Skip to main content
skill CX Codex official · Anthropic

comments — Claude Code skill: what it does, how to install

Tracks open NPRM comment periods, flags approaching deadlines, and logs filing decisions for legal teams.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add anthropics/claude-for-legal --skill comments -a claude-code
Open on GitHub

What comments does

The skill reads tracked rulemaking items from comment-tracker.yaml and organizes them by deadline urgency: under 14 days, over 14 days, and recently decided. If Slack MCP is configured and owner_slack is set, it sends direct reminders at 14 days and 3 days before the deadline for undecided items.

Logging decisions is handled through /regulatory-legal:comments --decide CMT-ID with options for filing, not-filing, or waived. When the user role in CLAUDE.md is set to Non-lawyer, a consequential-action gate halts any filing action until attorney review is explicitly confirmed. Public regulatory statements bind the company in subsequent proceedings, making this gate essential.

This skill does not draft comment letters or choose strategy. Its task ends once the decision is recorded in the tracker.

What it helps with

  • surface upcoming comment deadlines for open NPRMs
  • log filing, not-filing, or waived decisions with rationale
  • send automated deadline alerts through Slack MCP
  • enforce an attorney review gate before logging a filing decision

Example prompts for the agent

  • /regulatory-legal:comments
  • /regulatory-legal:comments --decide CMT-001
  • Show all open NPRMs with comment deadlines under 14 days

How to install comments

1Skills CLI (Vercel)

npx skills add anthropics/claude-for-legal --skill comments -a claude-code

2Manually: put the files in place

~/.claude/skills/comments/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/comments/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about comments

How to install comments in Claude Code?

Run npx skills add anthropics/claude-for-legal --skill comments -a claude-code. The skill will be available at ~/.claude/skills/comments/SKILL.md.

What does the comments skill do?

It lists open NPRM comment periods, calculates remaining days, and writes filing decisions directly into a YAML tracker.

What happens when a non-lawyer tries to log a filing decision?

The skill triggers a consequential-action gate. It halts execution and requires explicit confirmation of attorney review before allowing a filing decision.

Source text

SKILL.md · Apache-2.0
---
name: comments
description: Review open NPRM comment periods, log decisions, track deadlines. Use when an NPRM has a comment window open and you need to surface deadlines, decide whether to file, or record a filing / not-filing / waived decision (--decide CMT-ID).
argument-hint: "[optional: --decide CMT-ID]"
---

# /comments

## Purpose

NPRMs have deadlines. The decision to file a comment or not is an attorney
call — but the deadline disappearing without a logged decision is the risk.
This skill surfaces open comment periods and records decisions.

## Load context

`~/.claude/plugins/config/claude-for-legal/regulatory-legal/comment-tracker.yaml` → all tracked NPRMs and their status.
`~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md` → default comment decision owner.

## Default view — open comment periods

```markdown
## Comment Period Tracker — [date]

### ⏰ Deadline in <14 days

| ID | Regulation | Deadline | Days left | Decision | Owner |
|---|---|---|---|---|---|
| CMT-001 | [name] | [date] | [N] | Undecided | [owner] |

### 🟡 Open (>14 days)

[same table]

### Recently decided

| ID | Regulation | Decision | Rationale |
|---|---|---|---|
| CMT-002 | [name] | Not filing | [reason] |

---

**Total open:** [N]  **Undecided with deadline <30 days:** [N]
```

## Log a decision

```
/regulatory-legal:comments --decide CMT-001
Decision: [filing / not-filing / waived]
Rationale: "[brief — e.g., 'Rule doesn't apply to our model' or 'Filing comment on Section 3']"
```

Updates tracker. If decision is "filing": prompt for filing deadline reminder
(comment deadline minus 5 business days for internal review).

## Notifications

On first detection of an NPRM (populated by reg-feed-watcher): Slack DM to
comment decision owner if Slack MCP is configured and `owner_slack` is set.

Reminder at 14 days before deadline if decision is still "undecided."
Reminder at 3 days before deadline if still undecided — elevated urgency.

## Consequential-action gate (submit a regulatory comment / respond to a regulator)

**Before logging a decision as "filing" — and always before producing a comment letter or regulator-response draft for submission:** Read `## Who's using this` in ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md. If the Role is **Non-lawyer**:

> Submitting a comment or response to a regulator has legal consequences. It's a public statement of the company's position, it's on the record in the rulemaking or enforcement matter, and positions taken here bind the company and can be used against it in subsequent proceedings. Have you reviewed this with an attorney? If yes, proceed. If no, here's a brief to bring to them:
>
> - The rulemaking or inquiry (regulator, docket, deadline)
> - What the proposed comment/response says and on what sections
> - Open questions and what's unresolved
> - What could go wrong (adverse admissions, inconsistent prior positions, coordination-of-comment concerns with trade associations)
> - What to ask the attorney (should we file at all; should we file jointly through a trade group; are there positions we should not take)
>
> If you need to find a lawyer: your professional regulator's referral service is the fastest starting point (state bar in the US; SRA/Bar Standards Board in England & Wales; Law Society in Scotland/NI/Ireland/Canada/Australia; or your jurisdiction's equivalent).

Do not log a "filing" decision or produce a submission-ready draft past this gate without an explicit yes. Tracking views, deadline reminders, and "not-filing / waived" decisions do not require the gate.

---

## What this skill does not do

- Draft the comment letter. That is a separate attorney task.
- Make the filing decision. It tracks the decision; the attorney makes it.
- Monitor post-comment activity. Once a decision is filed, this tracker's job
  is done — follow the rulemaking through `/regulatory-legal:reg-feed-watcher`.

> The `comment-decision` `gap_type` semantics, the per-send Slack confirmation rule, and the comment-tracker.yaml schema live in the **gap-surfacer** reference skill — load it before doing substantive work.

© anthropics · Apache-2.0 · anthropics/claude-for-legal

Similar skills

Everything for Notes, tasks and projects →

From the same set118

use-case-triage Classifies proposed AI use cases against an internal registry, flags red lines, and outputs compliance conditions or handoffs. CX Codex +1 594installs oc-status Drafts weekly status-request emails to outside counsel for active matters and saves one Markdown file per matter. It can also create Gmail drafts through an available MCP. CX Codex +1 594installs investigation-open The skill opens a new internal investigation matter: it runs intake, builds the sources checklist and creates the persistent investigation log. CX Codex +1 594installs matter-update Appends a dated event to a litigation matter's history file and refreshes its row in _log.yaml, including risk, deadline and materiality changes. CX Codex +1 593installs worker-classification Evaluates proposed hiring arrangements across employee, IC, temp, and vendor classifications. It flags misclassification risks before the engagement begins. CX Codex +1 592installs client-comms-log Keep dated client contact records by case, then review recent entries or scan for follow-up gaps. Useful before a client call or when handing a case to someone else. CX Codex +1 591installs vendor-ai-review Checks a vendor's AI agreement, addendum or ToS against your governance positions: training on data, liability, model changes. CX Codex +1 592installs policy-starter Drafts an internal firm AI usage policy based on published model standards and legal guidelines. Useful when creating a first policy version or updating an outdated rulebook. CX Codex +1 592installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor