richkuo/rk-skills/new-issue-loop

Claude Code and agent skill by richkuo/rk-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when the user asks to file a GitHub issue and then autonomously drive it all the way to a reviewed PR in one shot — "new-issue-loop", "create the issue and run it to completion", "file this and fully automate it". Runs new-issue to create a fully-specified issue, then hands the new issue's `owner/repo#N` reference to validate-issue-loop (validate → update → work-on-issue-loop) — stopping instead when new-issue finds a duplicate or the discussion hasn't converged on one issue.

Install

npx vskill@latest install richkuo/rk-skills/new-issue-loop

SKILL.md

new-issue-loop

Chain new-issue → validate-issue-loop into one autonomous run with no human between steps: the loop feeds the issue it just filed into the validate-and-implement pipeline.

Do not skip filing a complete issue. Every step of new-issue still runs (grounding, approach design, complexity score); only the "offer next steps and wait" step is replaced by the handoff.

Input

Same as new-issue: an optional description of what the issue should cover; with no input, derive it from the current conversation. Optionally owner/repo when the issue belongs elsewhere.

Steps

1. Run new-issue

Invoke the new-issue skill (Skill tool, skill: new-issue) with the user's description (or conversation-derived scope). Let it run its full process. Capture the created issue from its report as the full reference owner/repo#N: the repository new-issue filed to (its -R owner/repo, else the current checkout per gh repo view --json nameWithOwner -q .nameWithOwner) and the new number.

2. Stop gate — cases the loop can't safely continue
ConditionAction
new-issue found an existing open issue/PR already covering it (no issue filed)STOP. Report the duplicate and new-issue's offer to update/comment instead; do not merge scopes yourself.
The conversation held several distinct candidatesIf one clearly converged, file it and continue the chain with it; the unfiled candidates go in the final report. If none clearly converged, STOP — report the candidates and ask which to file. Never bundle, never auto-file the extras.
new-issue split the work and named unfiled follow-upsContinue with the core issue only; relay the unfiled follow-ups in the final report.

Otherwise (one issue filed cleanly), continue.

3. Hand off to validate-issue-loop

Invoke the validate-issue-loop skill (Skill tool, skill: validate-issue-loop) with the step 1 owner/repo#N passed explicitly, always, whichever repository new-issue filed to. Its own scope gate (too large / infeasible / already-addressed) and its edit-landing stop still apply and may stop the run; the report relays such a stop as a stop.

validate-issue-loop owns the plan: yes signal that new-issue reports: that chain never plans, and its report says when a plan was due. This skill adds no plan gate of its own.

Run validation even though this session wrote the issue: validate-issue re-traces the claims against the code independently.

4. Report

Relay validate-issue-loop's final summary (PR URL, review cycles, verdict), prefixed with one line covering the front of the chain: issue number/URL filed, complexity score, and any unfiled follow-ups from step 2.

Cap the whole report at 55 words and 5 sentences, plain simple English in ASD-STE100 — apply the Response Style rules in CLAUDE.md/AGENTS.md, written for a reader with no context on this codebase.

Red Flags — STOP

SituationAction
Tempted to skip new-issue's grounding/duplicate check to get to implementation fasterNever
new-issue stopped on a duplicateStop and report per step 2; don't file anyway
Tempted to hand off without an explicit issue referenceAlways pass the step 1 owner/repo#N
validate-issue-loop's scope gate stops the runReport its disposition faithfully; don't override and implement anyway

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

7-day trend score
0

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/richkuo/rk-skills/new-issue-loop/badge)](https://verified-skill.com/skills/richkuo/rk-skills/new-issue-loop)

Something wrong with this skill or its page? Tell us.