chronology

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

Gates applied: no behavioural pass.

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

• Publisheranthropics GitHub organizationOwner of the repository this skill is read from
• Source folderanthropics/claude-for-legal/litigation-legal/skills/chronologyThe 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

Its description: Build or update a chronology from declared document sources and uploads — dated events extracted, de-duped, and tagged by significance per the matter theory. Use when the user asks to build a chronology or timeline from…

---
name: chronology
description: Build or update a chronology from declared document sources and uploads — dated events extracted, de-duped, and tagged by significance per the matter theory. Use when the user asks to build a chronology or timeline from a production or matter file, says "chron from the production" or "what happened when", or needs a working, statement-of-facts, or witness-specific timeline.
argument-hint: "[slug] [--format=working|sof|witness-[name]]"
---

# /chronology

1. Load `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/matter.md` → theory, pivot fact, key facts.
2. Load `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` → Document storage sources, default matter folder pattern.
3. Follow the workflow and reference below.
4. Identify sources in order: user-provided paths this session, default matter folder, declared sources from `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md`.
5. For readable sources: extract dated events. For unreachable sources: note in Gaps.
6. De-dupe, merge with sources list per event.
7. Tag significance (🔴/🟡/⚪) per matter theory.
8. Write `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/chronology.md` (or format variant per flag).
9. If prior version exists: version number increments, diff summary presented to user.
10. Confirm before finalizing: "Here's what I built. Scan the 🔴 entries — anything I miscalled?"

---

# Chronology

## 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."

## Purpose

Facts happen in order. The chronology is the spine every narrative hangs on — the statement of facts in a brief, reserve memos, settlement memos, depo prep, witness prep. Building a chron by hand is slow; AI is good at structured extraction. The catch: garbage-in, garbage-out. This skill pulls from the sources the configuration declares and from whatever the user uploads.

## Modes

This skill serves two practice settings. Pick a default from the user's `## Role` in the plugin's configuration CLAUDE.md; the user can override per-run with a flag.

- **`--matter` mode (default for in-house litigation counsel).** Matter-history-focused. Reads the matter's case theory and key facts from `matter.md`, pulls from declared document-storage sources (Google Drive, SharePoint, Gmail, iManage, CLM — whatever the `## Landscape` section of CLAUDE.md declares), and treats `history.md` as the running internal log (decisions, holds, reserve memos — intentionally not in the chronology). Output is matter-centric: what happened across the dispute, tagged for advocacy use.
- **`--documents` mode (default for firm associate / paralegal).** Production-document-focused. Reads the case theory from the configuration, then extracts from an eDiscovery export, a custodial file set, or a Bates-numbered production. Output is production-centric: what the documents show, with Bates citations, tagged per the case theory.

Both modes converge on the same output structure (timeline, 🔴/🟡/⚪ significance tags, gaps, SoF variant). The difference is the source profile and the significance frame.

If `## Role` is `solo` or `other`, default to `--matter` but mention both modes on the first run and let the user pick.

## Side framing (significance tags)

The same event is significant in different ways depending on whether the practitioner is proving a claim or disproving it. Read `## Side` in the practice profile (and the per-matter posture if the matter overrides the default):

- **Plaintiff (offensive framing)** — 🔴 marks events that *establish* elements of the claim (liability, causation, damages, notice), *close* gaps the defense will try to open, or *start* statute-of-limitations clocks in the plaintiff's favor. 🟡 marks events that support the claim but are subject to impeachment. ⚪ is background context.
- **Defense (defensive framing)** — 🔴 marks events that *break* elements of the claim (failure of causation, notice, reliance), *open* statute-of-limitations or jurisdictional defenses, or *support* affirmative defenses (release, waiver, assumption of risk, comparative fault). 🟡 marks events that undermine the plaintiff's narrative. ⚪ is background.
- **Both / varies** — ask the user per-chronology which side's framing to apply for significance tags. The underlying timeline is side-neutral; only the significance read changes.

Note the applied framing at the top of the output: `Significance tags applied from [plaintiff / defense] perspective.` When producing a Statement of Facts variant, use the side default unless the user specifies otherwise.

## Load context

Common:
- Plugin configuration CLAUDE.md → case theory context (in-house: `## Landscape` for document sources; firm associate: `## Case theory` and `## Document review` for platform + custodians), `## Outputs` for the work-product header, `## Decision posture` for the privilege-flagging rule.
- Prior `chronology.md` for this ma

Excerpt, first 6,009 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.

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

Works in

1. 2026-10-29
   ✓SAFE B 89 / 100

   first audit · source cb488a888d20

Questions about chronology

• github.com/anthropics/claude-for-legal/tree/main/litigation-lega — the audited source at commit cb488a888d20 and every finding aboveObserved · 29 Oct 2026

Spotted something wrong? Report a correction · Methodology