Skip to content

simiancraft/simiancraft-skills / skills/appraise-github-issues

appraise-github-issues

Verified

Appraise a GitHub issue backlog unattended: for each issue, decide whether it is still real and how big it is, then apply the answer to the tracker as a size label, a needs-decision or needs-human label with the question stated, or a close carrying a re-checkable receipt. A close is confirmed by a second engine before it is made. Runs once, on one issue, over the whole backlog, or as a periodic heartbeat, and is the sizing stage of burn-down-github-issues. Use when the task is "size the backlog", "appraise every issue in this repo", "close what is already done", "triage recent issues without fixing them", or "keep the backlog sized". Requires a per-repository config (its own, or the burndown's) and the codex and claude CLIs for the default seats. Skip for fixing anything; this skill never writes to the repository.

FileKindSize
SKILL.mdskill md7.1 KB
appraise.tsscript12.7 KB
lib/appraise.test.tsscript2.8 KB
lib/appraise.tsscript30.9 KB
lib/callbacks.tsscript4.1 KB
prompts/appraise.mdmarkdown6.2 KB
prompts/confirm-close.mdmarkdown3.3 KB
references/adopting.mdmarkdown4.0 KB
references/callbacks.mdmarkdown3.4 KB

lib/appraise.test.ts

View on GitHub
import { describe, expect, it } from 'bun:test';
import { FakeTracker, fakeIssue } from '../../carve-github-issue/lib/fake-tracker.ts';
import { readTree } from '../../carve-github-issue/lib/tree.ts';
import type { Context } from '../../fix-github-issue/lib/context.ts';
import { appraiseIssue, refusedAsTrunk, validateAppraisal } from './appraise.ts';

const treeOf = (labels: string[]) => {
  const io = new FakeTracker('loop-bot', [fakeIssue(1, { labels: labels.map((name) => ({ name })) })]);
  return readTree({ botLogin: 'loop-bot', runId: 'host-1-1', io } as unknown as Context, 1, io);
};

describe('the trunk gate an appraisal asks at every step', () => {
  it('refuses a released trunk, unless the burndown asked for its release appraisal', () => {
    expect(refusedAsTrunk(treeOf(['loop/released']), undefined)).toBe(true);
    expect(refusedAsTrunk(treeOf(['loop/released']), true)).toBe(false);
  });
  it('never refuses a leaf', () => {
    expect(refusedAsTrunk(treeOf(['bug']), undefined)).toBe(false);
    expect(refusedAsTrunk(treeOf(['bug']), true)).toBe(false);
  });
});

describe('the engines an appraisal requires', () => {
  const ctx = () => ({ botLogin: 'loop-bot', runId: 'host-1-1', io: new FakeTracker('loop-bot', [fakeIssue(1)]), log: () => {}, dryRun: true }) as unknown as Context;
  const seats = { appraiser: { engine: 'claude' }, confirmer: { engine: 'claude' } } as const;
  const run = (confirmCloses: boolean) =>
    appraiseIssue(ctx(), { number: 1, title: 't', createdAt: '2026-09-01T00:00:00Z', labels: [] } as never, { ageDays: null, seats, confirmCloses, skipLabels: [] }).then(
      () => '',
      (error: Error) => error.message,
    );
  it('refuses one engine in both seats when closes are confirmed', async () => {
    expect(await run(true)).toMatch(/must be different engines/);
  });
  it('does not care which engine the confirmer is when closes are not confirmed', async () => {
    expect(await run(false)).not.toMatch(/must be different engines/);
  });
});

describe('an appraisal that closes the issue', () => {
  const base = { issue: 7, reason: 'the spike measured 0.1 ms; nothing remains', closeComment: 'Nothing to do.' };

  it("reads the scale's zero on a closing verdict as no size, not a malformed answer", () => {
    const answer = validateAppraisal({ ...base, verdict: 'obsolete', points: 0 }, 7);
    expect(answer.ok).toBe(true);
    if (answer.ok) expect(answer.result.points).toBeUndefined();
  });

  it('still refuses a zero size on work it calls valid', () => {
    const answer = validateAppraisal({ ...base, verdict: 'valid', points: 0 }, 7);
    expect(answer.ok).toBe(false);
  });

  it('still refuses a negative size on any verdict', () => {
    expect(validateAppraisal({ ...base, verdict: 'already-fixed', points: -1 }, 7).ok).toBe(false);
  });
});
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall