Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tobihagemann/survey-patterns
Survey the codebase for analogous features, reusable utilities, and existing patterns relevant to a proposed change. Returns structured findings without writing code.
Passed 7 of 18 test cases with the skill, and 2 of 18 without it.
and 6 more in the full report
8 fixed1 passed either way13 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are considering adding GraphQL subscription support to our API layer. Give us a detailed multi-paragraph overview of your search plan before starting any subagent work.
| Checked | Without skill | With skill |
|---|---|---|
| States the confirmed task back in exactly one sentence before searching. | Missed | Passed |
The instructions your model reads when the skill loads.
Search the codebase for analogous features and reusable building blocks before planning a change, and read any source the task names outside this repo. Returns structured findings. Does not write code or plans.
Determine what the change is about:
State the task back in one sentence to confirm scope before searching.
Spawn a single subagent (model: "opus", no name). Wait for it to report before continuing; do not relaunch it if it has not yet reported. Its prompt must direct it to treat the shared working tree and its git index as read-only and to survey by reading and reasoning. HEAD stays where it is: read other refs with git show <ref>:<path> rather than git checkout or git switch. The subagent's prompt must include:
The subagent covers all three categories (Analogous Features, Reusable Utilities, Convention Anchors) in one sweep, reads any external source the task names, and returns a single structured report.
Output the subagent's report verbatim. Do not reformat or re-synthesize — references/pattern-surveyor.md specifies the exact output format the subagent produces.
Then use the TaskList tool and proceed to any remaining task.
test cases passed, vs 2 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.