npx skillsauth add laststance/skills issueInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
When running this skill in Codex, translate Claude Code-only primitives before acting: AskUserQuestion -> chat/request_user_input, TodoWrite -> update_plan, Task/TaskCreate/TeamCreate/SendMessage -> spawn_agent/send_input/wait_agent when available and allowed, and EnterPlanMode/ExitPlanMode -> a concise chat plan plus explicit approval.
Resolve Read/Write/Edit/Bash/WebSearch/WebFetch to Codex file/shell/web tools, and map ~/.claude/... paths to ~/.agents/... or ~/.codex/... unless the task explicitly targets Claude Code.
When running this skill in Cursor Agent, translate Claude Code-only primitives before acting: AskUserQuestion -> AskQuestion; TodoWrite -> Cursor TodoWrite or an equivalent checklist; Task/TaskCreate/TeamCreate/SendMessage/multi-agent flows -> Cursor Task (subagents), parallel Tasks, or run_in_background when allowed (TeamCreate/SendMessage may have no exact match); EnterPlanMode/ExitPlanMode -> Plan mode (SwitchMode / CreatePlan) plus explicit user approval.
Resolve Read/Write/Edit/StrReplace/Bash/web/search/MCP via Cursor Composer or Agent equivalents. MCP names written as mcp__server__tool typically map to call_mcp_tool with configured server identifiers. Map ~/.claude/... to ~/.cursor/skills/, .cursor/skills/, and .cursor/rules/ unless the task explicitly targets Claude Code.
Create issues or list open ones. Auto-detects the project's issue tracker.
| Input | Action |
|-------|--------|
| /issue list | List open issues |
| /issue list --assignee me | List my open issues |
| /issue list --label <label> | Filter by label |
| /issue <any other text> | Create issue with that text as title/description |
Determine which tracker this project uses. Check in order:
mcp__claude_ai_Linear__list_teams is available, check if the project has a Linear teamgh CLI availableOnce detected, remember the tracker for the rest of the conversation.
Classify the user's input into ONE of:
| Type | Signals | Body policy | |------|---------|-------------| | Feature request | "add", "want", "wish", "could we", "〜したい", "〜が欲しい", new capability | Strict: non-engineer voice only (see 2A.2) | | Bug | "broken", "doesn't work", "error", "regression", "crash", "〜が動かない" | Reproduction-focused (see 2A.3) | | Task | refactor, chore, internal work, infra, "clean up", "migrate" | Flexible; technical context allowed |
If ambiguous, default to Feature request (safer — stays user-facing) or ask the user.
Apply the matching label automatically when the tracker supports it (enhancement, bug, task).
Feature requests describe WHAT the user wants and WHY — never HOW.
Technical design is deferred to the engineer who picks up the issue (they run /plan-eng-review or similar).
MUST NOT include (reject and rewrite if present in user input):
MUST include:
Template (embed verbatim in the issue body):
## Problem / Motivation
<1–2 sentences, user-facing. No tech terms.>
## Acceptance Criteria
- [ ] <observable behavior 1>
- [ ] <observable behavior 2>
- [ ] <observable behavior 3>
## Examples (optional)
<user-story-style scenarios, plain language>
---
_Technical design & implementation plan will be produced at pickup time via `/plan-eng-review`._
Rewrite rule: if the user's raw input contains technical terms, translate them into user-facing outcomes before writing the body. E.g., "add a Redis cache for session lookups" → "Problem: login feels slow on repeat visits. AC: returning users see their home screen within 1 second."
See references/feature-request-policy.md for more examples and edge cases.
gh issue create --title "<title>" --body "<body>" --label "<type-label>"
Use mcp__claude_ai_Linear__save_issue:
title: user-facing phrasing for feature requestsdescription: the templated body from 2A.2 / 2A.3team: auto-detect from mcp__claude_ai_Linear__list_teams (use first team, or ask if multiple)labels: apply Feature / Bug / Task based on classificationLIN-123)gh issue list --state open --limit 20 --json number,title,url,body,labels
Display as table:
| # | Title | Labels | URL |
|---|-------|--------|-----|
Include a 1-line summary (first 80 chars of body) for each.
Use mcp__claude_ai_Linear__list_issues with state: "started" or unfiltered for all active.
Pass --assignee and --label filters if provided.
Display: identifier, title, state, URL.
Issue created: <URL or identifier>
Title: <title>
Render a markdown table with columns: #/ID, Title, Summary, URL
Keep summary to ~80 chars. Truncate with ... if longer.
testing
Cited research briefs
development
Daily coding habit prompts JP
development
React core deep-dive JP
data-ai
Copy last agent reply