issue
Draft well-structured GitHub issues with clear titles, structured descriptions, acceptance criteria, and appropriate labels.
Skill by Peleke
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/peleke-issue
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, writing, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/issue
What's inside
- Skill name
issue- Description
- Draft well-structured GitHub issues with clear titles, structured descriptions, acceptance criteria, and appropriate labels. Use this skill when a user asks to create, write, or draft a GitHub issue, bug report, feature request, task ticket, or RFC/proposal. Also use when a user asks to file an issue, open a ticket, or report a bug.
- License
- MIT
- Instructions
- 134 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- issue-templates.md · references/
SKILL.md (first lines)
# GitHub Issue Drafting Draft comprehensive GitHub issues that are actionable, well-scoped, and easy for contributors to pick up. ## Workflow 1. **Gather context** -- Understand what the user wants to report or request 2. **Classify the issue type** -- Bug report, feature request, task, or RFC/proposal 3. **Draft the issue** -- Apply the appropriate structure from `references/issue-templates.md` 4. **Refine** -- Suggest labels, link related issues, and tighten scope ## Step 1: Gather Context Before drafting, establish: - **What happened or what is needed?** Get the core problem or request. - **Who is affected?** Users, developers, specific teams. - **What is the impact?** Severity, frequency, blocking status. - **Is there existing context?** Related issues, PRs, Slack threads, error logs. If the user provides minimal context, ask targeted questions. Do not ask more than 3-5 questions at once. If the user provides rich context (error logs, reproduction steps, design ideas), proceed directly to drafting. When working in a codebase, use available tools to gather context: - Read relevant source files to reference specific code paths - Check git log for recent changes related to the issue - Search for existing issues or TODOs in the codebase ## Step 2: Classify Issue Type Select the type based on the user's intent: | Signal | Type | |--------|------| | Something is broken, wrong output, crash, error | **Bug report** | | New capability, improvement, user-facing change | **Feature request** | | Internal work, refactor, chore, migration | **Task** | | Architectural change, needs team input, multiple valid approaches | **RFC/proposal** | If ambiguous, default to **task** for internal work or **feature request** for user-facing work. Ask the user only if the classification materially changes the issue structure. ## Step 3: Draft the Issue Load `references/issue-templates.md` and apply the template for the classified type. ### Writing Good Titles Titles are the most-read part of any issue. Follow these rules: - **Start with a verb** for bugs and tasks: "Fix", "Add", "Update", "Remove", "Migrate" - **Start with a noun or area** for features and RFCs: "Authentication: support SSO", "API: rate limiting strategy" - **Be specific, not vague:** "Fix null pointer in UserService.getProfile when email is missing" not "Fix bug in user service" - **Include the affected component** when the repo has multiple areas: "[api] Fix 500 on /users/me with expired token" - **Stay under 72 characters** when possible **Bad titles:** - "Bug" / "Fix issue" / "Update code" / "Improvement" - "It doesn't work" / "Something is wrong with login" **Good titles:** - "Fix crash when uploading files larger than 10MB" - "Add dark mode support to settings page" - "Migrate user sessions from Redis to PostgreSQL" - "RFC: Replace REST API with GraphQL for mobile clients" ### Structural Guidelines Apply these regardless of issue type: **Description section:** - Lead with the most important information. A reader should understand the issue from the first two sentences. - Use concrete, observable facts. Replace "sometimes fails" with "fails on 3 of 10 attempts with error X". - Include code references as links or path+line when relevant: `src/api/auth.ts:42` **Acceptance criteria:** - Every issue needs at least one acceptance criterion. - Phrase criteria as checkboxes: `- [ ] Criterion here` - Each criterion must be independently verifiable. "Works correctly" is not a criterion. "Returns 200 with valid JSON body matching schema X" is. - Include non-functional criteria when relevant: performance, backward compatibility, documentation. **Scope control:** - If the issue grows beyond a single PR's worth of work, suggest splitting it. - Explicitly call out what is out of scope to prevent scope creep. - Prefer smaller, focused issues over large omnibus issues. ## Step 4: Refine After drafting, review and improve: ### Suggest Labels Recommend 2-4 labels based on the issue. Common taxonomy: - **Type:** `bug`, `enhancement`, `task`, `rfc`, `documentation` - **Priority:** `priority:critical`, `priority:high`, `priority:medium`, `priority:low` - **Area:** `area:frontend`, `area:backend`, `area:api`, `area:infra` Check the repo's existing labels first (via `gh label list` if available) to match the project's conventions. ### Link Related Context - Reference related issues: "Related to #123" or "Blocked by #456" - Mention relevant PRs: "Regression from #789" - Link to external resources: docs, Slack threads, monitoring dashboards - Tag specific people only when their input is required to unblock the issue ### Final Checks Before presenting the draft to the user: 1. Can someone unfamiliar with the codebase understand what needs to happen? 2. Is the scope clear and achievable in a single PR (or explicitly broken into phases)? 3. Are acceptance criteria specific and testable? 4. Does the title accurately summarize the issue? ## Creating Issues via CLI When the user wants to actually create the issue (not just draft it), use the GitHub CLI: ```bash gh issue create --title "Title here" --body "$(cat <<'EOF'
From Peleke/brunnr, MIT.
