Chronology Builder Andrew Bird logo

Chronology Builder Andrew Bird

Organization
lawve-ai
chronology-builder-andrew-bird

Builds a litigation chronology from the disclosure bundle itself — every entry attributed to its source document, behind a CPR 31.22 implied-undertaking check, because documents disclosed in English proceedings may only be used for those proceedings. Adds a privilege screen and case-theory significance tagging, so the output is court-facing work product, not a loose timeline. Use when the user asks to build a chronology or timeline from a disclosure bundle, a matter file, or witness statements, or says 'build the chron', 'what happened when', or needs a Statement of Facts ready timeline.

Overview

Publisherlawve-ai
Repositoryawesome-legal-skills
Skill namechronology-builder-andrew-bird
Stars
854
Forks
111
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by lawve-ai on GitHub. Read the source before you install it.

Installation

Install the Chronology Builder Andrew Bird AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/chronology-builder-andrew-bird
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git /tmp/awesome-legal-skills
mkdir -p .claude/skills
cp -r /tmp/awesome-legal-skills/skills/chronology-builder-andrew-bird .claude/skills/chronology-builder-andrew-bird
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Chronology Builder Andrew Bird in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Chronology Builder Andrew Bird on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Chronology Builder Andrew Bird is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/chronology

  1. Run the CPR 31.22 implied-undertaking check before extracting from disclosed documents.
  2. Identify sources: user-provided paths, matter folder, declared sources.
  3. Extract dated events, de-duplicate against sources, tag significance per case theory.
  4. Output a working chronology by default; Statement-of-Facts or witness-specific variants on request.

Chronology — UK civil litigation

CPR 31.22 implied-undertaking check

The host workspace enforces the hard gate (matter-slug match against the proceedings reference, privilege posture). If this skill is running, that gate has already passed — this check does not replace it. The skill still performs its own check below and refuses or flags if misuse is indicated; it is not the enforcement.

Before building from any document obtained through standard or extended disclosure in English / Welsh proceedings, confirm the use is permitted:

CPR 31.22(1): A party to whom a document has been disclosed may use the document only for the purpose of the proceedings in which it is disclosed, except where: (a) the document has been read to or by the court, or referred to, at a hearing held in public; (b) the court gives permission; or (c) the party who disclosed the document and the person to whom the document belongs agree.

Misuse of disclosed documents (using them for a different matter, a different claim, a commercial purpose, or external publication) is a contempt of court.

Confirm before extracting from any source that may have come through disclosure:

  • Whether the documents are from disclosure in current proceedings (infer from source path or matter context; surface for confirmation if not evident).
  • Whether the chronology is being built for use in those same proceedings (default assumption: yes — same matter slug, same proceedings).

If the answer indicates "different proceedings" or "external use", refuse to build until permission, the parties' agreement, or open-court reference is established — the implied undertaking would otherwise be breached. Flag prominently in the output header: CPR 31.22 — use restricted to current proceedings unless permitted, agreed, or read in open court.

Equivalent overlay in disclosure pilot / PD 57AD jurisdictions (Business and Property Courts): the implied undertaking applies; PD 57AD does not displace it.

Privilege screen

Documents may be subject to legal professional privilege (advice and litigation privilege), common-interest privilege, joint-defence privilege, without-prejudice protection. Extracting privileged content into a chronology that is later shared can risk waiver.

Determine the privilege posture before extracting. Infer from source type (cleared production folder → A; mixed mailbox / dataroom → B; ad-hoc bundle with no review history → B by default; explicit instruction to pause → C). Surface the inferred posture in the output header so counsel can override.

  • A. All sources screened and cleared by counsel. Extract without flags.
  • B. Mixed or unscreened (default for ambiguous sources). Extract and tag each entry priv: ok / priv: flag / priv: review. SoF variant filters flagged entries by default.
  • C. Pause and screen first (use when counsel has explicitly instructed).

Inputs

  • Matter slug, case theory (one sentence — the spine of the case), pivot fact (the single event the case turns on), key facts.
  • Sources: disclosure bundle path / cloud folder, supplemental disclosure, witness statements, expert reports, public registers (Companies House, Land Registry), correspondence (open and WP — handle differently).
  • Side (claimant / defendant) — drives significance tagging.

Workflow

Step 1 — CPR 31.22 implied-undertaking check (above)

Step 2 — Privilege posture choice (above)

Step 3 — Source identification

User-provided paths first, then matter folder, then declared sources. Name any source the skill cannot read in the Gaps section — don't silently skip.

Step 4 — Extraction

For each readable source, identify dated events. One event per document usually. Format: [date] [actor] [verb] [object/recipient] [content summary].

Step 5 — De-duplication

The same event surfaces in multiple documents (calendar entry, summary email, meeting note). Merge into one entry with multi-source attribution.

