一键导入
issue-plan
Read a GitHub issue, develop a resolution plan via sequential thinking, rate difficulty/complexity/priority, label low-priority when warranted.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Read a GitHub issue, develop a resolution plan via sequential thinking, rate difficulty/complexity/priority, label low-priority when warranted.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Audit corpus and highlight tests for tests that pass for the wrong reason — designed to pass rather than designed to catch regressions.
Fix multiple GitHub issues on an integration branch. Issues touching different areas (grammar, scanner, queries, bindings, tests) run in parallel worktrees; issues sharing an area or affecting cross-binding code run sequentially. Each goes through fix, simplify, review, and remediation before merging. Use when asked to fix several issues at once.
Complete workflow for fixing GitHub issues — investigation, implementation, review, testing, documentation.
Fetch open GitHub issues and produce a read-only triage report with quick wins and recommended groupings.
Review project activity (issues, commits, changelog) and draft entries for docs/lessons_learned.md.
Audit grammar / query / binding changes for correctness, performance, and quality. Use when asked to review changes, diffs, or pull requests.
| name | issue-plan |
| description | Read a GitHub issue, develop a resolution plan via sequential thinking, rate difficulty/complexity/priority, label low-priority when warranted. |
Read a GitHub issue, build a confirmed resolution plan via sequential
thinking, append a ratings table to the issue body, apply the low-priority
label when warranted.
Argument: $ARGUMENTS — a GitHub issue number (e.g. 42 or #42).
gh issue view "$ISSUE_NUMBER" --json number,title,body,labels
Record number, title, body, current labels. Read the full body — do not rely on the title alone.
main. If so: comment with the
resolving commit/PR, apply resolved label (create with
gh label create resolved --description "Already resolved" --color 0E8A16
if missing), stop. Do NOT close — leave that for a human.grammar.js — grammar rulesrc/scanner.c — external scannerqueries/groovy/*.scm — highlights / folds / indents / injectionsbindings/<lang>/ — language bindingtest/corpus/ or test/highlight/ — testsSPECIFICATION.md — design document (rare; only when the issue
calls out a spec inconsistency or missing decision)SPECIFICATION.md section before proposing a fix that changes
grammar shape.bindings/rust/lib.rs
re-exports), test churn expected.Use sequential-thinking:sequentialthinking. The thinking MUST:
thoughtNumber: 1, totalThoughts ~5–8, nextThoughtNeeded: true.dekobon/big-code-analysis, editor plugins).nextThoughtNeeded: false and a final summary.Distill into a clean numbered resolution plan.
nvim-treesitter configs,
dekobon/big-code-analysis metric impls) must update.Append — do not replace.
---
## Resolution Plan
<!-- Generated by issue-plan skill -->
1. Step one...
2. Step two...
3. ...
## Assessment
| Dimension | Rating |
|------------|--------|
| Difficulty | Low / Medium / High |
| Complexity | Low / Medium / High |
| Priority | Low / Medium / High |
Use --body-file:
cat > /tmp/issue-body.md <<'ISSUE_EOF'
... full updated body ...
ISSUE_EOF
gh issue edit "$ISSUE_NUMBER" --body-file /tmp/issue-body.md
gh issue comment "$ISSUE_NUMBER" --body "Added resolution plan and assessment ratings."
If either condition: Priority Low; or both Difficulty and Complexity Low AND Priority not High:
ensure_label() {
local name="$1" color="$2" desc="$3"
if ! gh label list --limit 200 --json name --jq '.[].name' | grep -qx "$name"; then
gh label create "$name" --color "$color" --description "$desc"
fi
}
ensure_label low-priority "fef2c0" "Low priority issue"
gh issue edit "$ISSUE_NUMBER" --add-label "low-priority"
Mention in the Step 5 comment instead of posting separately.
--body-file for any non-trivial edit.