Agent skill

Draft Issue To External Repository

by dyoshikawa in dyoshikawa/rulesync

Draft a GitHub issue targeting a third-party repository (outside this project's owner).

MITAuto-check passedDevelopment

Install Draft Issue To External Repository

skills CLI
$ npx skills add dyoshikawa/rulesync --skill draft-issue-to-external-repository -a claude-code

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

GitHub CLI
$ gh skill install dyoshikawa/rulesync draft-issue-to-external-repository --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/dyoshikawa/rulesync.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.rulesync/skills/draft-issue-to-external-repository .claude/skills/draft-issue-to-external-repository && 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
draft-issue-to-external-repository
GitHub stars
1.5k
Token cost
~1.9k tokens
SKILL.md length
1,029 words
Files
1
Skills in repo
40
Repo updated
First seen
Licence
MIT

At a glance

Draft a GitHub issue targeting a third-party repository (outside this project's owner).

  • Works in 8 steps: Inspect the Target Repository → Research the Topic → Ground the Proposal in This Repo → …
  • Development work in your project
  • SKILL.md covers Step 1: Inspect the Target…, Step 2: Research the Topic, Step 3: Ground the Proposal in… and Step 4: Align with the User on…, plus 4 more sections
  • Calls gh and curl; reaches github.com and api.npmjs.org

What it does

Draft Issue To External Repository is an agent skill from dyoshikawa/rulesync. Draft a GitHub issue targeting a third-party repository (outside this project's owner). Researches the target repo's conventions and the topic in depth, iterates with the user on scope and tone, and produces a final body saved to tmp/external-repository-issues/.md for the user to post manually when gh auth lacks permission on the target.

Its SKILL.md is about 1.9k 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 Development. It works with GitHub and Model Context Protocol. The repository describes itself as: A Utility CLI for AI Coding Agents. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “s owner). Researches the target repo”
  • “/draft-issue-to-external-repository”

Workflow steps

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

  1. Inspect the Target Repository
  2. Research the Topic
  3. Ground the Proposal in This Repo
  4. Align with the User on Scope and Tone
  5. Draft in the Conversation Language First
  6. Translate the Approved Draft to English
  7. Try Posting, Fall Back to Disk
  8. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 625bf98. 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
    • curl

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com
    • api.npmjs.org

    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

Draft Issue To External Repository loads about 1.9k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 1,029 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 dyoshikawa/rulesync at commit 625bf98, republished under its MIT licence (© dyoshikawa). 1,029 words, ~1,936 tokens.

Download SKILL.mdSave it as .claude/skills/draft-issue-to-external-repository/SKILL.md (or your agent's skills folder).
name
draft-issue-to-external-repository
description
Draft a GitHub issue targeting a third-party repository (outside this project's owner). Researches the target repo's conventions and the topic in depth, iterates with the user on scope and tone, and produces a final body saved to tmp/external-repository-issues/*.md for the user to post manually when gh auth lacks permission on the target.
targets
*

arguments = the user's request

Parse arguments as:

  • target_repo: the target repository in owner/repo form (or a URL)
  • intent: the rough idea the user wants to propose (may be vague — this skill is designed to sharpen it)

If target_repo is not provided, ask the user which repository to file against. If intent is not provided, ask the user what they want to propose.

This skill is for proposing a change to a repository we do not own. When the target is a repo under the user's own owner, prefer create-issue or create-issue-with-websearch instead.

Step 1: Inspect the Target Repository

Before drafting anything, understand the target repo's conventions. Run in parallel:

  • gh repo view <owner/repo> --json description,url,defaultBranchRef,primaryLanguage,latestRelease
  • gh issue list --repo <owner/repo> --limit 20 --state all --json number,title,labels,state — read recent titles to learn the house style (prefix tags like [FEATURE], casing, length).
  • gh api repos/<owner/repo>/contents/.github/ISSUE_TEMPLATE — list templates. If a feature-request template exists, fetch it with gh api or a raw URL and note the required sections plus any auto-applied title prefix / labels.
  • gh label list --repo <owner/repo> — note which labels exist (do not invent labels later).
  • Optionally fetch CONTRIBUTING.md / CODE_OF_CONDUCT.md if present to catch any issue-filing rules.

