Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Web Archive Scraper · gooseworks-ai | DecimalAI

researchby gooseworks-ai

Web Archive Scraper

gooseworks-ai/web-archive-scraper

Source gooseworks-ai/goose-skills ↗License MIT

Search the Wayback Machine for archived versions of websites. Extract cached pages, customer lists, testimonials, and partner directories from sites that have changed or gone offline. Uses the free CDX API — no API key needed.

SkillScore86Maintained

Automatic

Research pack

Last verified 8/16/2026

What it changes

Passed 17 of 20 test cases with the skill, and 5 of 20 without it.

Without skill23%

With skill86%

Checks it passed that the model alone missed

The command sets --limit 50.
The command includes --fetch-all.
The command includes --limit 100.

and 15 more in the full report

14 fixed5 passed either way3 still failing0 broke

Pass-rate lift: +64 pp
Tokens: +14%
Agent turns: 0%
Response time: -40%

Model gemini-3.6-flashMeasured 8/16/2026v119 of 22 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/gooseworks-ai-web-archive-scraper/SKILL.md https://app.decimal.ai/s/gooseworks-ai-web-archive-scraper/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gooseworks-ai-web-archive-scraper, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/gooseworks-ai-web-archive-scraper/ and pins it in .decimal/skills.lock

decimalai skills add gooseworks-ai-web-archive-scraper

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/gooseworks-ai-web-archive-scraper/SKILL.md https://app.decimal.ai/s/gooseworks-ai-web-archive-scraper/SKILL.md

Raw file: /s/gooseworks-ai-web-archive-scraper/SKILL.md ↗ · machine-readable summary at /s/gooseworks-ai-web-archive-scraper.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

We want to collapse archive results so we only get one snapshot per month for https://oldbrand.org instead of daily snapshots. Which flag controls this deduplication grouping?

What was checked, without and with the skill
Checked	Without skill	With skill
The command includes --collapse month.	Missed	Passed

case-08 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md81 lines2 filesincludes scripts

Web Archive Scraper

Search the Wayback Machine (Internet Archive) for archived snapshots of websites. Fetch cached page content to find customer lists, testimonials, partner directories, and other information from sites that have changed or shut down.

Quick Start

Only dependency is requests. No API key needed.

# Find all snapshots of a URL
python3 skills/web-archive-scraper/scripts/search_archive.py \
  --url "https://botkeeper.com/customers"

# Search with date range
python3 skills/web-archive-scraper/scripts/search_archive.py \
  --url "https://botkeeper.com" --from 2025-01-01 --to 2026-02-01

# Search all pages under a domain (prefix match)
python3 skills/web-archive-scraper/scripts/search_archive.py \
  --url "https://botkeeper.com" --match prefix --limit 50

# Fetch the actual archived page content
python3 skills/web-archive-scraper/scripts/search_archive.py \
  --url "https://botkeeper.com/customers" --fetch

# Output formats
python3 skills/web-archive-scraper/scripts/search_archive.py --url URL --output json
python3 skills/web-archive-scraper/scripts/search_archive.py --url URL --output csv
python3 skills/web-archive-scraper/scripts/search_archive.py --url URL --output summary

How It Works

CDX API search — Queries web.archive.org/cdx/search/cdx for snapshots matching the URL
Filtering — Filters by date range, HTTP status code, and MIME type
Dedup — Collapses to one snapshot per day by default to avoid redundant results
Content fetch — Optionally fetches the raw archived HTML (using id_ modifier to skip Wayback toolbar)
Text extraction — Strips HTML tags for readable text output when fetching content

CLI Reference

Track record

Benchmark

17 / 20

test cases passed, vs 5 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

gooseworks-ai / goose-skills

skills/research-tools/capabilities/web-archive-scraper/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Web Archive Scraper

Quick Start

How It Works

CLI Reference

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills