Log and review dated client communications for each case with action items.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "client-comms-log" skill from askskill: 1. Download https://raw.githubusercontent.com/anthropics/claude-for-legal/main/legal-clinic/skills/client-comms-log/SKILL.md 2. Save it as ~/.claude/skills/client-comms-log/SKILL.md 3. Reload skills and tell me it's ready
Use client-comms-log to add a new entry: case-id LC-2024-018, time today 3:15 PM, direction in, medium call, student Wang Min, client Ms. Li, duration 12 minutes. Summary: client called to ask about the next hearing date and said she would send updated income proof. Action items: we need to confirm the hearing schedule and reply by Friday; client needs to email the document by tomorrow. Follow-up due this Friday.
A formatted log entry is shown for confirmation, then appended to the case log after approval.
Use client-comms-log in --read mode to show the 5 most recent communication entries for case LC-2024-018.
Returns the latest entries from the case communication log for quick review.
Use client-comms-log in --summary mode to summarize the communication log for case LC-2024-018, focusing on 'what did we tell the client last time?'
Outputs a condensed paragraph summarizing the latest information communicated to the client and next steps.
A student or case worker logs a dated entry right after a call, email, text, meeting, or voicemail. This preserves a clear communication record and tracks follow-up tasks for both sides.
Before a handoff or continued work on a case, use read or summary mode to review recent communications. This helps avoid re-asking questions the client already answered and quickly restores context.
During supervision or review, the tool can scan patterns such as unanswered communications, missed follow-ups, language gaps, or long contact gaps. It is useful for detecting trends that are hard to spot from individual entries.
The README describes the purpose, workflow, and modes of /client-comms-log. It stores per-case client communication records and supports add, read, summary, and pattern-scanning modes. When adding an entry, it collects details such as direction, medium, summary, action items, and follow-up due date, then shows a formatted draft for confirmation before writing. The document also explains why these logs matter for malpractice defense, continuity during handoff, supervision visibility, and file retention.
--add (default): capture direction, medium, student, summary, action items, follow-up due. Confirm with user. Append (prepend most-recent-first) to ~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[case-id]/log.md.--read: show the most recent N entries.--summary: one-paragraph condensed read.--patterns: scan for unanswered comms, missed follow-ups, language gaps, tone shifts, contact gaps. Supervision-oriented./legal-clinic:deadlines --add if the log establishes a deadline; route to /legal-clinic:semester-handoff via --summary when relevant.Four reasons to keep this log:
Light. Append-only. The student's job is to write a two-sentence entry after every contact; the skill formats it and appends.
~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[case-id]/log.md (if exists) — append target~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md → not heavily read; this skill is case-scopedFlag: --add | --read | --summary | --patterns (default: add)
--add (default) — log a new entryInputs:
in (client → clinic) | out (clinic → client)call | email | text | letter | in-person | video | voicemail-left | voicemail-receivedBefore writing: show the user the formatted entry and ask for confirmation. Clinic records should be reviewed before they're written, not after.
Append to ~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[case-id]/log.md. If the log doesn't exist, create it with a header:
# Communications Log — [case name]
**Case ID:** [case-id]
**Client:** [name]
**Opened:** [YYYY-MM-DD]
Append-only. Most recent at top.
---
Then prepend new entries at the top (most recent first).
--read — show recent entriesPrint the most recent N entries (default 5). Useful when picking up a case mid-semester or before a client call.
--summary — condensed readProduce a one-paragraph summary of the log — most recent contact, total entries, common medium, any open action items from the student side, any unanswered communications. Feeds /semester-handoff and /status.
--patterns — flag concerns across the logScan for:
…
It keeps a per-case client communication log and supports adding, reading, summarizing, and scanning for patterns. Entries can include date, direction, medium, summary, action items, and follow-up due dates.
At minimum, a case ID is required. The docs also list fields such as time, direction, medium, student name, client-side contact, duration, summary, action items, follow-up date, and notes. Before writing, it shows the formatted entry and asks for confirmation.
The original description says it works alongside /client-letter and /status client. The docs also mention offering deadlines if a log creates a deadline, and routing a summary to semester-handoff when relevant.
Draft DMCA notices, triage incoming claims, and prepare counter-notice drafts.
Standardize new matter intake and generate matter files plus a structured log.
Compare proposed handbook edits and identify cross-reference and state supplement impacts.
Review offer letters and restrictive covenants with jurisdiction-specific hiring checks.
Create audience-specific summaries from privileged investigation memos safely.
Search watched skill registries, preview matches, and inspect SKILL.md before installing.
Turn call notes or transcripts into action items, follow-ups, and summaries.
Generate personalized outreach emails and messages using Common Room signals.
Run structured legal client intake and generate organized case summaries.
Draft common legal responses from templates with built-in escalation checks.
Draft routine client letters from templates with supervision and plain-language checks.
Automatically log completed tasks and build searchable weekly AI worklogs.