CtrlK
BlogDocsLog inGet started
Tessl Logo

diligence-issue-extraction

Read VDR documents and extract issues per house categories and materiality thresholds, producing findings in house memo format. Use when user says "review the data room", "extract issues from [folder]", "diligence review", "what's in the VDR", or points at VDR documents.

68

Quality

82%

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

65%Weight 40%Scale 1-3

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

A dense, domain-specific diligence workflow that is highly actionable and well-organized but somewhat verbose and monolithic. The main gaps are an explicit validation loop for batch processing and tighter prose in the guardrail sections.

Suggestions

Add an explicit validation checkpoint to the batch-processing step (e.g., verify each batch's findings against source documents before advancing, with a fix-and-retry loop) to lift workflow clarity.

Tighten the three blockquoted guardrails (source attribution, statute disagreement, no silent supplement) into compact bullets so the fabrication controls survive at lower token cost.

Consider extracting the per-category standard extraction sets and the output template into a references/ file referenced one level deep, leaving SKILL.md as a leaner overview.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the ~180-line body carries lengthy prose guardrails (source attribution, statute-disagreement, no-silent-supplement blockquotes) that could be tightened without losing the fabrication controls.

2 / 3

Actionability

Delivers concrete, copy-paste-ready guidance: per-category extraction checklists, an exact finding-field template, R/Y/G severity calibration with examples, and a markdown output skeleton — fully actionable for an instruction-only skill.

3 / 3

Workflow Clarity

The five steps are clearly sequenced with gap-noting and batch flagging, but the batch-processing path lacks an explicit validate/verify-then-proceed feedback loop, which caps batch-operation workflow clarity at 2.

2 / 3

Progressive Disclosure

No bundle files exist to split into; sections are well-organized with clear headers, but the body is a monolithic single file with substantial inline detail (extraction sets, templates) and only external plugin-config references, so it is not a cleanly split, one-level-deep structure.

2 / 3

Total

9

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 states concrete capabilities and pairs them with explicit, natural-language trigger phrases. It clearly communicates both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Names multiple concrete actions — "Read VDR documents", "extract issues per house categories and materiality thresholds", "producing findings in house memo format" — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (read/extract/produce findings in house memo format) and when ("Use when user says ..."), with an explicit trigger clause.

3 / 3

Trigger Term Quality

Provides natural phrasings a user would actually say — "review the data room", "extract issues from [folder]", "diligence review", "what's in the VDR" — giving good coverage of realistic trigger terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (VDR diligence issue extraction) with distinctive triggers tied to data-room review, making conflict with other 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anthropics/claude-for-legal
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.