$ loading_
Query an investigation log for conflicts, evidence strengths, and information gaps.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "investigation-query" skill from askskill: 1. Download https://raw.githubusercontent.com/anthropics/claude-for-legal/main/employment-legal/skills/investigation-query/SKILL.md 2. Save it as ~/.claude/skills/investigation-query/SKILL.md 3. Reload skills and tell me it's ready
Based on this investigation log, what did the respondent say about the December team dinner? Please cite the relevant log entry IDs.
A summary of the respondent's statements with the corresponding log entry IDs.
Compare the complainant's and respondent's accounts, identify where they conflict, and list the evidence sources and log entry IDs by issue.
A conflict list organized by issue, including each party's account and cited entries.
Using the current investigation log, explain what information is still missing and which issues lack supporting evidence. If the log has nothing relevant, say so explicitly and flag it as a gap.
A list of missing information, showing the gaps and the issues they affect.
When a user does not want to reread every investigation log entry, they can ask about an event, person, or disputed issue directly. The skill summarizes the answer from the record and cites log entry IDs.
When different witnesses or parties give competing accounts, this skill can point out the conflicts and summarize the strongest available evidence on each issue.
When a user wants to check whether the investigation is complete, they can ask what information is still missing. If the log contains nothing relevant, the skill explicitly says so and can prompt that it be treated as a gap.
The documentation describes /investigation-query as a skill for answering questions against an investigation log, including what witnesses said, where accounts conflict, what gaps remain, and what the strongest evidence is on each issue. It instructs users to load the `internal-investigation` reference skill first and run Mode 3 (Query). Answers should always cite log entry IDs, and if nothing relevant appears in the log, the response should say so explicitly and note how many entries were reviewed.
Answers questions against the investigation log — what witnesses said, where accounts conflict, what gaps exist, what the strongest evidence is on each issue.
internal-investigation reference skill and run Mode 3 (Query)./employment-legal:investigation-query [matter name]
What did the respondent say about the December team dinner?
/employment-legal:investigation-query [matter name]
Where do the complainant's and respondent's accounts conflict?
/employment-legal:investigation-query [matter name]
What do we still need?
Detailed log-query process, citation rules, and gap-flagging templates live in the
internal-investigationreference skill — load it before doing substantive work.
It is used to answer questions against an open investigation log, such as what a witness said, where accounts conflict, what information is missing, and what the strongest evidence is on each issue.
Yes. The documentation says answers should always cite the relevant log entry IDs so the basis can be traced.
The docs say you should first load the `internal-investigation` reference skill and run Mode 3 (Query). For the more detailed query process and rules, see the source repository.
Safely uninstall hub-installed community skills with confirmation and audit logging.
Temporarily disable or re-enable an installed community skill without deleting files.
Get a concise briefing on one legal matter's status, changes, deadlines, and risks.
Manage matter workspaces to separate, switch, and archive client contexts.
Search watched skill registries, preview matches, and inspect SKILL.md before installing.
Draft DMCA notices, triage incoming claims, and prepare counter-notice drafts.
Search and analyze past session logs with jq for context and insights.
Query persistent evidence memory for structured reverse engineering investigations.
Log and review dated client communications for each case with action items.
Find reference markers and evidence sources for knowledge items quickly.
Create Evidence reports and dashboards by querying schemas, docs, pages, and code.
Investigate failing GitHub integration tests and suggest likely fixes