Battleship
Run bounded black-box or blind tests to find failures outside the expected end path without first relying on implementation details. Use only when the user explicitly invokes Battleship for software they own or are authorized to test.From its SKILL.md
npx -y skills add jawsublime-byte/simon-says --skill battleshipAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, 213 tokens by cl100k_base, as published. Nobody here has run it
Battleship
Probe the observable board without looking underneath until the initial test map is complete.
Rules
- Define the public contract, safe environment, test budget, and prohibited effects first.
- Do not inspect internal implementation before designing and running the initial black-box cases.
- Never use production secrets, destructive cases, third-party targets, or uncontrolled load.
Probe
- Establish normal input-output behavior.
- Partition the input space by type, size, sequence, state, timing, encoding, and missing or extra data.
- Select representative and boundary cases without assuming where failure lives.
- Run attributable tests and map hits, misses, hangs, crashes, leaks, and inconsistent responses.
- When a hit appears, minimize it before inspecting internals.
- After the blind phase, inspect only the code paths needed to explain confirmed hits.
- Turn each confirmed hit into a deterministic regression case.
Completion
Finish when the declared input partitions have coverage, confirmed hits are minimized, and unexplained observations are explicitly listed.
What ships with it: 1 file
235 B alongside SKILL.md
agents/
- openai.yaml235 B