code-optimization

Optimize code performance through iterative improvements (max 2 rounds). Benchmark execution time and memory usage, compare against baseline implementations, and generate detailed optimization reports. Supports C++, Python, Java, Rust, and other languages.

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./.trae/openclaw-skills/code-optimization/SKILL.md

Quality

Content

56%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 content is well-structured and actionable with concrete commands and validation checkpoints, but it is verbose with heavy redundancy and inlines material that would benefit from being split into reference files. Trimming repetition and extracting the report templates would materially improve it.

Suggestions

Consolidate the repeated 2-iteration-limit messaging into one authoritative section and remove the redundant restatements throughout.

Remove or compress sections that re-explain general optimization concepts (SIMD, cache locality, SoA vs AoS) that Claude already knows.

Extract the full report example and report template into a separate references file (e.g., report-template.md) and link to it, eliminating the duplicated inlined copy.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the 2-iteration limit is restated roughly eight times, and sections re-explain concepts Claude already knows (cache locality, SIMD, SoA vs AoS, lock-free algorithms), plus a full duplicate report template.	2 / 5
Actionability	Most guidance is executable — concrete g++/perf/valgrind/sanitizer commands and a full report template — but the lead code example is a pseudocode placeholder ('Fill in the my_topk_inplace function') and read_file/write_file are abstract tool names rather than real commands.	4 / 5
Workflow Clarity	A clear 5-step sequence with explicit stopping criteria and validation checkpoints (correctness verification, sanitizers, diff comparison, PASS/FAIL); minor gaps keep it just below the feedback-loop-rich anchor at 5.	4 / 5
Progressive Disclosure	No bundle files exist, so all content — including a duplicated full report example and template, strategy catalog, and tool reference — is inlined in one monolithic file with headers but no one-level-deep references to separate files.	3 / 5
	Total	13 / 20 Passed

Description

75%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 specific and distinctive with concrete actions and clear language coverage, but it omits any 'when to use' trigger guidance, which caps completeness. Adding an explicit 'Use when...' clause would raise the completeness score.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants to speed up, benchmark, or optimize code performance against a baseline.'

Include more natural user phrasings (e.g., 'speed up', 'make faster', 'reduce runtime') alongside the technical terms.

Optionally name output artifacts in the trigger (e.g., 'or asks for an optimization report') to sharpen the when-to-use signal.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Optimize code performance', 'Benchmark execution time and memory usage', 'compare against baseline implementations', and 'generate detailed optimization reports' — with broad language coverage, matching the comprehensive-coverage anchor.	5 / 5
Completeness	The 'what' is clearly stated across several actions, but there is no 'Use when...' clause or explicit trigger guidance for when Claude should invoke the skill, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Domain keywords like 'code performance', 'benchmark execution time', and 'optimization reports' are present and natural, but common user phrasings such as 'make my code faster' or 'speed up' are missing, so it falls just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The niche is clearly defined — iterative performance optimization with a 2-round cap and baseline benchmarking — making it unlikely to trigger for unrelated skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: huangruiteng/CS-Notes
Path: .trae/openclaw-skills/code-optimization/SKILL.md
Commit: 43eb317

Reviewed: 3 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.