evidence
CommunityQuickly analyze evidence to surface key findings
System Documentation
What problem does it solve?
The evidence skill automates Phase 3 analysis of log bundles, HAR files, and support archives, eliminating manual extraction, grep, and jq chores while ensuring thoroughness and completeness for TAC investigations.
Core Features & Use Cases
- Bundle Extraction: Automatically untars support bundles and prepares files for analysis.
- HAR Forensics: Parses HTTP archives to surface errors, slow requests, and authentication issues.
- Log Mining: Greps logs for errors, timestamps, and stack traces, building a structured timeline.
- Cross‑Reference: Queries Cortex documentation, prior TAC cases, and Confluence knowledge bases to contextualize findings.
- Gate Enforcement: Calculates a completeness score and enforces the Phase 3 ≥ 80 % gate before proceeding.
Use case: When a customer reports intermittent API timeouts, the skill extracts the uploaded bundle, scans HAR logs for 5‑second responses, pulls error lines from log files, and checks against known issues, delivering a detailed evidence report ready for the next investigation phase.
Quick Start
Ask the assistant to run the evidence skill on the case directory you uploaded, and it will return a JSON summary of findings and gate status.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: evidence Download link: https://github.com/theLightArchitect/cappy-toolkit/archive/main.zip#evidence Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.