internal-investigation

Reference: shared framework for managing internal investigations from intake through final memo — privileged investigation log, document processing with needle-finding, source coverage tracking, Q&A against the log, memo drafting, and audience summaries. Loaded by /investigation-open, /investigation-add, /investigation-query, /investigation-memo, and /investigation-summary; not invoked directly.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./employment-legal/skills/internal-investigation/SKILL.md

Quality

Content

77%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 highly actionable, well-sequenced skill with concrete schemas, templates, and multiple validation gates, but it is a heavy monolithic file whose large repetitive templates would benefit from being split into reference files.

Suggestions

Move the four investigation-type source checklists into a single references/sources-checklists.md (or one file per type) and keep only a concise pointer plus the selection logic in SKILL.md to cut ~200 lines of repetition.

Externalize the full memo template to references/memo-template.md, leaving a short structure outline and the completeness gate inline.

De-duplicate the privilege/header caveat text (it appears in the description, the Privilege notice, the Privilege note, and the Distribution discipline block) into one canonical statement referenced where needed.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely concrete templates and schemas rather than conceptual padding, but at ~28KB it repeats material — four near-parallel source checklists, a full inline memo template, and repeated privilege/header caveats — that could be tightened or externalized; not the lean 'every token earns its place' of level 3.	2 / 3
Actionability	Provides copy-paste-ready structures — log.yaml/sources-checklist.yaml/documents-reviewed.yaml schemas, the full memo markdown template, explicit document pull criteria, and report templates — giving concrete, specific guidance with placeholders rather than vague direction.	3 / 3
Workflow Clarity	Five modes are each broken into numbered steps with explicit validation gates (the memo completeness gate 'do not draft until…', the consequential-action gate, the intake privilege flag) plus sources checklists, satisfying clear sequencing with checkpoints and checklists.	3 / 3
Progressive Disclosure	Sections and modes are well-organized, but the skill ships no bundle files at all and keeps content that should be split — the four source-checklist templates and the full memo template — inline in a monolithic SKILL.md, falling short of well-signaled one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

67%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 specific, well-scoped description that concretely enumerates capabilities and occupies a distinct niche, but it relies on command names rather than natural-language triggers and lacks an explicit 'Use when…' situational clause, capping trigger quality and completeness.

Suggestions

Add a 'Use when…' situational clause (e.g., 'Use when the attorney needs to open, build, query, or write up an internal investigation') so the 'when' is expressed in natural terms a user would say, not just command names.

Include common natural-language trigger variations ('investigation', 'investigate', 'investigating', 'investigation memo') alongside the slash commands to improve trigger-term coverage.

Consider pairing each command with a one-phrase plain-language trigger (e.g., '/investigation-open — start an investigation into…') so the trigger terms read naturally.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'privileged investigation log, document processing with needle-finding, source coverage tracking, Q&A against the log, memo drafting, and audience summaries' — matching the anchor for naming several specific concrete actions rather than vague language.	3 / 3
Completeness	The 'what' is clearly and comprehensively stated, but the 'when' is only the mechanical 'Loaded by /investigation-open ... /investigation-summary; not invoked directly' with no 'Use when…' situational clause, so per the guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Relevant keywords appear ('internal investigations', 'intake', 'memo', 'audience summaries') and five slash commands are named, but it is command-list-driven and lacks the natural-language variations a user would actually say; not the broad coverage of natural terms expected at level 3.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche — managing privileged internal investigations end-to-end — with distinct command triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 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
skill_md_line_count	SKILL.md is long (766 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-for-legal
Path: employment-legal/skills/internal-investigation/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.