plan-csv-execute
Skill2 starsChanged 5 months agoMITView on GitHub
Execute a single issues CSV snapshot as the unique task boundary and state source, then close the loop through implementation, review, validation, and local git commit without push. Use when the user explicitly mentions `$plan-csv-execute`, says "按 issues csv 执行", "根据 CSV 闭环开发", or wants to replace the deprecated `/prompts:issues_csv_execute` workflow.
In this repository12 other files it gives its agents.
- bug2csvSkill
- bugbatch-prepareSkill
- bugfix-comment-contextSkill
- bugfix-doneSkill
- bugfix-worktreeSkill
- debug-tag-addSkill
- debug-tag-clearSkill
- feature-doneSkill
- feature-prepareSkill
- feature-worktreeSkill
- planSkill
- plan-to-issues-csvSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. About 0 are common, 6 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill as the replacement for the deprecated custom prompt /prompts:issues_csv_execute.
- Distinctive: line 21
Treat the user-supplied CSV as the only state source.
- Distinctive: line 22
Do not create or sync any extra summary CSV files unless the user explicitly asks.
- Distinctive: line 23
Default goal: move every unfinished row to a closed local state.
- Very specific: line 31
Use update_plan for multi-step execution runs.
- Distinctive: line 41
If the CSV does not match, stop and ask the user to regenerate or repair the CSV first.
- Very specific: line 47
Write a short picked_reason: note into the row when selecting it.
- Very specific: line 52
If acceptance_criteria, review requirements, test_mcp, or refs are incomplete, update the CSV first.
- Very specific: line 54
Read refs, gather the minimum code context, and implement only the work inside that row's boundary.
- Distinctive: line 55
Run the most relevant tests or checks you can.
- Very specific: line 56
If full validation is not possible, record all of these in notes:
- Very specific: line 65
Commit code-only changes with a message exactly equal to the row's git_message.
- Very specific: line 66
If the commit succeeds, set git_state=已提交.
- Very specific: line 67
If the commit fails, set git_state back to 未提交 and record blocked:git commit failed <reason> in notes.
- Distinctive: line 72
Stop when all remaining rows are blocked and summarize the blockers plus the smallest next decision the user must make.
≈ “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.
Files
Issues CSV Execute
Use this skill as the replacement for the deprecated custom prompt /prompts:issues_csv_execute.
Invocation
Preferred explicit trigger:
$plan-csv-execute issues/2026-03-31_10-10-00-login-flow.csv
Natural-language triggers:
按这份 issues csv 执行根据 CSV 闭环开发直到提交
Core Rules
- Treat the user-supplied CSV as the only state source.
- Do not create or sync any extra summary CSV files unless the user explicitly asks.
- Default goal: move every unfinished row to a closed local state.
- Each issue must be handled as a full loop:
- implement
- review
- validate
- local git commit
- Never push.
- By default, do not add
issues/*.csv,plan/,*.md, or other process documents to commits. - Use
update_planfor multi-step execution runs.
Required Header
Expect this exact header:
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,notesIf the CSV does not match, stop and ask the user to regenerate or repair the CSV first.
Issue Selection Order
- Finish hanging work first: rows with
git_state=未提交anddev_state=进行中|已完成. - Then prefer unfinished rows by
P0 -> P1 -> P2. - Write a short
picked_reason:note into the row when selecting it.
Per-Issue Workflow
- Re-state the target row:
id,title, acceptance criteria, and main risks. - If
acceptance_criteria, review requirements,test_mcp, orrefsare incomplete, update the CSV first. - Set
dev_state=进行中andreview_initial_state=进行中. - Read
refs, gather the minimum code context, and implement only the work inside that row's boundary. - Run the most relevant tests or checks you can.
- If full validation is not possible, record all of these in
notes:validation_limited:<reason>manual_test:<steps>evidence:<what was verified>risk:<low|medium|high> <why>
- Once the issue is genuinely ready, set:
dev_state=已完成review_initial_state=已完成review_regression_state=已完成when the available regression evidence is sufficient
- Commit code-only changes with a message exactly equal to the row's
git_message. - If the commit succeeds, set
git_state=已提交. - If the commit fails, set
git_stateback to未提交and recordblocked:git commit failed <reason>innotes.
Stop Conditions
- Continue until every row is closed, or
- Stop when all remaining rows are blocked and summarize the blockers plus the smallest next decision the user must make.
Reply Shape
For each completed loop, report:
id/title- key changed files with
path:line - tests or checks actually run
- validation limits, if any
- local commit hash
- remaining blockers or next issue count
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
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.