If no issue template exists, plan to use a light structure (Problem / Proposal / Alternatives / Additional context) that mirrors common feature-request templates.

Step 2: Research the Topic

Ground the proposal in primary sources before writing anything opinionated.

  • Use WebSearch / WebFetch for official docs of the target project, release notes, and any pre-existing discussion (open/closed issues, PRs, RFCs).
  • Use the deepwiki MCP (mcp__deepwiki__ask_question, mcp__deepwiki__read_wiki_contents) against the target repo for structural questions — it is often faster and more definitive than grepping manually.
  • For deep or multi-angle investigation, delegate to a subagent (Agent with subagent_type: "general-purpose") with a self-contained prompt. Ask for a definitive answer, not a hedged summary.
  • Cross-check any claim the draft will rely on against at least one primary source. If two sources disagree, note the disagreement in the draft rather than silently picking a side.

Step 3: Ground the Proposal in This Repo

If the proposal implies work on our side (e.g., a new target, a new integrator, a new feature), inspect this repository's state so the draft is accurate:

  • Which features / directories / schemas exist here and will need to map to the target's concepts?
  • Prefer targeted symbol and search tools over reading whole files.
  • If the proposal includes popularity / adoption claims, verify the numbers before writing them down. For npm downloads: curl -s "https://api.npmjs.org/downloads/point/<start>:<end>/<package>". For stars/forks: gh repo view <owner/repo> --json stargazerCount,forkCount.

Step 4: Align with the User on Scope and Tone

Before drafting the full body, surface the design choices that most shape the final issue. Ask the user about:

  • Temperature: "Please consider this" (proposal + offer) vs. "Please implement this" (request). This changes how forceful the body reads and whether to include an explicit implementation offer.
  • Scope boundaries: minimum-viable vs. full surface. A small, shippable proposal is usually easier to get accepted; follow-ups can be called out explicitly.
  • Hard non-goals: things deliberately out of scope. Name them so the maintainer doesn't have to ask.
  • Any claims that need numbers: adoption stats, benchmarks, etc.

Iterate briefly — one or two rounds — until the scope is pinned down. Do not start drafting the full body while these are still open.

Show full SKILL.md (485 more words)Show less

Step 5: Draft in the Conversation Language First

Draft the body in the conversation language (typically Japanese for this user) so the user can review and correct efficiently. Keep the structure that the target repo's template dictates — if the template uses bold-heading prompts like **Describe the solution you'd like**, match that exactly. If there is no template, fall back to plain conversational paragraphs.

Style guidance:

  • Write like a human teammate proposing to peers in another team, not like an automated bot.
  • Lead with the problem and the "why", not with the solution.
  • Use small, tight mapping tables when concepts map across systems — tables are much easier to read than a wall of bullets for that case.
  • State open questions as concrete decisions the maintainer needs to make, each with the options considered.
  • If an implementation offer is appropriate (confirmed in Step 4), close with a short, concrete commitment ("happy to put up the PR — new integrator, target profile, and tests against a sample package").
  • Avoid filler like "Thanks for maintaining this great project!" unless genuinely warranted.

Iterate with the user on the draft until they approve it.

Step 6: Translate the Approved Draft to English

All issue content (title, body, labels) must be in English regardless of the conversation language. Translate faithfully — do not "improve" content during translation. Preserve tables, code fences, and links verbatim.

Title conventions:

  • If the target template auto-applies a title prefix (e.g., [FEATURE] ), keep it.
  • Otherwise pick a short, imperative title (under 70 characters) that names the change.

