Agent skill

File Issue

by Sma1lboy in Sma1lboy/rove

Turn a rough idea, a bug, or a batch of unsolved problems into well-structured GitHub issue(s) and file them with gh, auto-classifying type + labels from the content (recommend, then confirm) and…

MITAuto-check passedAgent Workflows

Install File Issue

skills CLI
$ npx skills add Sma1lboy/rove --skill file-issue -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Sma1lboy/rove file-issue --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Sma1lboy/rove.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/file-issue .claude/skills/file-issue && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
file-issue
GitHub stars
146
Token cost
~2.4k tokens
SKILL.md length
1,050 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Turn a rough idea, a bug, or a batch of unsolved problems into well-structured GitHub issue(s) and file them with gh, auto-classifying type + labels from the content (recommend, then confirm) and…

  • Works in 6 steps: Confirm target repo + available labels → Auto-classify (recommend, then confirm) → Verify every pointer (mandatory) → …
  • The user says file an issue
  • SKILL.md covers Scope boundary (read first), Modes, Hard rules (non-negotiable) and Step 0 — Confirm target repo +…, plus 5 more sections
  • Calls gh and git

What it does

File Issue is an agent skill from Sma1lboy/rove. Turn a rough idea, a bug, or a batch of unsolved problems into well-structured GitHub issue(s) and file them with gh, auto-classifying type + labels from the content (recommend, then confirm) and following Rove's conventions (beginner-friendly framing, concrete file pointers, an acceptance checklist, zero AI/Anthropic attribution). Handles single, batch, and "file the unsolved problems" modes. Use when the user says "file an issue", "open a GitHub issue", "draft a good first issue", "batch these as issues", "上报…

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. It works with GitHub. The repository describes itself as: Rove — the agent multiplexer for your terminal. Run coding agents on parallel tasks with isolated worktrees and persistent sessions. The licence is MIT.

When your agent uses it

  • The user says file an issue
  • Open a GitHub issue
  • Draft a good first issue
  • Batch these as issues

Example prompts

  • “file the unsolved problems”
  • “file an issue”
  • “open a GitHub issue”
  • “/file-issue”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Confirm target repo + available labels
  2. Auto-classify (recommend, then confirm)
  3. Verify every pointer (mandatory)
  4. Draft the body
  5. Confirm, then file
  6. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 8b9f22c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

File Issue loads about 2.4k tokens when it runs. Until then it costs about 189 tokens; SKILL.md has 1,050 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~189
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Sma1lboy/rove at commit 8b9f22c, republished under its MIT licence (© Sma1lboy). 1,050 words, ~2,412 tokens.

Download SKILL.mdSave it as .claude/skills/file-issue/SKILL.md (or your agent's skills folder).
name
file-issue
description
Turn a rough idea, a bug, or a batch of unsolved problems into well-structured GitHub issue(s) and file them with `gh`, auto-classifying type + labels from the content (recommend, then confirm) and following Rove's conventions (beginner-friendly framing, concrete file pointers, an acceptance checklist, zero AI/Anthropic attribution). Handles single, batch, and "file the unsolved problems" modes. Use when the user says "file an issue", "open a GitHub issue", "draft a good first issue", "batch these as issues", "上报 issue", "提个 issue", "报个 bug", "把没解决的发上去", or wants to hand low-priority tasks to outside contributors. Distinct from the daemon-owned internal issue store (`rove api issue-*`); this skill is for outward-facing GitHub issues.
metadata.internal
true

File a GitHub issue

Turn a rough idea, bug report, or low-priority task into a well-structured GitHub issue and file it with gh. The output should be something an outside contributor can pick up cold — accurate file pointers, clear scope, explicit acceptance — not a one-line stub.

Scope boundary (read first)

Rove tracks its own work in the daemon-owned issue store (rove api issue-*, the web Issues page) — see docs/WORK-TRACKING.md. That is the default for internal backlog.

This skill is for outward-facing GitHub issues — work you intend to hand to external contributors (especially good first issues), or a public bug report. If the user just wants to jot down internal backlog, prefer the daemon store and say so. If they explicitly want a GitHub issue, proceed here.

