| name | file-issue |
| description | File a new GitHub issue with the correct priority and area labels applied up front. Use whenever an agent needs to capture a new unit of work — follow-ups from a merged PR, TODOs discovered while coding, or manually-requested issues. Invoked as `/file-issue`. |
file-issue
Files a single GitHub issue against dburkart/auto-engineer with priority and classification labels applied on creation. Keeps the backlog triaged in one step instead of leaving un-labeled issues that pollute the auto-engineer candidate set.
Read docs/agent-playbooks/prioritization.md before running — the label taxonomy, priority rules, and triage policy all live there. This skill is the mechanical front-end for that policy.
Label taxonomy
Priority labels: priority:P0 (critical — blocks core functionality), priority:P1 (high — required for next milestone), priority:P2 (medium — polish and hardening), priority:P3 (low — nice-to-have or future work). Type labels: bug (something isn't working), enhancement (new feature or improvement). Every issue must have exactly one priority:* label and at least one type/area label.
When to invoke
- A merged PR surfaced out-of-scope follow-up work that needs its own issue (auto-engineer step 8, or a human reviewer deferring a nit).
- A
TODO/FIXME was introduced that deserves tracking.
- The user says "file an issue for …" or invokes
/file-issue directly.
Do not use this skill to edit an existing issue — use mcp__github__update_issue for that.
Inputs
Either accept them as free-form arguments after /file-issue, or infer from the invoking context:
- title — imperative phrase, ≤ 72 chars, no emoji.
- motivation — 1–3 sentences on why this matters and what it unblocks.
- work — bulleted sub-tasks, concrete enough to act on cold in a week (file paths, type names, function signatures when known).
- context — relevant commit SHAs, file paths, existing issue numbers, or the PR that surfaced the follow-up.
If any of those are missing and cannot be reasonably inferred, skip the issue silently — do not ask the user. This skill may be called from auto-engineer or other agents where user interaction is not available; asking would block the loop.
Cycle
1. Dedupe
Search open issues for overlap before filing:
mcp__github__search_issues(
query="repo:dburkart/auto-engineer is:open <keywords from title>",
)
If a strong duplicate exists, do not file. Instead, add a comment on the existing issue linking the new context (via mcp__github__add_issue_comment) and return its URL.
2. Decide labels
Follow the triage rules above (and in docs/agent-playbooks/prioritization.md):
- Assign exactly one
priority:P0 / P1 / P2 / P3 label.
- Assign any area, type, or classification labels appropriate to the work.
- Never invent a new label from this skill. If the taxonomy is missing a dimension, stop and update the label set in a separate step first.
3. Compose the body
Use the canonical template:
## Motivation
<1-3 sentences>
## Work
- [ ] <concrete sub-task 1>
- [ ] <concrete sub-task 2>
## Context
<PR/commit/issue references and file paths>
4. File
mcp__github__create_issue(
owner="dburkart",
repo="auto-engineer",
title="<title>",
body="<templated body>",
labels=["priority:PN", ...],
)
Report the new issue number and URL back to the caller.
5. Record
If the issue was filed from auto-engineer's follow-up capture pass (step 8), include it in the "captured follow-ups" summary that auto-engineer emits before re-entering its loop.
Never
- File an issue without at least one
priority:* label.
- File an issue that duplicates an open one.
- Invent new label values in-flight.
- File speculative "nice-to-have" items with no concrete motivation — they clutter the backlog and degrade the auto-engineer candidate set.
- Close, reassign, or relabel issues other than the one being filed.
