customize · anthropics/claude-for-legal, product-legal — Claude Code skill: profile settings
The customize Claude Code skill edits a product counsel practice profile one section at a time. It activates when someone asks to update a profile, risk calibration, or review framework.
Apache-2.0 ★ 10,060 updated 2026-10-23
/plugin marketplace add anthropics/claude-for-legal
/plugin install product-legal@claude-for-legalWhat customize does
The skill guides edits to a product counsel profile without repeating the initial interview. It displays the current settings, asks for the replacement value, then writes the change after confirmation.
It can adjust risk thresholds, escalation contacts, launch-review categories, marketing-claim rules, and matter workspace paths. Shared company details go into company-profile.md and affect all 12 plugins. Sections cannot be deleted; a review category can instead be marked out of scope and routed to another team or plugin.
An existing, completed profile is required. If the configuration is missing or still has [PLACEHOLDER] values, run /product-legal:cold-start-interview first. The skill also flags conflicting settings and preserves review and source-verification tags.
What it helps with
- change the risk threshold for a specific pattern
- update the escalation chain for legal issues
- add a category to a product launch review
- revise rules for substantiating marketing claims
- change the workspace path for a matter
Example prompts for the agent
- Change the risk threshold for this category to “needs a real look”.
- Update the escalation chain to include the legal team manager.
- Add an accessibility category to the launch review framework.
How to install customize
1Plugin marketplace
/plugin marketplace add anthropics/claude-for-legal/plugin install product-legal@claude-for-legalThis installs the whole product-legal plugin with all its skills
2Skills CLI (Vercel)
npx skills add anthropics/claude-for-legal --skill customize -a claude-code3Manually: put the files in place
~/.claude/skills/customize/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/customize/
1Skills CLI (Vercel)
npx skills add anthropics/claude-for-legal --skill customize -a codex2Manually: put the files in place
.agents/skills/customize/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add anthropics/claude-for-legal --skill customize -a cursor2Manually: put the files in place
.cursor/skills/customize/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install anthropics/claude-for-legal product-legal/skills/customize2Manually: put the files in place
.github/skills/customize/SKILL.md1Skills CLI (Vercel)
npx skills add anthropics/claude-for-legal --skill customize -a gemini-cli2Platform CLI
gemini skills install https://github.com/anthropics/claude-for-legal --path product-legal/skills/customizeManually: put the files in place
.devin/skills/customize/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about customize
How do I install customize in Claude Code?
Add the marketplace with /plugin marketplace add anthropics/claude-for-legal, then install the plugin with /plugin install product-legal@claude-for-legal.
What does customize do?
It guides edits to individual sections of a product counsel profile and saves confirmed changes. It can also flag inconsistencies between profile settings.
What does customize need to run?
The product counsel profile must already be set up. If it is not, run /product-legal:cold-start-interview first.
Source text
SKILL.md · Apache-2.0
---
name: customize
description: >
Guided customization of your product counsel practice profile — change one
thing without re-running the whole cold-start interview. Adjust risk
calibration, escalation contacts, launch review framework, marketing
claims posture, or matter workspace paths. Use when the user says
"change my [thing]", "update my profile", "edit my framework", "retune
my calibration", or "customize".
argument-hint: "[section name, or describe what you want to change]"
---
# /customize
## When this runs
The user typed `/product-legal:customize`. They want to change something
in their product counsel profile — a risk calibration threshold, an
escalation contact, a framework section — without re-running the whole
cold-start interview and without hand-editing YAML.
## What to do
1. **Read the config.** Read
`~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md`
(and `~/.claude/plugins/config/claude-for-legal/company-profile.md` one
level up). If the plugin config does not exist or still contains
`[PLACEHOLDER]` values, say:
> You haven't run setup yet. Run `/product-legal:cold-start-interview`
> first — customize is for adjusting a profile you already have.
2. **Show the customizable map.** List what's in the profile, grouped, with a
one-line summary of the current value:
- **Company / who you are** — name, industry, jurisdictions, stage, practice
setting, product surface area *(shared across all 12 plugins — changes
flow through `company-profile.md`)*
- **Launch review process** — intake (Jira / Linear / Asana / doc),
review SLA, launch tiering, PRD location
- **Review framework** — the categories you review launches against
(privacy, IP, safety, claims, regulatory, accessibility, security,
etc.) and the depth you go on each
- **Risk calibration** — what's P0 blocker / needs a real look / fine at
your company, with examples that anchor the labels
- **Marketing claims** — posture on puffery vs. substantiated, comparative
claims framing, superlatives, house rules for AI-feature claims
- **People** — product partners by surface, escalation chain (your
manager, GC, risk committee), marketing counterpart
- **Workflow** — matter workspaces, launch-radar watcher cadence, launch
review template
- **Integrations** — Jira / Linear / Asana / Slack / document storage
status, fallbacks
3. **Ask what they want to change.**
> What would you like to adjust? Pick a section, or describe the change in
> your own words.
4. **Make the change.** Show the current value, ask for the new value, explain
what changes downstream, confirm, write it to the config.
Examples:
- *Risk calibration tightening "fine" → "needs a real look" for a
pattern:* "`/is-this-a-problem` and `/launch-review` will start flagging this
pattern. Existing reviews stay as written; re-run if you want the new
posture applied."
- *New launch-review category:* "`/launch-review` will add a section for
this category. `/is-this-a-problem` will pattern-match it in triage."
- *Marketing claims posture tightening:* "`/marketing-claims-review` will flag more
language as needing substantiation or reframing."
5. **For shared-profile changes** (company name, industry, jurisdictions,
practice setting, stage): write to
`~/.claude/plugins/config/claude-for-legal/company-profile.md` and note:
> This change affects all 12 plugins — any plugin that reads your
> jurisdiction footprint now sees [new value].
6. **Close.**
> Done. Your next output will reflect the change. Anything else? You can
> run `/product-legal:customize` anytime.
## Guardrails
- **Never delete a section.** If the user wants to "remove" a review
category, offer to mark it `[Not in scope — route elsewhere]` and name
the plugin / team that picks it up.
- **Flag internal inconsistency.** If the change would make the profile
inconsistent (e.g., AI-feature claims scrutiny on + no AI policy
commitments set in `/ai-governance-legal`; or "fast SLA" + "every
launch requires GC sign-off"), flag the tension.
- **Flag guardrail degradation.** The `[review]` flag, source attribution
tags, and `[verify]` tags on cited regulations are load-bearing — do not
remove. The substantiation requirement on claims is the thing
`/marketing-claims-review` exists for; weakening it defeats the skill.
- **One change at a time.** Don't re-ask the whole interview.
© Anthropic · Apache-2.0 · anthropics/claude-for-legal
Similar skills
All skills for Agent setup: memory, context, orchestration →customize by other authors comes first.