targeted-questions
100 / 100 · Low risk
Fine to try.
Ask the minimum set of high-value factual questions needed to proceed safely, then persist the result in the task repository. Covers factual gaps only. Use when impact analysis or boundary definition found missing facts, correctness depends on unconfirmed information, or planning is blocked. Do not use for missing decisions (use decision-interview), when enough is known to plan, or, mid-implementation, when the gap is not correctness-critical.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'targeted-questions' ] || [ -L ~/.agents/skills/'targeted-questions' ]; then echo 'A skill folder named targeted-questions already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Mozurok/fhorja.dev' "$d" && git -C "$d" checkout --quiet '1abe596aff3cd974459118b57ecd631a69ea34f0' -- '.claude/skills/targeted-questions' && mkdir -p ~/.agents/skills && cp -R "$d"/'.claude/skills/targeted-questions' ~/.agents/skills/'targeted-questions' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'targeted-questions' ~/.claude/skills/'targeted-questions' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/Mozurok/fhorja.dev/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | 1abe596 | 100 |