More from Peleke/brunnr
- 0.497score
dossier-generator
Peleke
Turn a built system plus a client/deal context into three linked artifacts: a dual-format dossier (human executive summary + agent-facing implementation…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-pack
Peleke
Package a piece of completed work into an agent-consumable pack: an entrypoint README, the source documents, and an input-output contract, ready to hand to an…
SkillCFreshness: C★ 1Claude Code +9 - 0.437score
hunter-log
Peleke
Persistence layer for the hunter product discovery pipeline.
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
chapter-generator
Peleke
Generate a single tutorial chapter from a structured spec.
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
community-pitch
Peleke
Community pitch engine -- takes persona extraction output and signal scan data, then produces a complete paid community plan with concept, platform…
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
content-planner
Peleke
Scan GitHub activity and buildlog entries, synthesize engineering work into publishable content opportunities with fan-out analysis, and output an…
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
curriculum-planner
Peleke
Interactive elicitation protocol for designing tutorial series.
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
decision-log
Peleke
Structured product decision engine -- takes signal scan output and operator preferences, applies the Signal-to-Decision Pipeline (SDP) framework, and produces…
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
linwheel-content-engine
Peleke
Orchestrate LinkedIn content creation through LinWheel's MCP server.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
ax-interview
Peleke
Run a structured AX Interview on an agent-tool interaction session.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
ax-rubric
Peleke
Score agent-facing tool descriptions against the AX Description Rubric.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
engagement-pass
Peleke
Retrofit existing notebooks with interactive engagement elements — Plotly plots, video embeds, ipywidgets, animations, concept maps, and "build a toy"…
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 14
- Last commit (this folder)
- Mar 14, 2026 (7 months ago)
- Last release
- Mar 12, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Peleke/brunnr
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Peleke
- 0.497score
dossier-generator
Peleke
Turn a built system plus a client/deal context into three linked artifacts: a dual-format dossier (human executive summary + agent-facing implementation…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-pack
Peleke
Package a piece of completed work into an agent-consumable pack: an entrypoint README, the source documents, and an input-output contract, ready to hand to an…
SkillCFreshness: C★ 1Claude Code +9 - 0.437score
curriculum-planner
Peleke
Interactive elicitation protocol for designing tutorial series.
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
chapter-generator
Peleke
Generate a single tutorial chapter from a structured spec.
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
community-pitch
Peleke
Community pitch engine -- takes persona extraction output and signal scan data, then produces a complete paid community plan with concept, platform…
SkillDFreshness: D★ 1Claude Code +9 - 0.437score
content-planner
Peleke
Scan GitHub activity and buildlog entries, synthesize engineering work into publishable content opportunities with fan-out analysis, and output an…
SkillDFreshness: D★ 1Claude Code +9
Cite this page
issue skill. Agent Mart. https://agentmart.dev/skills/peleke-issue (last updated 2026-10-24)