investigation-summary

Draft an audience-specific summary from the privileged investigation memo — HR, leadership, or outside counsel versions. Use when an investigation memo needs to be communicated to an audience that should not see the full privileged work product.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 concise, well-organized instruction skill with concrete guidance and a clean one-level reference deferral. Its main gap is the absence of a verification step confirming that privileged content was fully stripped before the summary is shared.

Suggestions

Add an explicit final verification step — e.g., 'Before sharing, re-scan the summary for any attorney mental impressions, credibility methodology, or legal exposure analysis and confirm none remain' — to close the validation gap in this sensitive workflow.

Spell out the minimal leadership and outside-counsel audience rules inline (not just HR) so the skill is self-contained for the most common cases rather than deferring all stripping logic to the reference.

Dimension	Reasoning	Score
Conciseness	The body is lean — a short overview, three brief numbered steps, three one-line example invocations, and a short blockquote — with no padding and no explanation of concepts Claude already knows, matching anchor 3.	3 / 3
Actionability	Gives a concrete execution path ('Load the internal-investigation reference skill and run Mode 5') plus explicit prohibitions ('HR summaries must not include attorney mental impressions, credibility methodology, or legal exposure analysis') and concrete slash-command examples; as an instruction-only skill this is actionable guidance rather than pseudocode, matching anchor 3.	3 / 3
Workflow Clarity	The three steps are clearly sequenced, but in a context where leaking privileged content is the core risk there is no validation checkpoint confirming the audience-stripping actually removed all privileged material, matching anchor 2's 'steps listed but validation gaps.'	2 / 3
Progressive Disclosure	The body is a genuine overview deferring one level deep to a single clearly-named, twice-signaled reference (the internal-investigation skill) with no nesting or monolithic wall, matching the simple-skills anchor 3.	3 / 3
	Total	11 / 12 Passed

Description

90%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 clear, well-targeted description that explicitly covers both what the skill does and when to use it, with natural domain trigger terms and a distinct niche. Its only weakness is that it names a single high-level action rather than enumerating multiple concrete sub-actions.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete audience variants ('HR, leadership, or outside counsel versions'), but the action is a single verb ('Draft an audience-specific summary') rather than a list of multiple distinct concrete actions, matching anchor 2.	2 / 3
Completeness	Explicitly states what it does ('Draft an audience-specific summary...') and includes an explicit 'Use when an investigation memo needs to be communicated...' trigger clause, satisfying anchor 3's both what-and-when requirement.	3 / 3
Trigger Term Quality	Uses natural domain terms a user would actually say — 'investigation memo,' 'HR,' 'leadership,' 'outside counsel,' 'privileged work product' — giving good coverage matching anchor 3.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — audience-stripped summaries of privileged investigation memos — with distinct triggers unlikely to fire for unrelated skills, matching anchor 3.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-for-legal
Path: employment-legal/skills/investigation-summary/SKILL.md
Commit: 4a6c651

Reviewed: 6 days 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.