opportunity-tool-selection — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited opportunity-tool-selection (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this skill when an opportunity workflow needs a clear decision about whether to use web search, browser automation, MCP/API tools, local files, or ordinary chat reasoning.
This skill is generic. It applies to jobs, apartments, programs, vendor research, marketplaces, registrations, and similar search-then-act workflows.
Use chat-only reasoning when:
Do not use chat-only reasoning for current listings, prices, availability, deadlines, company facts, or database state.
Use normal web search when:
Prefer original source pages over aggregators once a promising result is found.
Use browser automation when:
Use browser automation for interaction and extraction. Do not use it to edit a structured system of record when an MCP/API tool is available.
Use MCP/API tools when:
Prefer MCP/API access over browser UI for systems of record. Browser UI is more fragile and easier to confuse with source extraction.
Use local files when:
Never publish private local data into reusable skills or public examples.
Do not use automation to bypass:
When a task crosses one of these boundaries, stop and hand control back to the user with the exact blocker and next action.
Return:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.