Agent skill

Revyl CLI Optimize Tests

by RevylAI in RevylAI/revyl-cli

Optimize existing Revyl YAML tests by converting granular, button-press-level steps into intent-driven natural-language instructions, reducing step count and run time without losing coverage.

No licenceAuto-check passed

Install Revyl CLI Optimize Tests

skills CLI
$ npx skills add RevylAI/revyl-cli --skill revyl-cli-optimize-tests -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install RevylAI/revyl-cli revyl-cli-optimize-tests --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/RevylAI/revyl-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/revyl-cli-optimize-tests .claude/skills/revyl-cli-optimize-tests && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
revyl-cli-optimize-tests
GitHub stars
522
Token cost
~4.5k tokens
SKILL.md length
2,178 words
Files
2
Skills in repo
20
Repo updated
First seen
Licence
None found

At a glance

Optimize existing Revyl YAML tests by converting granular, button-press-level steps into intent-driven natural-language instructions, reducing step count and run time without losing coverage.

  • Works in 5 steps: Pull the last execution → Inspect each instruction step's actual… → Pull screenshots for a visual check → …
  • SKILL.md covers Native Agent Behavior, Why This Matters, Modes and Optimization Loop, plus 6 more sections
  • Calls curl

What it does

Revyl CLI Optimize Tests is an agent skill from RevylAI/revyl-cli. Optimize existing Revyl YAML tests by converting granular, button-press-level steps into intent-driven natural-language instructions, reducing step count and run time without losing coverage. Supports a deep mode that inspects the last execution's report and screenshots to verify instruction wording against what actually happened on screen.

Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

Example prompts

  • “/revyl-cli-optimize-tests”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Pull the last execution
  2. Inspect each instruction step's actual evidence
  3. Pull screenshots for a visual check
  4. Rewrite grounded in the evidence, goal-state first
  5. Standard guardrails still apply

What it can do on your machine

Read from SKILL.md and the folder at commit a860206. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Revyl CLI Optimize Tests loads about 4.5k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 2,178 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~4.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 2,178 words (~4,470 tokens).

“Revyl executes instructions steps with an LLM driving perception and action against the live screen. Each step is its own reasoning-and-action loop, so:”

— opening of SKILL.md by RevylAI
name
revyl-cli-optimize-tests

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/revyl-cli-optimize-tests of RevylAI/revyl-cli.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit a860206

Compare with similar skills

Revyl CLI Optimize Tests next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Revyl CLI Optimize Tests compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Revyl CLI Optimize Tests this skillRevylAI/revyl-cli522—~4.5kAutomated safety check: PassNone
Convertremotion-dev/remotion62k—~247Automated safety check: PassCustom licence
SQL Optimizationgithub/awesome-copilot40k2 repos~2.3kAutomated safety check: PassMIT
Agent Performance Optimizerruvnet/ruflo74k2 repos~3.6kAutomated safety check: PassMIT
Database Optimizerdavila7/claude-code-templates32k8 repos~2.5kAutomated safety check: PassMIT
Prompt Optimizeraffaan-m/ECC275k2 repos~2.4kAutomated safety check: PassMIT

Similar skills

  • Convert

    remotion-dev/remotion

    Official

    Start the local @remotion/convert app and open it in the Codex browser.

    62k GitHub stars~247 tokensUpdated today
    Media & CreativeAuto-check passed
  • SQL Optimization

    github/awesome-copilot

    Official

    Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server…

    40k GitHub starsUsed in 2 repos~2.3k tokens
    DatabasesAuto-check passed
  • Agent skill for performance-optimizer - invoke with $agent-performance-optimizer

    74k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed
  • Database Optimizer

    davila7/claude-code-templates

    Expert database optimizer specializing in modern performance tuning, query optimization, and scalable architectures.

    32k GitHub starsUsed in 8 repos~2.5k tokens
    DatabasesAuto-check passed
  • Prompt Optimizer

    affaan-m/ECC

    分析原始提示,识别意图和差距,匹配ECC组件(技能/命令/代理/钩子),并输出一个可直接粘贴的优化提示。仅提供咨询角色——绝不自行执行任务。触发时机:当用户说“优化提示”、“改进我的提示”、“如何编写提示”、“帮我优化这个指令”或明确要求提高提示质量时。中文等效表达同样触发:“优化prompt”、“改进prompt”、“怎么写prompt”、“帮我优化这个指令”。不触发时机:当用户希望直接执行任…

    275k GitHub starsUsed in 2 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Cost Optimize

    ruvnet/ruflo

    Analyze token usage patterns and recommend cost optimizations with estimated savings

    74k GitHub starsUsed in 1 repo~997 tokens
    AI & LLM EngineeringAuto-check: notes

More from RevylAI/revyl-cli

All 20 skills in this repo
  • Revyl CLI

    RevylAI/revyl-cli

    Base CLI skill for Revyl command-driven workflows. An agent skill from RevylAI/revyl-cli.

    522 GitHub stars~825 tokensUpdated today
    Auto-check passed
  • Revyl CLI Atlas Review

    RevylAI/revyl-cli

    Inspect exact Atlas evidence and manage grounded annotation feedback when the user explicitly requests a feedback mutation.

    522 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Find meaningful visual differences between confidently matched iOS and Android app states in Revyl Atlas.

    522 GitHub stars~4.5k tokensUpdated today
    Auto-check passed
  • Revyl Proof Automation

    RevylAI/revyl-cli

    Set up a Cursor Automation that proves each pull request on a Revyl cloud device using a CI-uploaded build.

    522 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Revyl CLI Auth Bypass

    RevylAI/revyl-cli

    Set up test-only auth bypass for Revyl runs across Expo, React Native, native iOS, native Android, and Flutter apps.

    522 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Revyl CLI Analyze

    RevylAI/revyl-cli

    Analyze failed Revyl test, workflow, and device-session reports via CLI to classify real bugs, flaky tests, infra issues, setup failures, or test-design improvements.

    522 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Questions about Revyl CLI Optimize Tests

What does Revyl CLI Optimize Tests do?

Optimize existing Revyl YAML tests by converting granular, button-press-level steps into intent-driven natural-language instructions, reducing step count and run time without losing coverage. Revyl CLI Optimize Tests is an agent skill from RevylAI/revyl-cli. Optimize existing Revyl YAML tests by converting granular, button-press-level steps into intent-driven natural-language instructions, reducing step count and run time without losing coverage.

How do I install Revyl CLI Optimize Tests in Claude Code?

Run `npx skills add RevylAI/revyl-cli --skill revyl-cli-optimize-tests -a claude-code`. Or copy the skill folder (skills/revyl-cli-optimize-tests in RevylAI/revyl-cli) into .claude/skills/revyl-cli-optimize-tests in your project. Claude Code loads it when a task matches its description.

How do I install Revyl CLI Optimize Tests in Codex?

Run `npx skills add RevylAI/revyl-cli --skill revyl-cli-optimize-tests -a codex`. Or copy the skill folder (skills/revyl-cli-optimize-tests in RevylAI/revyl-cli) into .agents/skills/revyl-cli-optimize-tests in your project. Codex loads it when a task matches its description.

Can I use Revyl CLI Optimize Tests in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RevylAI/revyl-cli --skill revyl-cli-optimize-tests -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/revyl-cli-optimize-tests, .gemini/skills/revyl-cli-optimize-tests, .github/skills/revyl-cli-optimize-tests and .opencode/skills/revyl-cli-optimize-tests in your project.

What does Revyl CLI Optimize Tests need to run?

Going by SKILL.md and its folder, Revyl CLI Optimize Tests needs the command-line tools its instructions call (curl).

Does Revyl CLI Optimize Tests access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Revyl CLI Optimize Tests safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Revyl CLI Optimize Tests use?

No licence was found for Revyl CLI Optimize Tests or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Revyl CLI Optimize Tests use?

About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Revyl CLI Optimize Tests?

Skills that share tags, products or a category with Revyl CLI Optimize Tests: Convert (remotion-dev/remotion, 62k stars), SQL Optimization (github/awesome-copilot, 40k stars), Agent Performance Optimizer (ruvnet/ruflo, 74k stars) and Database Optimizer (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Revyl CLI Optimize Tests?

RevylAI (a GitHub organization) maintains it in RevylAI/revyl-cli, which has 522 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 7, 2026.

Source: RevylAI/revyl-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.