Specstory link trail

Skill specstoryai/agent-skills/skills/specstory-link-trail

SpecStory's official collection of agent skills. Summarize, organize and create with `.specstory/history`

Install

npx -y skills add specstoryai/agent-skills --skill specstory-link-trail

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

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".

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.9 KB, as published. Nobody here has run it

SpecStory Link Trail

Reviews your .specstory/history sessions and creates a summary of all URLs that were fetched via WebFetch tool calls. Useful for auditing external resources accessed during development.

How It Works

Parses SpecStory history files for WebFetch tool calls
Extracts URLs, status codes, and context
Groups by session with timestamps
Separates successful fetches from failures
Deduplicates repeated URLs with fetch counts

Why Track Links?

During AI-assisted coding, your assistant fetches documentation, APIs, and resources on your behalf. Link Trail helps you:

Audit what external resources were accessed
Find that documentation page you saw earlier
Review failed fetches that might need retry
Understand your research patterns

Usage

Slash Command

User says	Script behavior
`/specstory-link-trail`	All sessions in history
`/specstory-link-trail today`	Today's sessions only
`/specstory-link-trail last session`	Most recent session
`/specstory-link-trail 2026-01-22`	Sessions from specific date
`/specstory-link-trail *.md`	Custom glob pattern

Direct Script Usage

# All sessions
python skills/specstory-link-trail/parse_webfetch.py .specstory/history/*.md | \
  python skills/specstory-link-trail/generate_report.py -

# Specific session
python skills/specstory-link-trail/parse_webfetch.py .specstory/history/2026-01-22*.md | \
  python skills/specstory-link-trail/generate_report.py -

# Sessions from a date range
python skills/specstory-link-trail/parse_webfetch.py .specstory/history/2026-01-2*.md | \
  python skills/specstory-link-trail/generate_report.py -

Output

Link Trail Report
=================

Sessions analyzed: 5
Total URLs fetched: 23 (18 successful, 5 failed)

Session: fix-authentication-bug (2026-01-22)
--------------------------------------------
Successful fetches:
  - https://docs.github.com/en/rest/authentication (×2)
  - https://jwt.io/introduction
  - https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/401

Failed fetches:
  - https://internal.company.com/api/docs (403 Forbidden)

Session: add-caching-layer (2026-01-21)
---------------------------------------
Successful fetches:
  - https://redis.io/docs/latest/commands
  - https://docs.python.org/3/library/functools.html#functools.lru_cache
  - https://stackoverflow.com/questions/... (×3)

Summary by Domain
-----------------
  github.com: 5 fetches
  stackoverflow.com: 4 fetches
  docs.python.org: 3 fetches
  redis.io: 2 fetches
  (9 other domains): 9 fetches

Present Results to User

The script output IS the report. Present it directly without additional commentary, but you may:

Highlight key findings - Most frequently accessed domains, any failed fetches
Offer follow-ups - "Want me to retry the failed fetches?" or "Need details on any of these?"

Example Response

Here's your link trail from recent sessions:

[script output here]

I noticed 5 failed fetches - mostly internal URLs that require authentication.
The most accessed domain was github.com (5 fetches), mostly for their REST API docs.

Would you like me to:
- Retry any of the failed fetches?
- Open any of these links?
- Filter to a specific session?

Notes

Uses streaming parsing for large history files
URLs are extracted from WebFetch tool calls in the history
Fetch counts show when the same URL was accessed multiple times
Failed fetches include the HTTP status code when available