agentleFS
Sign inStart free
waynesuttonwaynesutton/markdown-site/.claude/workflow/SKILL.md

workflow

Skill628 starsChanged 7 months agoMITView on GitHub

Project workflow for PRDs, task tracking, changelog sync, and documentation updates. Use for any non-trivial task that spans multiple steps, touches several files, changes architecture, or needs project tracking updates. Also activates with @update to sync task.md, changelog.md, and files.md after completing work.

71 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use build-keil, can-debug and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ZhongYechengSkill

    build-keil

    当需要通过 Keil MDK 命令行编译嵌入式工程，调用自带脚本解析工程文件、执行构建并定位固件产物时使用。

    Also in 3 projects that use this

  • ZhongYechengSkill

    can-debug

    当需要调试 CAN 总线通信时使用，支持通过 USB-CAN 适配器监听、发送 CAN 帧和扫描节点。

    Also in 3 projects that use this

  • iPlug2Skill

    build-cmake

    Build an iPlug2 plugin project using CMake with Ninja, Xcode, or Visual Studio generators

    Also in 3 projects that use this

  • +9 more from ZhongYecheng

The file

Show its rules and text

We split this skill into the rules it gives an agent

20 rules. 0 are common, 16 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 55 edited versions we read keep these.

  • 16

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for any non trivial task that spans multiple steps, touches several files, changes architecture, or needs project tracking …

    line 8
  2. Distinctive:

    Ask if anything important is still unclear.

    line 19
  3. Distinctive:

    Create a PRD before non trivial work.

    line 25
  4. Distinctive:

    Add metadata at the top:

    line 38
  5. Very specific:

    Update task.md as the work moves forward.

    line 46
  6. Very specific:

    Put new work under ## to do

    line 48
  7. Very specific:

    Add timestamps in YYYY-MM-DD HH:mm UTC

    line 50
  8. Distinctive:

    Do not mark a task done until it has been verified

    line 51
  9. Distinctive:

    Keep task notes short but specific enough for the next session

    line 52
  10. Distinctive:

    After each feature or fix, sync the project docs:

    line 62
  11. Distinctive:

    use Keep a Changelog structure

    line 70
  12. Distinctive:

    add timestamps when helpful

    line 72
  13. Distinctive:

    update descriptions that changed

    line 77
  14. Distinctive:

    keep descriptions brief and concrete

    line 78
  15. Distinctive:

    Use subagents for research or parallel analysis when the task is large enough to benefit.

    line 82
  16. Distinctive:

    Use one focused subagent per task.

    line 83
  17. Distinctive:

    Stop and re plan if the work stops making sense.

    line 84
  18. Distinctive:

    Keep the change set tight.

    line 85
  19. Distinctive:

    Ask whether a staff engineer would approve the result before calling it done.

    line 86
  20. Very specific:

    If the user corrects a repeated pattern, record the lesson in prds/lessons.md so the mistake does not come back.

    line 90

“Common” is measured: kept by at least 6 in 10 of the 55 edited versions of this file we could read. “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

Project Workflow Skill

Use this skill for any non trivial task that spans multiple steps, touches several files, changes architecture, or needs project tracking updates.

Activate with: @update (for docs sync only)

Triage first

Before changing code:

  1. Identify what is missing, broken, or incomplete.
  2. Theorize a few likely causes or approaches.
  3. Narrow to the most likely plan.
  4. Ask if anything important is still unclear.

Skip the long process only for obvious one file fixes like typos or tiny copy changes.

PRD rules

Create a PRD before non trivial work.

  • Path: prds/<feature-or-problem-slug>.md
  • Extension: .md
  • Include:
    • problem
    • root cause for bugs
    • proposed solution
    • files to change
    • edge cases
    • verification steps
    • task completion log

Add metadata at the top:

  • Created: YYYY-MM-DD HH:mm UTC
  • Last Updated: YYYY-MM-DD HH:mm UTC
  • Status: Draft | In Progress | Done

Task tracking

Update task.md as the work moves forward.

  • Put new work under ## to do
  • Move finished work to ## completed
  • Add timestamps in YYYY-MM-DD HH:mm UTC
  • Do not mark a task done until it has been verified
  • Keep task notes short but specific enough for the next session

When useful, include:

  • the PRD path
  • the files touched
  • the verification command or outcome

Docs sync after changes

After each feature or fix, sync the project docs:

  • task.md
  • changelog.md
  • files.md

For changelog.md:

  • use Keep a Changelog structure
  • get real dates from git log --date=short -n 10
  • add timestamps when helpful

For files.md:

  • add new files
  • update descriptions that changed
  • keep descriptions brief and concrete

Execution style

  • Use subagents for research or parallel analysis when the task is large enough to benefit.
  • Use one focused subagent per task.
  • Stop and re plan if the work stops making sense.
  • Keep the change set tight.
  • Ask whether a staff engineer would approve the result before calling it done.

Learning loop

If the user corrects a repeated pattern, record the lesson in prds/lessons.md so the mistake does not come back.

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.

Check your setup, free