optimize
Skill0 starsChanged 4 months agoMITView on GitHub
Make a long/expensive run faster WITHOUT changing the science. Estimate cost from a measured slice, find the real bottleneck by measurement (never guessing), apply the highest-payoff lever (batch width, vectorize, GPU, parallelism, persist/reload), and PROVE result-invariance before/after. Use when the user says "/optimize", "make this faster", "this run is too slow/expensive", or when /research hits a >=2hr / large-compute task.
77 other projects use a version of this.
Adopted by
Most recently taken up by
- flavien-ia/hypervibe-harnesstheir own version, first seen Nov 15, 2026
- ffroliva/gflow-clitheir own version, first seen Nov 15, 2026
- localixai/tokendoctortheir own version, first seen Nov 15, 2026
- theexperiencecompany/gaiatheir own version, first seen Nov 13, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tooltheir own version, first seen Nov 8, 2026
Used with
Projects with it also use arrange, teach-impeccable and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
HK-hubSkillarrange
Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.
Also in 13 projects that use this
HK-hubSkillteach-impeccable
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
Also in 16 projects that use this
zwy123zwySkillnormalize
将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。
Also in 18 projects that use this
open-coder-aiSkillpolicy-init
Create conformant Chock policy from request. args(request, target_path,
Also in 3 projects that use this
- +8 more from HK-hub
Other versions77 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 77
- Z3Prover/z3★ 13ksame name
- highcharts/highcharts★ 13ksame name
- whitecircle/halo★ 863same name
- hacan359/tonkatsu_box★ 597same name
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- nexmoe/DayBee★ 424same name
- nexmoe/eve★ 424same name
- ffroliva/gflow-cli★ 396same name
- Southclaws/storyden★ 351same name
- 10xChengTu/Mux0★ 337same name
67 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- fleet/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/atlas.mdcCursor rule
- add-repoSkill
- atlas-setupSkill
- councilSkill
- mediateSkill
- onboardSkill
- registry-syncSkill
- researchSkill
- snapshotSkill
- sync-repo-knowledgeSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 74 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Prove invariance: Run the old and new paths on the same seed/slice and show the outputs match (bit-for-bit, or within a stated tolerance).
- Very specific: line 26
Never trade correctness for speed silently.
“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/optimize - faster, same science
Speed up an expensive run while proving the result does not change.
Procedure
- Measure a slice. Time a small representative slice; extrapolate the full cost. Report the estimate before doing anything big.
- Find the bottleneck by measurement - profile / time the stages. Never guess where the time goes.
- Apply the highest-payoff lever for the measured bottleneck:
- batch width (process many items at once instead of a Python loop),
- vectorize / use the right BLAS/GPU,
- parallelize across cores/nodes (mind memory-bandwidth limits - more cores ≠ linear speedup on bandwidth-bound kernels),
- persist/reload expensive intermediates instead of recomputing.
- Prove invariance. Run the old and new paths on the same seed/slice and show the outputs match (bit-for-bit, or within a stated tolerance). An optimization that changes the numbers is a different experiment, not a speedup - stop and flag it.
- Record the win (what changed, the speedup, the invariance check) so it's reusable.
Rule
Never trade correctness for speed silently. If a lever changes results, it is out of scope for
/optimize - surface it as a science change for explicit decision.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

