Automated summary
Verifies the authenticity of a Data Walker project's raw source files by checking URL reachability, presence of downloaded files, duplicates, and suspiciously small file sizes.
Strengths
- Five concrete checks: URL validation, file existence, md5 duplicate detection, minimum size thresholds, and unique download URLs per source
- Structured report that classifies issues by type (MISSING, BROKEN_URL, DUPLICATE, SUSPECT)
- Filtering options (--all, --category, --source) plus a --fix mode that searches Archive.org for alternatives
- Size thresholds are tailored per data type (audio, DNA, cosmos, PDB)
Limitations
- Tightly coupled to the Data Walker project layout (data_walker_rs/, data/ subfolders, sources.yaml)
- HEAD request checks may return 403/404 due to rate limiting; the skill only advises waiting and retrying
- Duplicate detection only covers audio files in the provided md5 example
Use it after downloading datasets, or whenever you suspect files in the source catalog are missing, corrupted, or duplicated.
Not useful outside a Data Walker-style project with sources.yaml and a data/ directory, nor for judging the semantic quality of the data rather than its integrity.
Security analysis
CautionThe skill performs verification tasks using bash, cargo, and network HEAD/Archive.org requests. All commands shown are read-only inspection and re-downloading of the project's own data, with no obfuscation, no destructive operations, and no sending of secrets/tokens outward. Because it invokes build-and-run tooling and network access, it warrants mild caution rather than being fully inert.
- •Executes `cargo run` which builds and runs code from the local data_walker_rs project, so behavior depends on that repo's code
- •Performs network requests (HTTP HEAD checks and Archive.org searches in --fix) — legitimate but outbound
- •Read-only bash utilities (md5sum, find) used; no destructive or exfiltrating commands present
Examples
/authenticate-sources --all/authenticate-sources --category audio --fixAuthenticate sources for source id cosmos-01 and tell me if the downloaded file is suspect or broken.name: authenticate-sources description: Verify all raw source files are authentic and URLs are valid. Use when user says "authenticate sources", "validate data", "check sources", "verify downloads", or invokes /authenticate-sources. Supports --all, --category, --source, and --fix options. metadata: author: Data Walker version: 1.0.0
Authenticate Sources
Verify all raw source files are authentic and URLs are valid.
Usage
/authenticate-sources [options]
Options
--all- Check all sources (default)--category <name>- Check only sources in a category--source <id>- Check a specific source--fix- Attempt to fix broken URLs by searching for alternatives
Instructions
Step 1: URL Validation
For each source in sources.yaml, verify the source URL is still accessible:
cd data_walker_rs && cargo run -- list
Then check each URL with HTTP HEAD requests to verify they're still valid.
Step 2: File Existence Check
Verify downloaded files exist in data_walker_rs/data/:
data/audio/- Check for.wavand.mp3filesdata/dna/- Check for.fastafilesdata/cosmos/- Check for.txt.gzfilesdata/finance/- Check for.jsonfilesdata/proteins/- Check for.pdbfiles
Step 3: Duplicate Detection
Check for duplicate files (same content with different names):
cd data_walker_rs/data/audio && md5sum *.mp3 *.wav 2>/dev/null | sort | uniq -d -w32
Step 4: File Size Validation
Flag suspiciously small files that may be error pages or corrupted:
- Audio files < 10KB are suspect
- DNA files < 100 bytes are suspect
- Cosmos files < 1KB are suspect
- PDB files < 1KB are suspect
Step 5: Download URL Verification
Check that the hardcoded URLs in src/download.rs match unique content:
- Each source ID should map to a unique URL
- No two sources should download the same file
Report Format
=== SOURCE AUTHENTICATION REPORT ===
VALID SOURCES: X
MISSING FILES: X
BROKEN URLS: X
DUPLICATE FILES: X
SUSPECT FILES: X
--- ISSUES ---
[MISSING] source_id - file not found
[BROKEN_URL] source_id - HTTP 404
[DUPLICATE] source_id1, source_id2 - same file content
[SUSPECT] source_id - file too small (X bytes)
Fixing Issues
If --fix is specified:
- For broken URLs, search Archive.org for alternatives
- For duplicates, find unique source files
- Re-download fixed sources
Troubleshooting
Error: Many URLs return 403/404 Cause: Network issues or rate limiting Solution: Wait and retry, or check if sources have moved
Error: Duplicate content detected Cause: Two sources point to the same file Solution: Find unique source files or remove duplicates from sources.yaml
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/authenticate-sources-mrwakewh/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/authenticate-sources-mrwakewh' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/authenticate-sources-mrwakewh/download' --output '.skill-downloads/authenticate-sources-mrwakewh/SKILL.md.part' && mv '.skill-downloads/authenticate-sources-mrwakewh/SKILL.md.part' '.skill-downloads/authenticate-sources-mrwakewh/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/authenticate-sources-mrwakewh/SKILL.md' && test -s '.skill-downloads/authenticate-sources-mrwakewh/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/authenticate-sources' && cp -R '.skill-downloads/authenticate-sources-mrwakewh' '.claude/skills/authenticate-sources'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/authenticate-sources-mrwakewh'openskills read 'authenticate-sources-mrwakewh'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/authenticate-sources-mrwakewh/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Create Interactive Maps with kepler.gl
Data & AI
Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.
Agent-Driven Parameter Optimization
Data & AI
Guide for optimizing configurable systems with a measurable objective, using bounded trials and evidence-based recommendations.
ICP Visitor Outreach
Data & AI
Identify signed-up users matching the ideal customer profile but stalled, and draft personalized outreach to re-engage them.