Skip to content

simiancraft/simiancraft-skills / skills/carve-github-issue

carve-github-issue

Verified

Break one GitHub issue that is too large to work into sub-issues, unattended, and keep the carving honest as the children close. A carver names the pieces along the highest natural seam (domain, tier, route, area, file, unit, material), matches each against the backlog so nothing is authored twice, and a second engine confirms the cut covers the parent before anything is created. The parent becomes a trunk that is finished by closing its children; every child close re-checks the trunk, and a trunk with nothing left goes back to the appraiser. Use when the task is "this issue is too big, split it", "carve #N into sub-issues", "is this carving still good", or when burn-down-github-issues sizes an issue over its ceiling. Requires a per-repository config (its own, or the burndown's), the codex and claude CLIs for the default seats, and GitHub sub-issues on the repository. Skip for fixing anything; this skill writes only to the tracker.

FileKindSize
SKILL.mdskill md5.9 KB
carve.tsscript10.6 KB
lib/callbacks.tsscript1.4 KB
lib/carve.test.tsscript19.0 KB
lib/carve.tsscript25.6 KB
lib/claims.test.tsscript12.9 KB
lib/claims.tsscript13.8 KB
lib/fake-tracker.tsscript9.4 KB
lib/knife.test.tsscript52.3 KB
lib/knife.tsscript52.9 KB
lib/record.tsscript12.7 KB
lib/tree.tsscript23.3 KB
lib/validate.test.tsscript12.8 KB
prompts/carve.mdmarkdown8.1 KB
prompts/confirm-carve.mdmarkdown4.1 KB
prompts/revisit.mdmarkdown4.9 KB
references/adopting.mdmarkdown6.3 KB
references/callbacks.mdmarkdown1.7 KB
references/lifecycle.mdmarkdown29.7 KB
references/seams.mdmarkdown9.1 KB
references/the-record.mdmarkdown6.6 KB

references/callbacks.md

View on GitHub
# Callbacks

Two slots, on the shared slot mechanism in `fix-github-issue/lib/callbacks.ts`, in the same
directory the appraiser's size callbacks live (`callbacksDir`, by default
`<worktreeRoot>/appraisal-callbacks`):

| Slot | When |
|---|---|
| `on-carve-pass` | a confirmed `carve`, `amend`, `still-good`, or `exhausted` |
| `on-carve-fail` | a confirmed hand-off (`small-enough`, `indivisible`, `nothing-left`, `too-uncertain`), or a dispute that reached the round cap |

Each may exist as an executable (run by the knife with the payload as one line of JSON on stdin,
its own process group, no timeout, exit code logged) and as a Markdown prompt `<name>.md` (left
for a producer that wants one; the knife does not run it).

## The payload

```json
{
  "key": { "issue": 1282, "generation": 1, "epoch": 1, "revisits": 0, "verdict": "carve" },
  "issue": 1282, "title": "...", "mode": "carve", "verdict": "carve",
  "generation": 1, "seam": "domain", "relation": "layers",
  "children": [1301, 1302], "superseded": [], "paused": [],
  "reason": "...", "repo": "owner/repo", "baseBranch": "main", "repoRoot": "/abs/path"
}
```

## When a callback replays

A callback runs before the write that completes its intent (the `live` record, `loop/released`),
so a run that dies between the two replays the callback when the next run finishes the intent.
That is the only way a callback runs twice. A callback with a side effect keys on `key`: the same
`{issue, generation, epoch, revisits, verdict}` is the same event. A callback's exit code is logged
and a non-zero exit is not retried; the knife cannot tell a failed side effect from a completed
one, and nothing a callback does can fail the carve.
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: 472kUpdated 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