richkuo/rk-skills/github-issue-format
Claude Code and agent skill by richkuo/rk-skills
- community
Checking that the SKILL.md file is still in the repository.
Required format for creating or editing any GitHub issue — [C<score>] title convention, complexity rationale line, complete-body rule, mandatory Plain simple English section, attribution footer, milestone title rule. Load BEFORE creating or editing a GitHub issue or milestone.
Install
npx vskill@latest install richkuo/rk-skills/github-issue-formatSKILL.md
GitHub issue format
Title
[C<score>] <title>: a plain-simple-English sentence in ASD-STE100, precise about component and behavior, e.g.[C95] Orders can be filled twice when two fills arrive at the same moment.- The complexity score (0–100) is a model and effort routing signal.
validate-issuestep 6 owns the formula, axes, and routing table; never restate or approximate them here.
Milestone
- Every milestone title you create or rename is one hyphenated token with no spaces (
MCP-Read-foundations,Backtest-live-parity). This holds for every path that creates one: a batch fromprd-to-issues, a split of one issue into follow-ups, or a manual request. - Before you assign an issue to a milestone that has spaces in its title, rename that milestone to the hyphenated form (
gh api -X PATCH repos/<owner>/<repo>/milestones/<number> -f title=<new-title>). The rename keeps every issue on the milestone. Quote a title that still has spaces in everyghcall.
Body
- Never create a placeholder, stub, or empty-bodied issue. Every issue gets a complete body at creation, even in a batch. If a follow-up is not ready to spec, track it in the parent issue or notes until it is.
- Section order: complexity rationale line,
## Problem,## Goal,## Approach,## Acceptance criteria,## Plain simple English, then any Execution block, then the attribution footer. - Complexity rationale line (first line of the body): matches the title prefix and ends with an explicit plan signal:
**Complexity: 95/100** — Capability 3 (Risk 4, Uncertainty 2 — money/data-integrity on order-fill path); Volume 20 (Scope 4, Coupling 3, Verification 3) — Opus 5.5, high · plan: yes. The line always carries all five axis grades; the validate-issue scoring reference owns the axes and their anchors.
- plan signal:
· plan: yeswhen the score is ≥ 75 (a plan is posted before the build, by Opus 5.5 at xhigh when the score is ≥ 85 and at high below 85, unless aPlan model: Fable 5.1stamp asks for Fable, whose plan runs only at high; the builder is Opus 5.5 at high);· plan: nobelow 75. Always write it. Compatibility (owned here): the signal and the Execution block key were once spelled· fableplan: yes|noand**fableplan first:**, and the PR-title suffix, fableplan. Every reader accepts both spellings, every writer emits onlyplan, and a restamp rewrites an old spelling to the new one. Fable 5.1 effort tiers follow the LLM Attribution Footer section of CLAUDE.md. - `## Plain simple English` is mandatory on every issue: one short paragraph under 55 words in ASD-STE100, per the CLAUDE.md/AGENTS.md Response Style definition. State what is wrong or missing and why it matters, for a reader who knows the product but not the code. Never restate the approach, list file paths or symbols, or give a time or effort estimate there. An edit that rewrites body prose adds the section when it is missing; an edit that changes only machine metadata (the Execution block, the
[C<score>]title prefix, or the complexity rationale line, as a rescore-only edit does) leaves every prose section unchanged and does not add it. - LLM Attribution Footer ends the body:
Createdfor a new issue,Validatedwhen a validation pass produced the edit (validate-issueand its wrappers),Updatedfor any other edit. Stack the new line under the existing ones; never replace them, and never append an exact duplicate of a line already there. - Project precedence: a repo CLAUDE.md issue or footer format overrides this default.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/github-issue-format/SKILL.md
Popularity
- Repository stars
- 35
- Repository forks
- 7
- 7-day trend score
- 18
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/richkuo/rk-skills/github-issue-format)