CtrlK
BlogDocsLog inGet started
Tessl Logo

datapack-builder

Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract, normalize, and standardize financial data into investment committee-ready Excel workbooks with consistent structure, proper formatting, and documented assumptions. Use for M&A due diligence, private equity analysis, investment committee materials, and standardizing financial reporting across portfolio companies. Do not use for simple financial calculations or working with already-completed data packs.

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 concrete formatting rules, executable code patterns, and a well-sequenced workflow with strong validation checkpoints. Its main weakness is conciseness and progressive disclosure: rules are repeated across several sections and substantial reference material sits inline rather than in separate files, inflating the context cost.

Suggestions

De-duplicate the formatting rules: state the six essential rules once and have later phases (3, 5, and the final checklist) reference them rather than restate them, cutting roughly a third of the body.

Extract the industry-specific adaptations and the EBITDA normalization patterns into a separate reference file (e.g., references/normalization.md and references/industry-metrics.md), signposting them with one-line pointers to improve progressive disclosure.

Consolidate Phase 5 quality control and the FINAL DELIVERY CHECKLIST, which currently overlap heavily, into a single verification section with explicit pass/fail checkpoints.

DimensionReasoningScore

Conciseness

The body is dense and largely relevant, but formatting rules are restated four times (CRITICAL SUCCESS FACTORS, Phase 3 build steps, Phase 5 QC, FINAL DELIVERY CHECKLIST) and some sections repeat concepts; it is mostly efficient but could be tightened, matching the 'some unnecessary explanation' anchor.

2 / 3

Actionability

Provides concrete formats ($#,##0.0, 0.0%, accounting parentheses), an executable Python row-tracking pattern, a dictionary row-ref pattern, and an explicit 8-tab structure — copy-paste ready guidance, not pseudocode.

3 / 3

Workflow Clarity

A clear six-phase sequence with explicit validation checkpoints in Phase 5 (data accuracy, format consistency, structure, presentation, documentation) and feedback-style verification (balance sheet balances, no #REF!/#VALUE!/#DIV/0! errors), matching the explicit-validation anchor.

3 / 3

Progressive Disclosure

The skill is a monolithic single file with no bundle files (references/scripts/assets absent), and large inline reference blocks (industry-specific adaptations, normalization patterns) that could be split out; the only external pointer is the well-signaled 'xlsx skill', so structure exists but content that should be separate is inline.

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.

The description is comprehensive: it states concrete actions, enumerates data sources, provides explicit positive and negative use triggers in third person, and carves out a clearly distinct niche with low conflict risk. It is one of the stronger example descriptions, with no missing elements.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Extract, normalize, and standardize financial data', 'investment committee-ready Excel workbooks') and enumerates specific sources (CIMs, offering memorandums, SEC filings, web search, MCP servers), matching the multiple-specific-actions anchor.

3 / 3

Completeness

Clearly answers what the skill does and when to use it via an explicit 'Use for...' clause, and adds a 'Do not use for...' exclusion; written in third person, satisfying both what-and-when with explicit triggers.

3 / 3

Trigger Term Quality

Strong coverage of natural terms a user would say — 'M&A due diligence', 'private equity analysis', 'investment committee materials', 'standardizing financial reporting across portfolio companies' — with several common variations.

3 / 3

Distinctiveness Conflict Risk

A distinct financial-data-pack niche with an explicit negative trigger ('Do not use for simple financial calculations or working with already-completed data packs') makes conflict with adjacent skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (657 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
anthropics/financial-services
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.