'Many passages below say "use the S&P Kensho MCP / Daloopa MCP / FactSet MCP"' — no such passages exist in this adapted version, so it confuses more than it informs.

Move the ~75-line verification checklist and common-errors table to a one-level-deep reference file (e.g., references/verification.md) linked from SKILL.md, and either ship examples/LBO_Model.xlsx in the bundle or drop the instruction to copy it.

DimensionReasoningScore

Conciseness

The body is dense with domain-specific guidance and never explains concepts Claude already knows, but redundancy is beyond minor: the recalc command appears three times ("Recalculate before delivery: `python /path/to/excel-author/scripts/recalc.py ./out/model.xlsx`", "run the `excel-author` skill's `recalc.py` helper before delivery", "```python /path/to/excel-author/scripts/recalc.py model.xlsx```"), the template mandate is stated three ways in TEMPLATE REQUIREMENT ("you MUST use it as your template - do not build from scratch" / "Never decide to 'build from scratch' when a template is provided"), and the section-by-section rule appears in both Core Principles ("Work section by section, verify with user at each step") and the full WORKING WITH THE USER section. The line "Many passages below say 'use the S&P Kensho MCP / Daloopa MCP / FactSet MCP'" dangles, referencing passages that don't exist in this adapted version.

3 / 5

Actionability

Concrete, executable guidance throughout: exact formula patterns ("`=-MAX(0,B4)`", "`=Assumptions!B5`", "`=B5*B6`"), exact hex colors ("#1F4E79", "#BDD7EE"), number-format strings ("`$#,##0;($#,##0);"-"`", "`0.0"x"`"), mixed-reference syntax ("`$A5` for row input, `B$4` for column input"), a symmetric axis example ("[8.0x, 9.0x, 10.0x, 11.0x, 12.0x]"), and a runnable validation command. Not a 5 because the command paths are placeholders ("`/path/to/excel-author/scripts/recalc.py`") and "`examples/LBO_Model.xlsx`" is absent from the bundle, so commands aren't literally copy-paste ready and there's no complete openpyxl code example.

4 / 5

Workflow Clarity

Clear gated sequence with explicit validation, feedback loops, and checklists: "TEMPLATE ANALYSIS PHASE - DO THIS FIRST" → "Clarify Requirements First" → a three-step fill hierarchy → section gates ("After Sources & Uses → show the balanced table, confirm the plug is correct, get sign-off before building the operating model" through "After Sensitivity Tables") → "VERIFICATION CHECKLIST - RUN AFTER COMPLETION". Validation is explicit ("Must return success with zero errors") with a feedback loop ("If errors are found during verification, fix them before moving to the next section") and an extensive per-section checklist. This matches the anchor 5 example's validate-fix-retry pattern; the mild duplication of checkpoint guidance is a conciseness issue, not a sequence gap.

5 / 5

Progressive Disclosure

Good in-file structure with clearly labeled sections ("DO THIS FIRST", "RUN AFTER COMPLETION"), but it's a single ~275-line monolith with no bundle: no references/, scripts/, or examples/ exist, and the referenced paths ("Copy `examples/LBO_Model.xlsx` as your starting point", the excel-author recalc script) are unresolvable in this bundle. The ~75-line verification checklist and the common-errors table are inlined where separate one-level-deep reference files would fit — matching the anchor 3 pattern of inline content that should be separate; not a 2 because section headers make the file genuinely navigable.

3 / 5

Total

15

/

20

Passed

Description

61%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 concise, domain-specific, and unmistakably states what the skill produces, with good natural keywords (leveraged buyout, IRR/MOIC, Excel). Its main weaknesses are the complete absence of when-to-use trigger guidance and thin action coverage — a single build verb with the 'LBO' acronym itself missing as a trigger term.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for an LBO model, leveraged buyout analysis, or buyout returns (IRR/MOIC) in Excel" — this directly addresses completeness, the highest-weighted dimension.

Include the "LBO" acronym and "private equity" as trigger terms, since users most often say "build an LBO model" rather than the spelled-out phrase.

Name one or two more concrete capabilities (e.g., debt schedules, sensitivity tables) to lift specificity from one action toward comprehensive coverage.

DimensionReasoningScore

Specificity

"Build leveraged buyout workbooks with IRR/MOIC in Excel" names the domain and one concrete action with specific outputs (IRR/MOIC), but coverage isn't comprehensive — no mention of debt schedules, operating projections, or sensitivity tables that the body actually covers. Not a 2 because the action is concrete and output-specific rather than generic; not a 4 because only one action verb is listed, not 'several specific actions.'

3 / 5

Completeness

The "what" is clear ("Build leveraged buyout workbooks with IRR/MOIC in Excel") but the "when" is entirely absent — no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. Matches anchor 3 ("Has a clear 'what' but 'when' is missing or only weakly implied").

3 / 5

Trigger Term Quality

Good natural keyword coverage: "leveraged buyout", "IRR/MOIC", "Excel" — phrases users would actually say. A few natural terms are missing: the "LBO" acronym (the single most common way users refer to this task), "private equity", and the .xlsx extension. Not a 5 (no synonyms/extensions); clearly above 3 ("some relevant keywords but missing common variations") because the full domain phrase plus both return metrics are present.

4 / 5

Distinctiveness Conflict Risk

"leveraged buyout workbooks with IRR/MOIC" is a clear, highly specific niche that no generic skill would claim — but "in Excel" plus the ecosystem of closely related skills (excel-author, dcf-model, 3-statement-model per the metadata) leaves minor overlap risk for generic 'build an Excel model' requests. Not a 5 because the related-skill overlap is real; well above 3 because LBO/IRR/MOIC triggers would never fire for the wrong skill.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/finance/lbo-model/SKILL.md

Reviewed

Table of Contents

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.