agentleFS
JacobinwweyJacobinwwey/notemdpro/skills/batch-processor/SKILL.md

batch-processor

Skill2 starsChanged 38 days agoMITView on GitHub

Execute bounded Markdown batches with complete task logs and explicit partial failures.

2 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, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use workflow-runner for the common task record.

    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

Batch processor

English

Use workflow-runner for the common task record. Resolve the authorized folder and output policy once. Enumerate eligible files deterministically, exclude symlinks outside the selected tree, and process each file through read -> transform -> validate -> write. Recheck the source before writing; preserve unrelated notes and source artifacts.

Bound concurrency according to the host/provider. Retry only transient transport failures and HTTP 408/425/429/500/502/503/504 within a finite attempt/time budget; honor Retry-After when available. Authentication, invalid configuration, parser errors and cancellation do not retry. Stop scheduling new work when cancelled, retain completed outcomes, and report pending/cancelled files separately.

Keep a single task transcript across stages and files. Log stage, path, attempt, severity and actionable error summaries; never log credentials, authorization headers or raw provider payloads. Record partial failures honestly. File helper progress is separate from transcript retention. No app.vault API or local provider implementation exists here.

中文

共享任务记录遵循 workflow-runner。一次性确认授权目录及输出策略,确定性枚举可处理文件,排除指向选定目录外的符号链接,逐文件执行读取 -> 转换 -> 验证 -> 写入。写入前重新检查源文件,保留无关笔记与源产物。

按宿主/provider 能力限制并发。仅对暂态传输失败和 HTTP 408/425/429/500/502/503/504 在有限次数及时间内重试;可用时遵循 Retry-After。认证、配置、解析错误及取消不得重试。取消后停止调度,保留已完成结果,分别报告待处理及已取消文件。

跨阶段、跨文件保留一份完整任务日志。记录阶段、路径、重试次数、严重级别及可操作的错误摘要,不记录凭据、认证头或原始 provider 载荷。如实报告部分失败。进度与日志保留独立;此处不存在 app.vault API 或本地 provider 实现。

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.