Agent skill · Audited from source

claim-chart

skill · anthropics/claude-for-legalApache-2.0 licenceAudited 29 Oct 2026 · source cb488a888d20

★ 9,824pushed 5 days ago
✓SAFEGrade B · 89/100 · 29 Oct 2026 · cb488a8
9,824repo stars · whole anthropics/claude-for-legal

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit cb488a888d20 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Build or review an element chart — a patent claim chart (infringement, invalidity, or review) or a civil element chart for any cause of action or defense — with every cell pin-cited and gap detection as the priority…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “claim-chart (anthropics/claude-for-legal)”. Retrieved 29 Oct 2026. https://modelsatlas.com/skills/anthropics/claim-chart

Trust audit

Audit 0.4.1 · source read 29 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha cb488a888d20 · 29 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheranthropics GitHub organizationOwner of the repository this skill is read from
  • Source folderanthropics/claude-for-legal/litigation-legal/skills/claim-chartThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdictcb488a888d20A new audit runs when the source changes
  • Repository statusNot archivedLast push 5 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Build or review an element chart — a patent claim chart (infringement, invalidity, or review) or a civil element chart for any cause of action or defense — with every cell pin-cited and gap detection as the priority…

---
name: claim-chart
description: Build or review an element chart — a patent claim chart (infringement, invalidity, or review) or a civil element chart for any cause of action or defense — with every cell pin-cited and gap detection as the priority output. Use when the user asks for a claim chart, element chart, proof chart, infringement or invalidity contention, element-by-element mapping, or asks "what are we missing to prove [claim]".
argument-hint: '[--patent | --civil] [--infringement | --invalidity | --review] [--claim <n>] [--count <name>] [--target <slug>]'
---

# /claim-chart

1. Load `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` → role, work-product header, decision posture, document storage.
2. If matter workspaces enabled, confirm or select the active matter; load `matter.md` (side, jurisdiction, phase, theory, pleadings).
3. Follow the workflow and reference below.
4. Mode selection:
   - `--patent` → patent claim chart. Require patent number and at least one asserted claim. Sub-modes: `--infringement`, `--invalidity`, `--review`.
   - `--civil` → civil element chart. Require the cause of action (or defense) and the side.
   - No flag → ask the user which.
5. For civil mode: consult `references/element-templates.md` in the skill directory for the baseline element list. Confirm the controlling pattern instruction or statute with the user before mapping.
6. For patent mode: parse asserted claims into elements, flag disputed terms for construction, apply any Markman order.
7. Map elements against the target (accused product / prior art / evidence corpus / chart under review). Every cell pin-cited. Apply the apostrophe-prefix neutralization before writing any cell value starting with `=`, `+`, `-`, `@`, tab, or CR.
8. Produce the gap list (civil) or needs-evidence list (patent) — the priority output.
9. Write markdown, CSV (values + `_sources` companion), and Excel or Sheets per user preference. Work-product header on every output.
10. Write to the matter's `claim-charts/` folder if a matter is active; otherwise the practice-level `claim-charts/` folder. Append a one-line entry to `history.md` if a matter is active.
11. Return a summary readout: claim(s), target(s), jurisdiction, phase, element counts by state, the gap list, file paths, and the reminder that every cell is a lead.

---

# Claim Chart

## Disclosed-document use restrictions

Before working with a set of litigation documents, ask: "Were any of these documents obtained through disclosure or discovery in legal proceedings?" If yes:

- **England & Wales (CPR 31.22):** Documents obtained through disclosure are subject to the implied undertaking — you may only use them for the purpose of the proceedings in which they were disclosed, unless the court grants permission, the disclosing party consents, or the document has been read in open court. Using them for a different matter, a different claim, or a commercial purpose without permission is a contempt.
- **US:** Protective orders and Rule 26(c) may impose similar restrictions. Check the order.
- **Other jurisdictions:** Similar restrictions commonly apply. Check the local rule.

Confirm: "This use is within the proceedings in which the documents were disclosed, or I have permission / consent, or the documents are now public." If not confirmed, flag it: "⚠️ Disclosed documents may have use restrictions. Confirm this use is permitted before proceeding."

## A CHART IS A DRAFT, NOT A FINDING OR A CONTENTION

**Put this at the top of every output. Do not drop it. Do not soften it.**

> This chart is a draft for attorney analysis and verification, not a filed contention, an MSJ brief, an opening statement, or a legal opinion. Every mapping is a lead the attorney must verify against the source. The elements listed come from pattern jury instructions, the Restatement, or the claim language as parsed — the **controlling** authority in the user's jurisdiction (CACI / NYPJI / the circuit's pattern charge / the governing statute / a Markman order) may differ and always controls. Gap detection is a starting point for discovery or a motion; it is not a conclusion about the merits.

Under-flagging a gap is a one-way door — a complaint filed without plausibility on an element, an MSJ response served without evidence for a disputed element, or a case tried without proof of damages. Over-flagging is a two-way door — the attorney clears flags in review. The default is biased toward the two-way door.

---

## 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 `/litigation-legal:matter-workspace switch <slug>` or say `practice-level`." Load the active matter's `matter.md` — especially the case theory, the pleading / complaint (for the elements actually alleged), the jurisdiction, any Markman order or stipulated constructions (patent mode), and the phase of the case. Write outputs to the matter folder at `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/<matter-slug>/claim-charts/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

## Load context

- `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` → role, work-product header, decision posture, document storage, case-theory scaffolding
- Active matter's `matter.md` — claims, defenses, side, jurisdiction, phase, theory
- For civil mode: the complaint or counterclaim (for the actually-pleaded counts), any answer (for the actually-pleaded affirmative defenses), the relevant pattern jury instruction source, and the governing statute if statutory. Also the evidence corpus — deposition transcripts, declarations, produced documents, expert reports.
- For patent mode: the patent, the asserted 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit cb488a8

Download folder ↗
git clone https://github.com/anthropics/claude-for-legal
git -C claude-for-legal checkout cb488a888d20

The author documents no install command, so this uses the repository directly. Our verdict covers commit cb488a888d20 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source cb488a888d20

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/anthropics/claim-chart/badge.svg)](https://modelsatlas.com/skills/anthropics/claim-chart/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/anthropics/claim-chart/badge.svg)](https://modelsatlas.com/skills/anthropics/claim-chart/)

Questions about claim-chart

What does the claim-chart skill do?
A suite of plugins for legal workflows
Is claim-chart safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can claim-chart access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (cb488a888d20), read on 2026-10-29. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.