| name | building-chronologies |
| title | building-chronologies |
| description | Use when users say "build a chronology", "make a timeline", "what happened when", "chronology from disclosure", "source the key events", or need legal documents, correspondence, pleadings, witness evidence, or disclosure materials turned into a sourced event chronology. |
| author | LegalQuants |
| author_url | https://github.com/LegalQuants/lq-skills/tree/main/skills/building-chronologies |
| license | Apache-2.0 |
| version | 0.1.0 |
| execution_mode | open |
| jurisdiction | general |
| practice | litigation |
| language | en |
| tags | ["chronology","timeline","evidence","disclosure","source-attribution"] |
building-chronologies
When to Use
- A lawyer needs a timeline from a bundle, disclosure set, correspondence folder, witness statement set, or case file.
- The user asks "what happened when" or needs chronology support for pleadings, advice, witness prep, mediation, or trial.
- The output must cite each event back to a source document.
Do not use this skill to fill gaps from memory. A chronology is only as reliable as its sources.
Audience and Work Shape
Audience: litigators, trainees, paralegals, and litigation-support teams building first-pass chronologies for lawyer review.
Work shape: bounded extraction with accretive judgment. The skill extracts dated events from sources, then applies judgment to de-duplicate, flag conflicts, and surface gaps. It does not decide what happened.
Legal Failure Modes
- Legal support, not legal advice: a chronology is a working evidence map, not merits advice, submissions, or a final statement of facts.
- Privilege/confidentiality: if source material appears privileged or work-product-sensitive, flag it as
privilege_review and do not include it in an externally shareable chronology without lawyer approval.
- Accountability: the responsible lawyer decides whether a disputed or low-confidence event can be used in pleadings, evidence, settlement material, or submissions.
Access Modes
This skill works in three modes:
- Live source mode - use browser, web search, MCP, API, or other configured access to retrieve public filings, dockets, emails, storage folders, or document repositories.
- User-supplied source mode - use uploaded or pasted documents, correspondence, pleadings, disclosure exports, witness materials, PDFs, images, or OCR text supplied by the user.
- No-source mode - design the chronology schema and source-request list, but do not create factual chronology entries.
If documents cannot be retrieved or supplied, do not infer events from model memory. Mark missing periods, missing sources, and source requests explicitly.
How It Works
1. Define scope
Confirm:
- Matter or project name.
- Date range.
- Document sources.
- Jurisdiction or forum, if legal deadlines or procedural events will be interpreted.
- Intended output: working chronology, witness-specific chronology, statement-of-facts draft, or issue chronology.
If source coverage is thin, say so before drawing conclusions.
2. Extract dated events
For each source, extract only events with a reliable date or date range:
