Every design choice leaves a trail. This skill helps you follow that trail from the first idea to the final code. It searches through conversations, handoffs, git history, and stored artifacts to piece together how a decision was made.
You get a clear timeline of events. Each event shows what changed, why it changed, and who made the change. All claims are backed by direct links to the evidence. This makes it easy to understand the reasoning behind any feature or architecture.
The trace skill works best with concepts like a feature name or a keyword. It produces a report with dates and sources. Teams use it to learn from past decisions and avoid repeating mistakes.
Global
mkdir -p ~/.claude/skills/traceProject
mkdir -p .claude/skills/traceSource Repository
Lark Baselarksuite/cli
Simplify your Lark Base data with tables, fields, records, and views
Lark Wikilarksuite/cli
Manage your Lark Wiki spaces, members, and documents with simple commands
Paper Context Resolverlllllllama/ai-paper-reproduction-skill
Resolve deep learning paper reproduction gaps with precise primary source evidence
Repo Intake And Planlllllllama/ai-paper-reproduction-skill
Scan a repo, extract commands, and get a minimal reproduction plan
Minimal Run And Auditlllllllama/ai-paper-reproduction-skill
Run commands and capture normalized evidence for reproducible deep learning research
Firecrawl Searchfirecrawl/cli
Search the web and extract full page content as markdown for deeper research
Ai Research Reproductionlllllllama/rigorpilot-skills
Faithful reproduction of deep learning research with auditable steps and minimal changes
Minimal Run And Auditlllllllama/rigorpilot-skills
Capture evidence from deep learning runs and create standardized audit reports