CtrlK
BlogDocsLog inGet started
Tessl Logo

deal-team-summary

Aggregate diligence findings into a deal team briefing at the right altitude for the audience — exec summary for leadership, working summary for the team. Use when user says "brief the deal team", "what's the state of diligence", "summarize findings for [audience]", "deal update", or on the briefing cadence.

76

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

87%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 well-organized, lean, actionable instruction skill whose templates and tier table make it directly usable; the only gap is the absence of an explicit verification checkpoint in the multi-step flow, which caps workflow clarity. Conciseness, actionability, and progressive disclosure are all at the top of the scale.

Suggestions

Add an explicit verification step before the brief is considered draft-complete — e.g. a checklist confirming the privilege-circle distribution warning was applied, coverage figures reconcile against the diligence output, and the decision items each name an owner and a deadline.

Make the tier-selection checkpoint a numbered step (e.g. "1. Confirm audience tier; ask if not obvious") so the multi-step flow reads as an explicit sequence rather than a soft inline instruction.

Specify how recurring-brief deltas are detected against the prior brief (e.g. compare finding IDs/severity against the last brief's snapshot) so 'New findings since last brief' is reproducible rather than left to interpretation.

DimensionReasoningScore

Conciseness

The body is lean — templates and a tier table carry most of the weight with minimal prose, no explaining of concepts Claude already knows, and every line earns its place (e.g. "Deal leads care more about movement than state" is a useful non-obvious insight), matching the 'lean and efficient' anchor rather than the padded level 2.

3 / 3

Actionability

Delivers copy-paste-ready markdown skeletons with concrete fields (Status, Coverage, Material findings, Decisions needed) and a progress table with exact columns, plus the five named decision-tree branches — specific and executable rather than abstract, fitting the level-3 anchor for an instruction-only skill.

3 / 3

Workflow Clarity

The sequence is clear — tier selection ("Ask which tier if not obvious"), matching summary template, deltas for recurring briefs, decision tree — but there is no explicit validation/verification checkpoint in the flow, so it sits at level 2 ('sequence present but checkpoints missing') rather than the level-3 'explicit validation steps' anchor; it is not level 1 because steps are well-sequenced and the tier-conditional logic is explicit.

2 / 3

Progressive Disclosure

No bundle files exist, but the self-contained body is cleanly sectioned (Purpose, Load context, Audience tiers, The summary, Deltas, Handoffs, What this skill does not do) and external config references (CLAUDE.md, deal-context.md) are one-level-deep and fully pathed, matching the 'clear overview with well-signaled references; easy navigation' anchor.

3 / 3

Total

11

/

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, well-constructed description: it states concrete actions, gives natural trigger phrasings, covers both what and when, and occupies a distinctive niche. It scores at the top of the scale on every dimension.

DimensionReasoningScore

Specificity

Names multiple concrete actions — "Aggregate diligence findings into a deal team briefing", "exec summary for leadership, working summary for the team" — within a specific domain, matching the 'lists multiple specific concrete actions' anchor rather than the partial-coverage level 2.

3 / 3

Completeness

Explicitly answers both what ("Aggregate diligence findings into a deal team briefing...") and when ("Use when user says..."), with explicit triggers present, so it clears the level-3 bar rather than the implied-when level 2.

3 / 3

Trigger Term Quality

Quotes natural phrasings a user would actually say — "brief the deal team", "what's the state of diligence", "summarize findings for [audience]", "deal update" — giving good coverage of common variations rather than jargon.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — deal-team diligence briefing at audience tiers — with distinct triggers unlikely to fire for other legal skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.