skills/mine-create-issue/SKILL.md
Use when the user says: 'create an issue', 'file an issue', 'open an issue', 'write an issue', 'new issue for this'. Codebase-aware issue creation — investigates the code to produce well-structured issues with acceptance criteria, affected areas, and enough detail for automated triage.
npx skillsauth add NodeJSmith/Claudefiles mine-create-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.
Codebase-aware issue creation. Dispatches a subagent to investigate the code, draft a structured issue, and create it on GitHub.
To enrich an existing issue, use the issue-refiner agent instead.
$ARGUMENTS — a description of the issue to create. Can be:
/mine-create-issue "add retry logic to the webhook sender"/mine-create-issue "500 error when submitting empty form"If $ARGUMENTS is empty, ask the user: "What do you want to create an issue for?"
Classify the issue type from the description:
| Type | Signals | |------|---------| | bug | "error", "broken", "crash", "fails", "wrong", "500", reproduction context | | feature | "add", "new", "support", "enable", "implement" | | task | "refactor", "rename", "move", "split", "clean up", "remove", "update", "upgrade" | | chore | "deps", "CI", "config", "version bump" |
When signals overlap, prefer the type whose follow-up questions would extract the most useful detail. If genuinely ambiguous, default to task.
Ask only what's missing from the description. Skip questions the user already answered. Keep this to 1-2 questions max. The codebase investigation fills in the technical detail — don't ask the user for file paths or function names.
Bug — what's happening vs what should happen; how to reproduce. Feature — what problem this solves; any constraints or non-goals. Task / Chore — only ask if the scope is ambiguous.
Launch one subagent (model: sonnet, subagent_type: general-purpose):
Create an issue for this codebase.
Type: <classified type> Description: <user's description + any follow-up answers>
Read
${CLAUDE_CONFIG_DIR:-~/.claude}/skills/mine-create-issue/worker.mdfor the complete workflow. Follow every step. Do NOT use the Skill tool — the instructions are in worker.md, not a skill.
The subagent returns the issue URL, or an error message if something blocked it.
Present the result to the user.
development
Use when the user says: "document how X works", "write up how this works", "durable explanation", "explain this for the docs", "document this subsystem". Writes a durable, architectural-altitude explanation that survives code churn.
development
Use when picking up a fresh session after /clear, a stop, or an unanswered AskUserQuestion. Reconstructs the prior session's intent from its transcript tail and surfaces any unresolved decision; user-invoked only — for a hand-written end-of-day handoff use /mine-good-morning instead.
development
Use when the user says: "what did we discuss", "continue where we left off", "remember when", "as I mentioned", "you suggested", "we decided", "search my conversations", "find the conversation where", "what did we work on", or uses implicit signals like past-tense references, possessives without context, or assumptive questions. Direct search over past Claude Code sessions via cass.
tools
Use when the user says: "what context do I have", "relevant history for this task", "what have we done related to this". Also usable proactively when starting work that likely has prior history. Assembles a structured context brief from past session history via cass, scoped to the current task and workspace.