agentleFS
JacobinwweyJacobinwwey/notemdpro/skills/workflow-runner/SKILL.md

workflow-runner

Skill2 starsChanged 38 days agoMITView on GitHub

Compose skill stages with complete task diagnostics and honest output status.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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
  1. Very specific:

    Create one task identity and ordered stage list for the user's request.

    line 10

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Workflow runner

English

Create one task identity and ordered stage list for the user's request. Track each stage's inputs, outputs and status (pending, running, completed, failed, cancelled, unavailable). A stage consumes only verified output from its dependencies. Preserve earlier outcomes when another stage starts or fails.

Retain full diagnostic records with stage, severity (error|warning|info), kind, message, source path and suggested action. Group by severity plus kind, never tag alone. In CLI summaries show counts and errors by default; keep warnings/information available in the full report. If the host offers disclosures, close the entire panel without errors, otherwise open only error groups. This skill does not provide a UI component.

Write an authorized task report with all stage outcomes and artifact paths, or return it in the conversation when file output was not requested. Never erase previous stage logs on a progress reset. Clear a retained report only on explicit user instruction. Redact credentials and provider payloads. Distinguish a successful source generation from preview/export success and preserve partial outputs on failure.

中文

为用户请求建立一个任务标识与有序阶段列表,记录每阶段的输入、输出及状态(pending、running、completed、failed、cancelled、unavailable)。阶段只消费已验证的依赖输出,后续阶段开始或失败时仍保留前序结果。

完整诊断记录包含 stage、severity(error|warning|info)、kind、消息、来源路径和建议操作。按严重级别加标签分组,不能仅按标签合并。CLI 摘要默认显示计数与错误,完整报告保留警告及信息。若宿主提供折叠界面,无错误时整体收起,有错误时仅展开错误组。本技能不提供界面组件。

在已授权范围内写入包含所有阶段结果和产物路径的报告;未请求文件输出时在会话中返回。进度重置不得擦除前序日志,只在用户明确要求时清空保留的报告。隐去凭据及 provider 载荷,区分源生成与预览/导出成功,失败时保留部分产物。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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.