exploration-optimizer — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited exploration-optimizer (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
<example> <commentary>User wants to evaluate and improve a specific exploration skill.</commentary> User: Evaluate and improve the exploration-session-brief skill using the optimization loop. Agent: [invokes exploration-optimizer, runs baseline-first iteration on exploration-session-brief] </example>
<example> <commentary>User notices a skill feels weak and wants a systematic improvement cycle.</commentary> User: The exploration cycle feels slow — help me identify which skill to optimize first. Agent: [invokes exploration-optimizer, runs discovery phase to identify highest-impact target] </example>
<example> <commentary>BRD generation routes to business-requirements-capture, not this skill.</commentary> User: Generate a BRD from our session captures. Agent: [invokes business-requirements-capture, NOT exploration-optimizer] </example>
Ask for:
Confirm:
This skill implements autoresearch-style optimization for the exploration-cycle system. It uses a baseline-first iteration loop to improve skill prompts and logic.
Usage:
python ./scripts/execute.py \
--target ${plugins}/skills/user-story-capture/SKILL.md \
--eval-script ./scripts/eval_runner.py \
--goal "Improve Gherkin block accuracy" \
--iterations 3The execute.py script follows a disciplined loop:
keep or discard.Always conclude execution with a Source Transparency Declaration explicitly listing what was queried to guarantee user trust: Sources Checked: [list] Sources Unavailable: [list]
<!-- Suggest logical follow-up skills here. For example: -->
./scripts/benchmarking/run_loop.py --results-dir evals/experiments for repeatable improvement loops.audit-plugin to verify the generated artifacts.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.