agentleFS
midFangmidFang/ai-agent-skills-workflow/plan-to-issues-csv/SKILL.md

plan-to-issues-csv

Skill2 starsChanged 5 months agoMITView on GitHub

Convert a `plan/*.md` execution plan into a uniquely named `issues/*.csv` snapshot for long-lived tracking. Use when the user explicitly mentions `$plan-to-issues-csv`, asks to turn a plan into issues CSV, says "plan 转 issues", "从 plan 生成 CSV", or wants to replace the deprecated `/prompts:plan_to_issues_csv` workflow. Read one plan file, derive 5-30 maintainable issues rows, and write `issues/YYYY-MM-DD_HH-mm-ss-<slug>.csv` in UTF-8 BOM.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 8 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill as the replacement for the deprecated custom prompt /prompts:plan_to_issues_csv.

    line 8
  2. Very specific:

    If no path is provided, use the latest plan/*.md in the current workspace.

    line 22
  3. Distinctive:

    Read the plan file first, then read only the minimum referenced files needed to fill gaps.

    line 23
  4. Very specific:

    Always write a uniquely named snapshot under issues/.

    line 27
  5. Very specific:

    Never create or update issues/issues.csv, issues.csv, or any other fixed summary CSV.

    line 28
  6. Distinctive:

    Write the file as UTF-8 with BOM for Excel compatibility.

    line 29
  7. Distinctive:

    Keep the CSV maintainable: default to one issue row per plan phase unless a phase clearly contains multiple independent workstreams.

    line 30
  8. Distinctive:

    Use this exact header order:

    line 35
  9. Distinctive:

    Ensure the CSV is parseable.

    line 54
  10. Distinctive:

    Ensure every row has the full header width.

    line 55
  11. Distinctive:

    Ensure all state columns only use the allowed enum values.

    line 56
  12. Very specific:

    Ensure every row has a non-empty refs value.

    line 57
  13. Distinctive:

    If file writes are blocked, return the full CSV in a code block and state the target path plus the UTF-8 BOM requirement.

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Plan To Issues CSV

Use this skill as the replacement for the deprecated custom prompt /prompts:plan_to_issues_csv.

Invocation

Preferred explicit trigger:

  • $plan-to-issues-csv plan/2026-03-31_10-00-00-login-flow.md

Natural-language triggers:

  • 把这个 plan 转成 issues csv
  • 从 plan 生成可维护的 issues 快照

Input Rules

  1. Accept an optional plan file path.
  2. If no path is provided, use the latest plan/*.md in the current workspace.
  3. Read the plan file first, then read only the minimum referenced files needed to fill gaps.

Output Rules

  1. Always write a uniquely named snapshot under issues/.
  2. Never create or update issues/issues.csv, issues.csv, or any other fixed summary CSV.
  3. Write the file as UTF-8 with BOM for Excel compatibility.
  4. Keep the CSV maintainable: default to one issue row per plan phase unless a phase clearly contains multiple independent workstreams.
  5. Target roughly 5-30 rows.

Fixed Header

Use this exact header order:

id,priority,phase,area,title,git_message,description,acceptance_criteria,test_mcp,review_initial_requirements,review_regression_requirements,dev_state,review_initial_state,review_regression_state,git_state,owner,refs,notes

Row Defaults

  • dev_state: 未开始
  • review_initial_state: 未开始
  • review_regression_state: 未开始
  • git_state: 未提交
  • owner: empty
  • notes: empty
  • refs: must not be empty; use path:line and separate multiple refs with ;

Validation

Before finishing:

  1. Ensure the CSV is parseable.
  2. Ensure every row has the full header width.
  3. Ensure all state columns only use the allowed enum values.
  4. Ensure every row has a non-empty refs value.

Reply Shape

Return only the essentials:

  • Snapshot path
  • Row count
  • Any risks such as Excel/WPS file locks or limited source detail
  • The next recommended command in skill form: $plan-csv-execute <snapshot-path>

If file writes are blocked, return the full CSV in a code block and state the target path plus the UTF-8 BOM requirement.

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.