warp-compile-time-optimizer

Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start or stalls at the first wp.launch; seconds of compiling before real work begins; JIT modules recompiling on every run or every CI job. Only applies when the code being optimized uses Warp kernels. Not for steady-state kernel runtime, memory, correctness, building Warp itself from source, or nvcc/C++ build times.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tightly structured, executable optimization playbook with a numbered workflow, validation feedback loops, and well-organized one-level-deep references. Its only weakness is mild verbosity in a few explanatory passages given its length.

Suggestions

Tighten the "Compilation model" prose: the module-identity and cold-start-cost formulas already convey the idea, so the surrounding sentences could be cut to one or two.

The "Preserve behavior" section lists many preserved attributes inline; consider folding the enumeration into the `references/mechanisms.md` verification checklist to shorten the body.

Collapse the two example tables in steps 1 and 3 where rows overlap, or move the diagnostic symptom table fully into `references/measurement.md` to reduce body length.

Dimension	Reasoning	Score
Conciseness	Information-dense — tables, executable commands, and domain-specific model explanation that Claude would not already know — but at roughly 290 lines a few explanatory passages (e.g., the "Compilation model" prose around module identity) could be tightened without losing clarity.	4 / 5
Actionability	Copy-paste-ready commands (`python scripts/warp_compile_probe.py measure --samples 3 --json baseline.json -- ...`, `compare`), concrete code for `wp.set_module_options()` / `wp.get_module()`, and a symptom→mechanism table cover the common cases fully.	5 / 5
Workflow Clarity	A clear six-step numbered workflow with explicit validation checkpoints — the probe `compare` rejects changed launch topology and flags inconclusive results, plus gradient-path and runtime-benchmark verification — and feedback loops for recovery.	5 / 5
Progressive Disclosure	SKILL.md is an overview that defers the thirteen mechanisms to `references/mechanisms.md` and the measurement protocol to `references/measurement.md` (both real files), with one-level-deep, clearly signaled references and a dedicated "Reference files" section.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a model trigger: third-person, opens with "Use when…", names concrete symptoms and synonyms, and explicitly bounds what the skill does and does not cover. It is comprehensive and highly distinguishable with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names multiple concrete situations — "improve, optimize, or cut compile times", "slow to start or stalls at the first wp.launch", "JIT modules recompiling on every run or every CI job" — giving comprehensive, concrete coverage rather than generic language.	5 / 5
Completeness	Explicitly answers both what (optimize/cut Warp compile and startup time) and when ("Use when compile time or startup time is the problem in code that uses Warp"), plus concrete trigger phrases and an explicit negative scope.	5 / 5
Trigger Term Quality	Uses natural phrases a user would actually say — "compile time", "startup time", "slow to start", "recompiling on every run or every CI job" — with synonyms and the recognizable `wp.launch` marker.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Warp kernel compile/startup time) with explicit exclusions — "Not for steady-state kernel runtime, memory, correctness, building Warp itself from source, or nvcc/C++ build times" — minimizing overlap with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/warp
Path: skills/warp-compile-time-optimizer/SKILL.md
Commit: 238de60

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.