Agent Analytics Autoresearch
v1.0.1Run an autoresearch-style growth loop for landing pages, onboarding, pricing, and experiment candidates. Collect or read analytics snapshots, preserve produc...
⭐ 0· 20·0 current·0 all-time
byDanny Shmueli@dannyshmueli
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill claims to run an autoresearch growth loop and includes templates, loop instructions, and helper scripts that collect analytics snapshots and initialize runs. Requiring npx and referencing @agent-analytics/cli is coherent with the stated purpose.
Instruction Scope
SKILL.md confines the agent to reading/writing local run files (brief.md, results.tsv, final_variants.md) and collecting analytics snapshots. It explicitly forbids editing production code without explicit user approval. The instructions accept many analytics data sources and do not direct the agent to read unrelated system files or to transmit data to unexpected endpoints.
Install Mechanism
No install spec is declared (instruction-only), but the scripts call npx to fetch and run a pinned npm package (@agent-analytics/cli@0.5.12). Using npx is expected for a CLI-driven workflow but carries the typical risk that running npx executes code from the npm registry; this is proportional to the task but worth reviewing if you don't trust the package source.
Credentials
The skill does not request environment variables, credentials, or config paths. The scripts and docs use local variables (PROJECT_SLUG, PRIMARY_EVENT, PROXY_EVENT) provided at runtime, which is appropriate for analytics collection.
Persistence & Privilege
The skill is not always-enabled and does not attempt to modify other skills or system-wide settings. It writes only to its run directory and created run artifacts, which matches its purpose and includes clear guidance to avoid wiring experiments without explicit human approval.
Assessment
This skill appears coherent and focused on generating A/B test variants from analytics snapshots. Before installing or running: 1) be aware that the included scripts use npx to fetch and execute @agent-analytics/cli from the npm registry — only run that if you trust the package and its pinned version; consider auditing the CLI or running in an isolated environment. 2) The agent will read and write files in the run directory (brief.md, results.tsv, final_variants.md, data/...), so avoid using a production folder as the run directory. 3) The skill will not wire experiments or change production unless you explicitly instruct it to, but double-check the outputs before applying them to live systems. 4) If you use Agent Analytics login, confirm you understand the CLI's authentication flow (it may require interactive login or tokens) and only provide credentials through the platform's normal secure mechanisms.Like a lobster shell, security has layers — review code before you run it.
latestvk9725sexed6f5a26766fecyjkn84wsz8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
Any binnpx