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".

Install with Tessl CLI

npx tessl i github:specstoryai/agent-skills --skill specstory-link-trail

What are skills?

Review — 87%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

Audit AI-Fetched URLs Before Security Review

Two-step pipeline execution and direct output presentation

Criteria

Without context

With context

Uses parse_webfetch script

100%

Uses generate_report script

100%

Correct pipeline order

100%

Correct script path prefix

100%

History path used

100%

Link Trail Report format

100%

Per-session breakdown

100%

Successful vs failed separation

100%

Follow-up offers

100%

Without context: $0.9307 · 3m 48s · 27 turns · 23 in / 15,372 out tokens

With context: $0.8075 · 2m 14s · 32 turns · 147 in / 7,081 out tokens

100%

Recover Documentation Links from a Specific Session

Date-specific session filtering

Criteria

Without context

With context

Uses parse_webfetch script

100%

Uses generate_report script

100%

Pipeline pattern used

100%

Date glob pattern

100%

Correct history path

100%

Correct script path prefix

100%

Report contains only Jan 22 sessions

100%

Report format correct

100%

Without context: $0.5065 · 2m 18s · 17 turns · 18 in / 8,487 out tokens

With context: $0.5930 · 1m 43s · 28 turns · 56 in / 5,918 out tokens

98%

14%

Investigate Failed Resource Fetches in AI Coding Sessions

Key findings highlighting and follow-up offers

Criteria

Without context

With context

Uses parse_webfetch script

100%

Uses generate_report script

100%

Pipeline used

50%

100%

Script output preserved

100%

Failed fetches identified

100%

HTTP status for failures

100%

Most accessed domain highlighted

86%

Offer to retry failed fetches

100%

Additional follow-up offered

100%

Without context: $0.8403 · 3m 43s · 26 turns · 27 in / 13,143 out tokens

With context: $0.8317 · 3m 49s · 24 turns · 58 in / 14,115 out tokens

Evaluated: about 19 hours ago
Agent: Claude Code

Table of Contents

Audit AI-Fetched URLs Before Security Review Recover Documentation Links from a Specific Session Investigate Failed Resource Fetches in AI Coding Sessions

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.