Step 6 — Significance tagging (per side)

  • Claimant (offensive): 🔴 events establishing elements of the cause (duty, breach, causation, loss, notice), starting limitation in claimant's favour. 🟡 supportive but impeachable. ⚪ background.
  • Defendant (defensive): 🔴 events breaking causation, establishing limitation, supporting affirmative defence (waiver, estoppel, release, contributory negligence). 🟡 undermining claimant narrative. ⚪ background.

Discipline: 🔴 should be reserved for events that move a factfinder. If everything is 🔴, nothing is.

Step 7 — Source attribution per entry

Every entry cites its source(s): Bates / disclosure list reference, file path, or witness statement paragraph. Entries derived from web search, model knowledge, or user statement in-session must be tagged [web search — verify], [model knowledge — verify], [user provided].

Step 8 — Output

Working chronology by default. Variants:

  • Statement of Facts (SoF): filtered to 🔴 and select 🟡, prose narrative, with disclosure references. Privilege-flagged entries excluded by default.
  • Witness-specific: filtered to events where the named witness is sender, recipient, attendee, or subject.

Output

Produce the chronology with the sections below. Render this as the finished chronology — do not echo this template back, do not leave [placeholder] markers or emoji-count scaffolding in the output, and do not invent events to fill rows. Attribute every entry to its source document; if a section has nothing in it, say so.

This is a draft for solicitor review, not legal advice. The chronology and its significance tags are a first pass; counsel decides what goes into a pleading or before the court.

The sections:

  • A reviewer-note line: work product, prepared in contemplation of litigation, subject to litigation privilege.
  • A CPR 31.22 notice naming the proceedings the sources were disclosed in.
  • A header: matter slug, build date, case theory, pivot fact, side framing, privilege posture, source count, and entry count by tag.
  • The timeline table — one row per de-duplicated event, with date, event, significance tag, privilege flag, and sources.
  • Key events (🔴) — the events that move a factfinder, each with what happened, the tie to the case theory, and sources.
  • Gaps — date ranges with no events, expected-but-missing events, unreadable sources.

Worked shape for the sections (do not copy the placeholder text — fill from real sources):

[Reviewer note: work product, prepared in contemplation of litigation, subject to litigation privilege.]

CPR 31.22 notice. Sources include documents disclosed in [proceedings]. Use restricted to those proceedings per CPR 31.22 unless permitted, agreed, or already read in open court.

Chronology — [Matter name]

  • Matter: [slug]
  • Built: [YYYY-MM-DD]
  • Case theory: [one sentence]
  • Pivot fact: [one sentence]
  • Side framing: [claimant / defendant]
  • Privilege posture: A-cleared / B-mixed / C-aborted
  • Sources: [N] documents across [bundle / supplemental / witness / expert]
  • Entries: [N] ([N] 🔴 / [N] 🟡 / [N] ⚪)

Timeline

DateEventTag🔒Sources
[YYYY-MM-DD][actor + verb + object + content]🔴/🟡/⚪/ 🔒-flag / 🔒-review[D1/123, WS-Smith para 14]

Key events (🔴)

[date] — [event title]

  • What: [...]
  • Theory tie: [why this matters to the case theory]
  • Sources: [...]

Gaps

  • Date ranges with no events: [...]
  • Expected but missing: [...]
  • Unreadable sources: [...]

Marker discipline

  • [VERIFY — factual assertion not yet checked against the source doc]
  • [UNCERTAIN — legal characterisation]
  • [CITE NEEDED — disclosure reference]
  • [SME VERIFY — privilege status / borderline significance]

Version

  • v[N] built on [date] from [source summary]
  • v[N-1] superseded

Incremental builds

If a prior chronology.md exists: read, build new from current sources, diff (new / modified / removed), bump version. Preserve provenance and tags.

What this skill does not do

  • Resolve contradictions between sources. Both go in with flags.
  • Fill gaps from web search or model knowledge silently. The user is asked first.
  • Decide privilege status. The posture is selected; per-entry flags are first-pass; counsel decides distribution.
  • Cover Scottish / NI proceedings.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Chronology Builder Andrew Bird AI skill do?

Builds a litigation chronology from the disclosure bundle itself — every entry attributed to its source document, behind a CPR 31.22 implied-undertaking check, because documents disclosed in English proceedings may only be used for those proceedings. Adds a privilege screen and case-theory significance tagging, so the output is court-facing work product, not a loose timeline. Use when the user asks to build a chronology or timeline from a disclosure bundle, a matter file, or witness statements, or says 'build the chron', 'what happened when', or needs a Statement of Facts ready timeline.

Why use Chronology Builder Andrew Bird on TypingMind?

Because you install it once and use it with any model. Chronology Builder Andrew Bird is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Chronology Builder Andrew Bird in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lawve-ai/awesome-legal-skills/tree/main/skills/chronology-builder-andrew-bird. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Chronology Builder Andrew Bird?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Chronology Builder Andrew Bird?

As many as you like. As long as a model supports skills, you can use Chronology Builder Andrew Bird with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Chronology Builder Andrew Bird AI skill free?

It is published on GitHub by lawve-ai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