new-issue-loop
Skill50 starsChanged 5 days agoMITView on GitHub
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.
In this repository39 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- app-prdSkill
- cli-dispatchSkill
- codex-validate-plan-work-on-issueSkill
- create-releaseSkill
- execution-plan-reviewSkill
- expo-app-initializeSkill
- fable-advisorSkill
- fable-dispatchSkill
- fable-new-issue-loopSkill
- fable-new-issueSkill
- fable-orchestrateSkill
- fableplan-loopSkill
- fableplanSkill
- fableplan-work-on-issueSkill
- fable-validate-fableplan-loopSkill
- fable-validate-fableplanSkill
- fable-validate-loopSkill
- fable-validateSkill
- fix-pr-review-loopSkill
- fix-pr-reviewSkill
- github-issue-formatSkill
- issueplanSkill
- milestoneplanSkill
- milestone-workflowSkill
- new-app-pipelineSkill
- new-issueSkill
- prd-questionsSkill
- prd-to-issuesSkill
- pr-reviewSkill
- sync-docs-releaseSkill
- sync-docsSkill
- tldrSkill
- validate-fableplan-loopSkill
- validate-issue-loopSkill
- validate-issueSkill
- wansSkill
- work-on-issue-loopSkill
- work-on-issueSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Do not skip filing a complete issue: Every step of new-issue still runs (grounding, approach design, complexity score).
- Distinctive: line 38
Run validation even though this session wrote the issue: validate-issue re-traces the claims against the code independently.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
| Condition | Action |
| 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 candidates | If 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-ups | Continue 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
| Situation | Action |
| Tempted to skip new-issue's grounding/duplicate check to get to implementation faster | Never |
| new-issue stopped on a duplicate | Stop and report per step 2; don't file anyway |
| Tempted to hand off without an explicit issue reference | Always pass the step 1 owner/repo#N |
| validate-issue-loop's scope gate stops the run | Report its disposition faithfully; don't override and implement anyway |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.