- Skill ID
- anthropics/claude-for-legal/internal-investigation
- Publisher
- anthropics
- Repository
- claude-for-legal
- Installs
- 0
- Files
- 1
- Synced
- Sep 23, 2026
Open any RiverX project, open the Skills panel in the chat, and search for this identifier. The files are fetched from the source repository at install time.
anthropics/claude-for-legal/internal-investigationInstalls these files- SKILL.md
What this skill tells the agent
Internal Investigation Skill
Matter context
Matter context. Check ## Matter workspaces in the practice-level CLAUDE.md. If Enabled is ✗ (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run /employment-legal:matter-workspace switch <slug> or say practice-level." Load the active matter's matter.md for matter-specific context and overrides. Write outputs to the matter folder at ~/.claude/plugins/config/claude-for-legal/employment-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.
Output header
Prepend the work-product header from ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → ## Outputs (it differs by user role — see ## Who's using this). Every file, log, memo, and summary produced by this skill opens with that header.
Distribution discipline. Every file this skill creates — log entries, memo drafts, audience summaries, document notes — inherits the privilege and confidentiality status of the underlying investigation. Distribution beyond the privilege circle (forwarding to non-attorneys outside the investigation team, cc'ing HR without scoping, handing to the business side) can waive privilege over the entire investigation. Store these files where privileged materials live, label per the work-product header, and make every distribution decision deliberately.
⚠️ Privilege notice — read before proceeding
Marking does not create privilege. The header above reflects the intended protection and is important to include — but it does not itself establish privilege. Whether any given output is actually privileged depends on whether the investigation is attorney-directed, the purpose for which documents are created, and how they are subsequently used or disclosed.
Before opening a matter, confirm: Is this investigation attorney-directed? If it is not — if HR is running it with legal in an advisory role, or if it was not initiated at the direction of counsel for the purpose of obtaining legal advice — the privilege analysis changes materially and this skill's default labeling may be misleading. Flag that question to the attorney before creating any log or file.
If there is any doubt about privilege applicability, the attorney should resolve it before investigation files are created. Improperly labeled materials can create problems in discovery if privilege is later challenged.
Purpose
Internal investigations fail in two ways: coverage gaps (sources that were never gathered) and synthesis gaps (evidence that was gathered but never connected). This skill handles both — it tracks what has and hasn't been gathered, processes document dumps to surface what matters without burying the attorney, and maintains a structured log that can be turned into a privileged memo at any point.
Privilege note
All files created by this skill carry the privilege marking above. See the notice at the top of this skill for the full caveat on what that marking does and does not do.
Load context
Read ~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md → escalation table, any investigation protocols noted.
Mode 1: Open a new matter
Triggered by /employment-legal:investigation-open or "open an investigation" or "start an investigation into".
Step 1 — Intake
Ask the following in a single block:
To open the investigation log I need a few things: The matter - What is the allegation or concern in plain terms? - Who is the complainant (or what triggered this — complaint, tip, audit, manager observation)? - Who is the respondent or subject? - What is the approximate timeframe the alleged conduct occurred? - Is this attorney-directed? (If yes: work product protection applies. If no: flag privilege risk before proceeding.) Investigation type (helps me suggest the right sources checklist) - HR: harassment / discrimination / retaliation - Financial misconduct: expense fraud / procurement irregularities / embezzlement - Executive misconduct: COI / undisclosed relationships / governance failures - Whistleblower: retaliation for protected activity - Other: describe briefly Representation and employer status (surfaces parallel legal frameworks that change interview procedure) - Is the respondent, the complainant, or any anticipated witness represented by a union or covered by a collective bargaining agreement? (If yes, flag for Weingarten research — representational rights at investigatory interviews may apply and change the interview protocol.) - Is the company a public employer (government entity, public university, state or municipal agency) or otherwise acting under color of state law? (If yes, flag for Garrity research — compelled statements in public-sector investigations have special use-immunity consequences and change how interviews must be conducted and documented.)
If either flag fires, research the applicable rules (NLRA / state public-sector labor statutes for Weingarten; 5th Amendment and the Garrity line of cases, plus any state analogs) before conducting interviews. Cite primary sources. Verify currency. Do not interview until the protocol is adjusted.
Step 2 — Create the matter directory and files
Create the following files:
~/.claude/plugins/config/claude-for-legal/employment-legal/investigation-[matter-slug]/log.yaml:
# [WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]
matter: "[matter name]"
matter_slug: "[slug]"
opened: "[ISO date]"
attorney_directed: [true/false]
allegation: "[plain-language summary]"
complainant: "[name/role or anonymous]"
respondent: "[name/role]"
conduct_timeframe: "[approximate dates]"
investigation_type: "[HR/financial/executive/whistleblower/other]"
status: open
last_updated: "[ISO date]"
issues:
- "[Issue 1 — derived from allegation, e.g. 'alleged hostile work environment']"
- "[Issue 2 if applicable]"
entries: []
evidentiary_gaps: []~/.claude/plugins/config/claude-for-legal/employment-legal/investigation-[matter-slug]/sources-checklist.yaml:
Generated from the investigation type. See sources checklist templates below.
~/.claude/plugins/config/claude-for-legal/employment-legal/investigation-[matter-slug]/documents-reviewed.yaml:
# [WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]
matter: "[matter name]"
total_reviewed: 0
total_surfaced: 0
last_updated: "[ISO date]"
documents: []Step 3 — Sources checklist
Generate the appropriate checklist based on investigation type. Present it to the attorney and ask: "Does this fit your matter? Let me know if any items are not applicable (I'll mark them N/A) or if there are additional sources specific to this situation."
HR investigation sources (harassment/discrimination/retaliation):
sources:
- id: 1
source: "Complainant interview"
status: open
notes: ""
- id: 2
source: "Respondent interview"
status: open
notes: ""
- id: 3
source: "Witness interviews — identify from complainant and respondent accounts"
status: open
notes: ""
- id: 4
source: "Email/messaging review — parties, relevant date range"
status: open
notes: ""
- id: 5
source: "HR records — respondent's performance history, prior complaints,
prior discipline"
status: open
notes: ""
- id: 6
source: "Prior complaints — any prior complaints against respondent in
HR system"
status: open
notes: ""
- id: 7
source: "Comparator data — how were similar situations handled"
status: open
notes: ""
- id: 8More from anthropics
Use this skill in a project
Open any RiverX project, search the Skills panel for anthropics/claude-for-legal/internal-investigation, and install it in one click.