Step 7: Try Posting, Fall Back to Disk

Attempt to create the issue directly:

bash
gh issue create --repo <owner/repo> \
  --title "<title>" \
  --body-file <path to english body>

If the template auto-applies labels, do not pass --label (the template wins). If no template auto-applies labels, pass only labels that exist in the repo's label vocabulary gathered in Step 1.

If posting fails (common cause: fine-grained PATs cannot create issues on repos outside the user's owner — Resource not accessible by personal access token), do not retry blindly. Instead:

  1. Save the final English body to tmp/external-repository-issues/<owner>-<repo>-<slug>.md, where <slug> is a short kebab-case summary of the proposal.
  2. At the top of that file include a metadata block (before the issue body) with:
    • # <suggested issue title>
    • Target repo
    • Template path used (if any)
    • Suggested title
    • Auto-applied labels (from template frontmatter, if any)
    • A pre-filled new-issue URL of the form https://github.com/<owner>/<repo>/issues/new?template=<template-filename> when a template exists, otherwise https://github.com/<owner>/<repo>/issues/new
    • A --- horizontal rule separating the metadata from the issue body
  3. Report the path to the user and explain how to post (web UI paste, or re-authenticate gh with gh auth login --web and let this skill retry).

Step 8: Report

Output:

  • If posted: the issue URL, title, and any labels applied.
  • If saved to disk: the absolute path of the saved file, the suggested title, and the pre-filled new-issue URL.
  • A one-line summary of the proposal's scope (what's in, what's out).
  • Any open questions the draft left for the maintainer to decide.

© dyoshikawa, 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 .rulesync/skills/draft-issue-to-external-repository of dyoshikawa/rulesync.

Open the folder on GitHubat commit 625bf98

Compare with similar skills

Draft Issue To External Repository 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.

Draft Issue To External Repository compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Draft Issue To External Repository this skilldyoshikawa/rulesync1.5k—~1.9kAutomated safety check: PassMIT
GitDiagram Repository Overviewahmedkhaleel2004/gitdiagram18k—~427Automated safety check: PassMIT
Library Documentation Seekerwithkynam/vibecode-pro-max-kit1.1k1 repos~1kAutomated safety check: NotesMIT
Herdr Issue Triageherdrdev/herdr43k—~517Automated safety check: PassApache-2.0
Plane Release Notes Generatormakeplane/plane61k—~2.5kAutomated safety check: PassAGPL-3.0
Deepseek Automationzhu1090093659/deepseek-pp1.9k—~2.1kAutomated safety check: NotesApache-2.0

Similar skills

  • GitDiagram Repository Overview

    ahmedkhaleel2004/gitdiagram

    Explains the architecture of a public GitHub repository through GitDiagram: how the code is organized, the main components with paths, and a Mermaid diagram.

    18k GitHub stars~427 tokensUpdated today
    DevelopmentAuto-check passed
  • Library Documentation Seeker

    withkynam/vibecode-pro-max-kit

    Looks up library and framework documentation through Context7 first, with bundled Node scripts as a fallback that fetch and analyze llms.txt files.

    1.1k GitHub starsUsed in 1 repo~1k tokens
    DevelopmentAuto-check: notes
  • Herdr Issue Triage

    herdrdev/herdr

    Triages open herdr GitHub issues into a short decision-first Markdown table with a priority light, recommendation, age, reactions and a reason for each.

    43k GitHub stars~517 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Builds categorized release notes for a Plane release pull request from its commits and writes them into the PR description, for both the plane-cloud and plane-ee repos.

    61k GitHub stars~2.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Deepseek Automation

    zhu1090093659/deepseek-pp

    A skill your agent uses when implementing, resuming, reviewing, or verifying the DeepSeek++ Codex-style automation feature in this repository.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • Issue Triage

    mono/SkiaSharp

    Triage a SkiaSharp GitHub issue or PR into structured JSON with classification (type, area, platform, severity), suggested response, automatable actions, and companion Markdown/HTML reports.