Modes

The skill handles three shapes of input — detect which from the user's ask:

  • Single — one idea / bug → one issue. Draft it, auto-classify (Step 1), confirm, file. The lightest path; fine to file directly once the draft + labels are shown.
  • Batch — a list of ideas / a backlog dump / "file these N as issues" → many issues. Draft all, classify each, present the whole set as a table (title + proposed labels) for one confirmation, then file them in a loop and report URLs together.
  • From unsolved problems — the user points at problems that came up but weren't fixed this session ("发没解决的上去") — e.g. a known bug you hit, a deferred follow-up, a TODO you found. Convert each into an issue: capture the symptom/repro while it's fresh, mark it bug or enhancement, and note in the body that it's filed-not-fixed (no implied owner). Then batch-confirm and file as above.

Pick the mode, then follow the per-issue steps below for each issue.

Hard rules (non-negotiable)

  • Filing is an outward-facing publish. Show the draft(s) and labels before gh issue create — never create silently. A batch needs one explicit confirmation; a single obvious issue can be filed right after you show it. Editing an already-filed issue is fine without re-asking.
  • No AI / Anthropic / Claude / Codex attribution anywhere in the title, body, or comments (per CLAUDE.md). No "Generated with…" footers.
  • Never invent file paths, line numbers, flags, or function names. Every pointer in the body must be verified against the current tree (see Step 2). A wrong pointer costs a contributor 30–50% of their session reconciling a false premise.
  • Default language: English for issue titles and bodies (the repo's contributor language), even when the conversation is in Chinese. Narrate to the user in whatever language they're using. If the user asks for another language, follow that.
  • One concern per issue. If an idea bundles several independent tasks, split it into several issues (e.g. "add a theme" is one issue per theme).

Step 0 — Confirm target repo + available labels

bash
git remote -v                                   # confirm origin is the intended repo
gh label list --limit 60                         # use ONLY labels that already exist

Rove's relevant labels: good first issue, enhancement, bug, documentation, help wanted, question. Do not invent labels — if a needed label is missing, surface it and let the user create it (gh label create), don't guess a substitute.

Show full SKILL.md (557 more words)Show less

Step 1 — Auto-classify (recommend, then confirm)

Derive the type + labels from the issue's content automatically — don't ask the user to pick from scratch. Read the idea, match it against the repo's existing labels (Step 0), and propose a classification; the user confirms or overrides at the Step 4 gate (for a batch, one confirmation covers the whole table).

How to classify from content:

  • bug — words like "broken / throws / crashes / regression / doesn't work", or a repro of wrong behavior → bug.
  • enhancement — "add / support / it would be nice / feature" → enhancement.
  • documentation — only docs/README/comments change → documentation.
  • good first issue — additionally apply when the task is self-contained, low-risk, and a meaningful mini-project (see the shape rubric below). Usually paired with enhancement.
  • help wanted — maintainer wants outside help but it's not necessarily beginner-safe.

Only emit labels that exist in the repo (Step 0). If content suggests a label the repo lacks, surface it rather than silently dropping or inventing one. When classification is genuinely ambiguous, state your best guess + the runner-up so the confirm step is a quick yes/no, not an open question.

The issue's shape also drives the body template (Step 3):

  • good first issue — self-contained, low-risk, meaningful (a mini-project a contributor can own end-to-end), not a micro-cleanup. Good signals: greenfield feature with no existing infra (e.g. i18n, shell completions), a self-contained new subcommand (rove doctor), or a repeatable visual contribution (a new theme). Anti-signal: "add a unit test for X" / "extract a constant" — too small to be worth an external contributor's onboarding cost; the user has rejected these. Aim for tasks that touch 1–3 files but deliver a complete, satisfying chunk of value.
  • bug — reproducible defect. Body leads with repro steps + expected vs actual.
  • enhancement — a feature/improvement for the maintainers, not necessarily beginner-friendly.

Most low-priority hand-off tasks are good first issue + enhancement together.

