simiancraft/simiancraft-skills / skills/burn-down-github-issues
burn-down-github-issues
UnverifiedRun an unattended burndown of a GitHub issue backlog as cards on a per-operator GitHub Projects board whose lanes are an explicit state machine: appraise and size the inbox, carve what is over the ceiling, fix the ready ones in parallel git worktrees, prove each fix on a draft pull request, have an isolated second-engine reviewer judge it, land one branch at a time with freshness checks, and dead-letter per phase whatever a machine cannot finish. Use when the task is "work the backlog unattended", "triage and fix recent issues", "run the issue loop", "burn down issues", or "where is issue N on the board". Requires a per-repository burn-down-github-issues.config.ts at the target repo's root (the loop refuses to start without it), the prove-work-on-github skill, the codex and claude CLIs for the default seats, and a gh token with the project scope for the board. Skip for one-off fixes to a known issue you are already working interactively, and for backlogs whose issues are mostly product decisions rather than code.
lib/refs.ts
View on GitHub/**
* The issue numbers a set of pull requests reference: by `#1234` in title or body or `-1234` in
* the branch (`any`), or only by a closing keyword before the number at the start of a line or a
* sentence (`closing`), which is what makes a merge a resolution rather than a mention. Lexical:
* a sentence that starts with the keyword counts, one that starts with "not" or "does not" does not.
*/
export function issueRefs(prs: Array<{ body: string; title: string; headRefName: string }>, mode: 'any' | 'closing' | 'owning' = 'any'): number[] {
const refs: number[] = [];
const CLOSING = /^(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)\s+#(\d{1,6})\b/i;
const OWNING = /\b(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?|refs?)\s+#(\d{1,6})\b/gi;
for (const pr of prs) {
if (mode === 'owning') {
// A pull request owns an issue when its branch names it or its body references it with a
// keyword. A passing `#1234` in another change's body is a mention, not a claim: one such
// mention kept a sized issue out of selection for a whole run.
for (const match of `${pr.title}\n${pr.body}`.matchAll(OWNING)) refs.push(Number(match[1]));
for (const match of pr.headRefName.matchAll(/(?:^|[/_-])(\d{1,6})(?=$|[/_-])/g)) refs.push(Number(match[1]));
continue;
}
if (mode === 'closing') {
for (const sentence of `${pr.title}\n${pr.body}`.split(/\r?\n|[.!?]\s+/)) {
const match = CLOSING.exec(sentence.trim());
if (match) refs.push(Number(match[1]));
}
continue;
}
for (const match of `${pr.title}\n${pr.body}`.matchAll(/#(\d{1,6})\b/g)) {
refs.push(Number(match[1]));
}
// A branch name is structured, so a number standing alone between separators is a reference:
// `fix/1234-null-guard` and `feat/1240-export-button` both name their issue.
for (const match of pr.headRefName.matchAll(/(?:^|[/_-])(\d{1,6})(?=$|[/_-])/g)) {
refs.push(Number(match[1]));
}
}
return refs;
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |