Agent skill

Accutest

by syy12335 in syy12335/Environment-Runtime

生成 accutest workflow 任务,面向精度、质量、评分、效果评估场景. An agent skill from syy12335/Environment-Runtime.

MITAuto-check passed

Install Accutest

skills CLI
$ npx skills add syy12335/Environment-Runtime --skill accutest -a claude-code

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

GitHub CLI
$ gh skill install syy12335/Environment-Runtime accutest --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/syy12335/Environment-Runtime.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/task_router_graph/skills/controller/accutest .claude/skills/accutest && 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
accutest
GitHub stars
129
Token cost
~164 tokens
SKILL.md length
32 words
Files
2 (incl. scripts)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

生成 accutest workflow 任务,面向精度、质量、评分、效果评估场景. An agent skill from syy12335/Environment-Runtime.

  • SKILL.md covers 常见情况, 路由边界, task_content 生成要点 and Workflow I/O
  • Runs Python scripts from its folder

What it does

Accutest is an agent skill from syy12335/Environment-Runtime. 生成 accutest workflow 任务,面向精度、质量、评分、效果评估场景。

Its SKILL.md is about 160 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/run.py`).

The repository describes itself as: Environment-Runtime 是一个面向工程场景的轻量级 Agent Runtime。它源于 OpenClaw 在工程流程落地时偏重、等待体验不理想、稳定性不足的问题,希望把常见工程任务组织成更清晰、更可复用、更容易维护的运行时。项目还在成长阶段,欢迎认领 issue、提交 PR,一起参与开发。 The licence is MIT.

Example prompts

  • “/accutest”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 512c43b. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

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

  • Network

    No URLs in SKILL.md.

    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

Accutest loads about 164 tokens when it runs. Until then it costs about 13 tokens; SKILL.md has 32 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~13
When it runs · the whole SKILL.md, loaded when a task matches
~164

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); the scripts in this folder are not scanned.

SKILL.md

The full file from syy12335/Environment-Runtime at commit 512c43b, republished under its MIT licence (© syy12335). 32 words, ~164 tokens.

Download SKILL.mdSave it as .claude/skills/accutest/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
accutest
description
生成 accutest workflow 任务,面向精度、质量、评分、效果评估场景。
when_to_use
用户请求执行精度测试、质量评估、评分评测;且目标是执行评估而非解释历史结果。
task-mode
workflow
workflow-entry
scripts/run.py
status-aliases
精度测试, 准确率, 质量评估, 评分

Accutest Workflow Type

定位:accutest 用于精度、质量、评分、效果评估。

常见情况

  • 做一次精度测试
  • 评估这版输出质量
  • 给这个结果打分
  • 看一下模型效果

路由边界

  • 若用户要“解释上一轮 accutest 含义”,通常应路由到 executor。
  • 若用户要“执行评估”,应路由到 accutest。

task_content 生成要点

  • 明确评估对象
  • 明确核心评估维度(准确性/质量/评分)
  • 用简洁可执行语言描述本轮评估目标

Workflow I/O

  • 入口:scripts/run.py
  • 调用:run(*, task_content: str) -> dict
  • 返回:{"task_status": "done|failed", "task_result": "..."}

© syy12335, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in src/task_router_graph/skills/controller/accutest of syy12335/Environment-Runtime.

  • SKILL.md
  • scripts/run.py

Open the folder on GitHubat commit 512c43b

More from syy12335/Environment-Runtime

  • Functest

    syy12335/Environment-Runtime

    生成 functest workflow 任务,明确本轮功能测试对象、目标与关注方向. An agent skill from syy12335/Environment-Runtime.

    129 GitHub stars~214 tokensUpdated 4 mo ago
    Auto-check passed
  • Perftest

    syy12335/Environment-Runtime

    生成 perftest workflow 任务,面向延迟、吞吐、并发和压测评估. An agent skill from syy12335/Environment-Runtime.

    129 GitHub stars~168 tokensUpdated 4 mo ago
    Auto-check passed
  • Time Range Info

    syy12335/Environment-Runtime

    查询某个时间段的时效信息;需要先锚定当前时间,再检索外部信息并输出证据化结论。

    129 GitHub stars~248 tokensUpdated 4 mo ago
    Auto-check passed
  • Greeting Guide

    syy12335/Environment-Runtime

    处理问候、寒暄、能力介绍与使用引导场景,给出友好且可执行的下一步建议。

    129 GitHub stars~122 tokensUpdated 4 mo ago
    Auto-check passed

Questions about Accutest

What does Accutest do?

生成 accutest workflow 任务,面向精度、质量、评分、效果评估场景. An agent skill from syy12335/Environment-Runtime. Accutest is an agent skill from syy12335/Environment-Runtime.

How do I install Accutest in Claude Code?

Run `npx skills add syy12335/Environment-Runtime --skill accutest -a claude-code`. Or copy the skill folder (src/task_router_graph/skills/controller/accutest in syy12335/Environment-Runtime) into .claude/skills/accutest in your project. Claude Code loads it when a task matches its description.

How do I install Accutest in Codex?

Run `npx skills add syy12335/Environment-Runtime --skill accutest -a codex`. Or copy the skill folder (src/task_router_graph/skills/controller/accutest in syy12335/Environment-Runtime) into .agents/skills/accutest in your project. Codex loads it when a task matches its description.

Can I use Accutest 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 syy12335/Environment-Runtime --skill accutest -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/accutest, .gemini/skills/accutest, .github/skills/accutest and .opencode/skills/accutest in your project.

What does Accutest need to run?

Going by SKILL.md and its folder, Accutest needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Accutest access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Accutest 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Accutest use?

Accutest is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Accutest use?

About 164 tokens (SKILL.md is roughly 656 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

Who maintains Accutest?

syy12335 (a GitHub user) maintains it in syy12335/Environment-Runtime, which has 129 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on May 29, 2026.

Source: syy12335/Environment-Runtime on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.