Step 2 — Verify every pointer (mandatory)

Before writing the body, confirm each claim against the tree. Cheap checks that prevent filing fiction:

bash
# file exists + size/shape is what you think
ls -la packages/rove/src/<path>
# the function/string/registry you're pointing at really lives there
grep -rn "BUNDLED_THEMES" packages/rove/src/tui/context/theme/
# the thing you claim is MISSING really is absent (greenfield framing)
find packages -iname '*completion*' | grep -v node_modules    # empty => "no completions exist"

If you spawned an Explore agent to find candidates, re-verify its file paths yourself — exploration output can carry typo'd or doubled paths (e.g. packages/rove/packages/rove/...). Never paste an unverified path into an issue.

For greenfield framing ("there is no X today"), prove the absence with a find/grep that comes back empty — that sentence is load-bearing for a contributor.

Step 3 — Draft the body

Use this template for a good first issue / enhancement (trim sections that don't apply):

markdown
## Background
<1–3 sentences: what exists today, why this matters, what's missing. State greenfield
absence explicitly if true: "the repo has no X infrastructure at all.">

## Why it's beginner-friendly      ← only for good first issue
- <what knowledge is NOT required — e.g. "does not touch daemon/engine/orchestrator">
- <why it's safely incremental / splittable>

## Scope
1. <concrete step with the exact file path to add/edit>
2. <next step, with the registry/wiring point named>
3. <docs/README update if user-facing>

## Important notes        ← constraints that would otherwise trip a newcomer
- <e.g. "engine-owned copy is not translated — comes from AIEngine.identity">
- <e.g. "do not change DEFAULT_THEME = 'claude'">

## Acceptance
- <observable pass condition>
- <exit-code / test / screenshot expectation>

For a bug, lead instead with:

markdown
## Repro
1. <steps>

## Expected vs actual
- Expected: …
- Actual: …

## Environment / pointers
- <version, OS, relevant file:line>

Style: terse, concrete, second-person imperative for scope steps. Reference code as file_path:line so it's clickable. Link Rove docs with repo-relative paths (docs/ARCHITECTURE.md).

Step 4 — Confirm, then file

Show the user the drafted title(s) + body(ies) and the labels you'll apply. For a single obvious issue you may file directly; for a batch, confirm the set first (an AskUserQuestion with "file all / show full drafts / pick a subset" works well).

File with a heredoc to keep Markdown intact:

bash
gh issue create \
  --label "good first issue" --label "enhancement" \
  --title "feat: <concise imperative title>" \
  --body "$(cat <<'EOF'
<body from Step 3>
EOF
)"

gh issue create prints the new issue URL — collect them and report back as a table (number, title, URL). To revise after filing, use gh issue edit <n> --title … --body … (same heredoc pattern); editing needs no re-confirmation.

Step 5 — Report

Summarize what was filed (table of #/title/URL) and offer obvious follow-ups only if they have a concrete hook: assign a milestone, split a multi-part issue, or add a few more candidates at the same scale. Don't over-offer.

© Sma1lboy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/file-issue of Sma1lboy/rove.

Open the folder on GitHubat commit 8b9f22c

Compare with similar skills

File Issue next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

File Issue compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
File Issue this skillSma1lboy/rove146—~2.4kAutomated safety check: PassMIT
Diagnosing Superpowers Sessionsobra/superpowers296k3 repos~1.7kAutomated safety check: PassMIT
Auto Skill Buildertradecatlabs/vibe-coding-cn17k1 repos~2.4kAutomated safety check: PassMIT
Agentic Workflow Designerdotnet/Open-XML-SDK4.6k2 repos~3.5kAutomated safety check: PassMIT
Skill Seekers Builderyusufkaraaslan/Skill_Seekers15k—~760Automated safety check: PassMIT
Repomix Codebase Packeryamadashy/repomix29k—~1.3kAutomated safety check: NotesMIT

Similar skills

  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    296k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • Auto Skill Builder

    tradecatlabs/vibe-coding-cn

    Meta-skill that turns docs, APIs, code or specs into a reusable skill with references and a quality gate, and refactors skills that are unclear or misfire.

    17k GitHub starsUsed in 1 repo~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Agentic Workflow Designer

    dotnet/Open-XML-SDK

    Official

    Interviews you one question at a time about goal, trigger, permissions and data needs, then drafts a single agentic workflow markdown file.