    5.6k GitHub stars~3.4k tokensUpdated today
    DevelopmentAuto-check passed

More from dyoshikawa/rulesync

All 40 skills in this repo
  • Rulesync Feature Research

    dyoshikawa/rulesync

    Maps rulesync feature implementations to upstream coding-agent documentation.

    1.5k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Babysit Dependabot PR

    dyoshikawa/rulesync

    Babysit a Dependabot dependency-bump PR all the way to merge: verify the author is the genuine Dependabot bot, diagnose and resolve any CI failure (excluding or fixing a breaking bump when needed)…

    1.5k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Commit Push PR

    dyoshikawa/rulesync

    Commit current changes, push to remote, and create or update a pull request.

    1.5k GitHub stars~458 tokensUpdated yesterday
    Auto-check passed
  • Git Worktree Runner

    dyoshikawa/rulesync

    Manages git worktrees using git-worktree-runner (gtr). An agent skill from dyoshikawa/rulesync.

    1.5k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check: notes
  • Goal PR

    dyoshikawa/rulesync

    Drive a pull request to a clean state and merge it: run the review-pr skill, fix every mid-or-above finding, and repeat until no mid-or-above findings remain, then merge.

    1.5k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Goal Release

    dyoshikawa/rulesync

    Cut a release end to end: use the draft-release skill to open the release PR and draft GitHub release, wait for CI to turn green, run the merge-pr skill to merge the release PR, then update the…

    1.5k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Draft Issue To External Repository

What does Draft Issue To External Repository do?

Draft a GitHub issue targeting a third-party repository (outside this project's owner). Draft Issue To External Repository is an agent skill from dyoshikawa/rulesync. Draft a GitHub issue targeting a third-party repository (outside this project's owner).

When should I use Draft Issue To External Repository?

Draft Issue To External Repository fits situations like: development work in your project.

How do I install Draft Issue To External Repository in Claude Code?

Run `npx skills add dyoshikawa/rulesync --skill draft-issue-to-external-repository -a claude-code`. Or copy the skill folder (.rulesync/skills/draft-issue-to-external-repository in dyoshikawa/rulesync) into .claude/skills/draft-issue-to-external-repository in your project. Claude Code loads it when a task matches its description.

How do I install Draft Issue To External Repository in Codex?

Run `npx skills add dyoshikawa/rulesync --skill draft-issue-to-external-repository -a codex`. Or copy the skill folder (.rulesync/skills/draft-issue-to-external-repository in dyoshikawa/rulesync) into .agents/skills/draft-issue-to-external-repository in your project. Codex loads it when a task matches its description.

Can I use Draft Issue To External Repository 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 dyoshikawa/rulesync --skill draft-issue-to-external-repository -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/draft-issue-to-external-repository, .gemini/skills/draft-issue-to-external-repository, .github/skills/draft-issue-to-external-repository and .opencode/skills/draft-issue-to-external-repository in your project.

What does Draft Issue To External Repository need to run?

Going by SKILL.md and its folder, Draft Issue To External Repository needs the command-line tools its instructions call (gh and curl).

Does Draft Issue To External Repository access the network?

SKILL.md names 2 domains. In commands or code: github.com and api.npmjs.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Draft Issue To External Repository 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 Draft Issue To External Repository use?

Draft Issue To External Repository 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 Draft Issue To External Repository use?

About 1.9k tokens (SKILL.md is roughly 7.7k 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 Draft Issue To External Repository?

Skills that share tags, products or a category with Draft Issue To External Repository: GitDiagram Repository Overview (ahmedkhaleel2004/gitdiagram, 18k stars), Library Documentation Seeker (withkynam/vibecode-pro-max-kit, 1.1k stars), Herdr Issue Triage (herdrdev/herdr, 43k stars) and Plane Release Notes Generator (makeplane/plane, 61k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Draft Issue To External Repository?

dyoshikawa (a GitHub user) maintains it in dyoshikawa/rulesync, which has 1,509 GitHub stars. The repository holds 40 skills in this directory. The repository was last updated on October 9, 2026.

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