feat(skills): add perf skill and plugin manifest - #15
Merged
Conversation
ms-shashank
force-pushed
the
feat/perf-skill
branch
from
August 24, 2026 18:11
deee7ed to
2f367a1
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #8
Summary
Adds the
perfskill and plugin manifest enforcing benchmarked numbers, baseline commands, paired after measurements, and input scale boundaries.What task was tested
Tested on optimizing batch order tax calculation ($N = 5,000$ ).
Without skill: The model defaulted to speculative code cleanups and asserted "this should be faster" without running benchmarks or profiling.
With skill: The model refused to optimize without baseline numbers, identified the N+1 dictionary lookup bottleneck via profiling, recorded paired before/after measurements (142.6 ms -> 18.2 ms, 7.8x speedup), stated the input size where the result holds ($N = 5,000$ ), and noted trade-offs for $N = 1$ .
Deliberately left out
Automatic rewriting of micro-optimizations (e.g. loops vs list comprehensions) unless verified by profile traces.
Guessing performance improvements when benchmarks or databases are unavailable.
Tools matching
tools: fullmatches the active profiling, benchmarking, and code editing operations required by the skill's method.