    4.6k GitHub starsUsed in 2 repos~3.5k tokens
    Agent WorkflowsAuto-check passed
  • Skill Seekers Builder

    yusufkaraaslan/Skill_Seekers

    Detects the type of a knowledge source and uses the Skill Seekers MCP tools to turn docs, repos, PDFs or videos into packaged AI skills.

    15k GitHub stars~760 tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Repomix Codebase Packer

    yamadashy/repomix

    Packs a local directory or remote GitHub repository into one AI-friendly file with Repomix, then searches it to explore structure, find patterns and count tokens.

    29k GitHub stars~1.3k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check: notes
  • DBS Skill Maker

    dontbesilent2025/dbskill

    Turns a problem you keep running into into a single installable, tested skill, and prepares a GitHub repository only when you ask to share it.

    11k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from Sma1lboy/rove

All 13 skills in this repo
  • Image Gen

    Sma1lboy/rove

    Generate a single image from a text prompt using the MiniMax image generation API.

    146 GitHub starsUsed in 1 repo~927 tokens
    Auto-check passed
  • Unslop

    Sma1lboy/rove

    Strip AI writing tells from Rove's user-facing prose — README, the docs/ pages that sync to docs.rove.run, landing copy, and release notes.

    146 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • Hyperframes Design

    Sma1lboy/rove

    Non-animation creative direction for HyperFrames videos. An agent skill from Sma1lboy/rove.

    146 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Changelog Generator

    Sma1lboy/rove

    Draft Rove release notes as Changesets. An agent skill from Sma1lboy/rove.

    146 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Rove

    Sma1lboy/rove

    A skill your agent uses when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell.

    146 GitHub stars~8.8k tokensUpdated yesterday
    Auto-check passed
  • Why

    Sma1lboy/rove

    A skill your agent uses for 'why does X work this way', 'why we picked Y', '为什么这么设计', design rationale, regressions, or where a magic number came from.

    146 GitHub stars~5.6k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about File Issue

What does File Issue do?

Turn a rough idea, a bug, or a batch of unsolved problems into well-structured GitHub issue(s) and file them with gh, auto-classifying type + labels from the content (recommend, then confirm) and…. File Issue is an agent skill from Sma1lboy/rove. Turn a rough idea, a bug, or a batch of unsolved problems into well-structured GitHub issue(s) and file them with gh, auto-classifying type + labels from the content (recommend, then confirm) and following Rove's conventions (beginner-friendly framing, concrete file pointers, an acceptance checklist, zero AI/Anthropic attribution).

When should I use File Issue?

File Issue fits situations like: the user says file an issue; open a GitHub issue; draft a good first issue; batch these as issues.

How do I install File Issue in Claude Code?

Run `npx skills add Sma1lboy/rove --skill file-issue -a claude-code`. Or copy the skill folder (.claude/skills/file-issue in Sma1lboy/rove) into .claude/skills/file-issue in your project. Claude Code loads it when a task matches its description.

How do I install File Issue in Codex?

Run `npx skills add Sma1lboy/rove --skill file-issue -a codex`. Or copy the skill folder (.claude/skills/file-issue in Sma1lboy/rove) into .agents/skills/file-issue in your project. Codex loads it when a task matches its description.

Can I use File Issue in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Sma1lboy/rove --skill file-issue -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/file-issue, .gemini/skills/file-issue, .github/skills/file-issue and .opencode/skills/file-issue in your project.

What does File Issue need to run?

Going by SKILL.md and its folder, File Issue needs the command-line tools its instructions call (gh and git).

Does File Issue access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is File Issue safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does File Issue use?

File Issue is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does File Issue use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to File Issue?

Skills that share tags, products or a category with File Issue: Diagnosing Superpowers Sessions (obra/superpowers, 296k stars), Auto Skill Builder (tradecatlabs/vibe-coding-cn, 17k stars), Agentic Workflow Designer (dotnet/Open-XML-SDK, 4.6k stars) and Skill Seekers Builder (yusufkaraaslan/Skill_Seekers, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains File Issue?

Sma1lboy (a GitHub user) maintains it in Sma1lboy/rove, which has 146 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 7, 2026.

Source: Sma1lboy/rove on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.