Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →notque/read-only-ops
Read-only exploration, inspection, and reporting without modifications. Explore and report on code/config/state without writing or modifying anything.
Passed 8 of 17 test cases with the skill, and 7 of 17 without it.
and 6 more in the full report
6 fixed5 passed either way8 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Inspect running processes to see if `nginx` is active. Do not send signals or restart services. Provide summary, raw output, and examined paths.
| Checked | Without skill | With skill |
|---|---|---|
| Uses process inspection commands like pgrep or ps without kill or systemctl commands. | Missed | Passed |
| Displays raw process output. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill operates as a safe exploration and reporting mechanism without ever modifying files or system state. Use it when you need to gather evidence, verify facts, or show current state to the user.
The core principle: Observation Only. Gather evidence. Report facts. Keep all state unchanged.
Goal: Understand exactly what the user wants to know before exploring.
Step 1: Parse the request
Determine:
Step 2: Confirm scope if ambiguous
If the request could match dozens of results or span the entire filesystem, clarify before proceeding. If the scope is clear, proceed directly. This prevents wasting tokens on over-broad searches.
Gate: Scope is understood. Target locations are identified. Proceed only when gate passes.
Goal: Collect evidence using read-only tools. Tools must preserve state.
Step 1: Execute read-only operations
Allowed commands (safe for read-only use):
ls, find, wc, du, df, file, stat
test cases passed, vs 7 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.