specstory-link-trail
Track all URLs fetched during SpecStory AI coding sessions. Run when user says "show my link trail", "what URLs did I visit", "list fetched links", or "show web fetches".
91
87%
Does it follow best practices?
Impact
99%
1.05xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Evaluation results
100%
Audit AI-Fetched URLs Before Security Review
Two-step pipeline execution and direct output presentation
Uses parse_webfetch script
100%
100%
Uses generate_report script
100%
100%
Correct pipeline order
100%
100%
Correct script path prefix
100%
100%
History path used
100%
100%
Link Trail Report format
100%
100%
Per-session breakdown
100%
100%
Successful vs failed separation
100%
100%
Follow-up offers
100%
100%
100%
Recover Documentation Links from a Specific Session
Date-specific session filtering
Uses parse_webfetch script
100%
100%
Uses generate_report script
100%
100%
Pipeline pattern used
100%
100%
Date glob pattern
100%
100%
Correct history path
100%
100%
Correct script path prefix
100%
100%
Report contains only Jan 22 sessions
100%
100%
Report format correct
100%
100%
98%
14%Investigate Failed Resource Fetches in AI Coding Sessions
Key findings highlighting and follow-up offers
Uses parse_webfetch script
100%
100%
Uses generate_report script
100%
100%
Pipeline used
50%
100%
Script output preserved
100%
100%
Failed fetches identified
100%
100%
HTTP status for failures
100%
100%
Most accessed domain highlighted
86%
86%
Offer to retry failed fetches
0%
100%
Additional follow-up offered
100%
100%
- Repository
- specstoryai/agent-skills
- Commit
9454d3f
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.