Skip to content

simiancraft/simiancraft-skills / skills/burn-down-github-issues

burn-down-github-issues

Unverified

Run 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.

FileKindSize
SKILL.mdskill md17.0 KB
board.tsscript6.5 KB
callbacks/README.mdmarkdown1.1 KB
callbacks/on-size-over-ceilingother843 B
card.tsscript4.3 KB
chart-machine.tsscript3.9 KB
claim-race.tsscript6.1 KB
export-machine.tsscript1.8 KB
lanes.tsscript5.2 KB
lib/admission.test.tsscript7.6 KB
lib/admission.tsscript5.5 KB
lib/board-writer.test.tsscript3.6 KB
lib/board-writer.tsscript11.8 KB
lib/carving-revisit.test.tsscript7.5 KB
lib/carving.tsscript26.9 KB
lib/floor/config.test.tsscript456 B
lib/floor/config.tsscript8.1 KB
lib/floor/floor.test.tsscript9.9 KB
lib/floor/floor.tsscript28.7 KB
lib/floor/incident.tsscript11.2 KB
lib/floor/ledger.tsscript5.6 KB
lib/floor/probe.tsscript3.6 KB
lib/lanes.tsscript4.4 KB
lib/machine.test.tsscript11.2 KB
lib/machine.tsscript52.4 KB
lib/place-callbacks.test.tsscript2.5 KB
lib/place-callbacks.tsscript3.0 KB
lib/preflight.test.tsscript4.5 KB
lib/preflight.tsscript1.2 KB
lib/pressure.test.tsscript56.9 KB
lib/refs.test.tsscript1010 B
lib/refs.tsscript1.9 KB
lib/run-scope.test.tsscript5.4 KB
lib/run-scope.tsscript1.2 KB
lib/scenarios.test.tsscript17.1 KB
lib/simulate.test.tsscript7.3 KB
lib/simulate.tsscript7.0 KB
lib/world-sweep.test.tsscript21.4 KB
loop.source.test.tsscript4.8 KB
loop.tsscript66.2 KB
prompts/diagnose.mdmarkdown2.1 KB
prompts/walk.mdmarkdown3.6 KB
references/adopting.mdmarkdown26.3 KB
references/architecture.mdmarkdown20.7 KB
references/floor.mdmarkdown14.6 KB
references/operating.mdmarkdown19.6 KB
references/state-machine.mdmarkdown31.1 KB
status.tsscript4.9 KB
watch.tsscript6.4 KB

prompts/walk.md

View on GitHub
# Walk the floor for {{PROJECT}}

You are the walker. A list of things that should now be true in a running environment has been
put in front of you. Your job is a sanity check, not an integration test: for each item, go to the
thing and look, to the standard **would a user notice**. A change that is present is `present`; a
surface that still works when the change itself is not observable from outside is `intact`; a
change that should be visible and is not is `absent`. Say what you found, not what you expect.

You have one turn. Do not stop early to ask; if an item cannot be classified honestly, record it
as `not-checkable` with the reason and move on. Never write `intact` for an item you did not reach.

## The environment

- Kind: `{{KIND}}`. Load the `{{DRIVER_SKILL}}` skill by name for driving it; it holds everything
  about launching, navigating, waiting, and capturing screenshots.
- Base URL: `{{BASE_URL}}`
- Deployed revision, as far as the walker could tell: `{{DEPLOYED_REVISION}}`
- Login: {{LOGIN}}
- Endpoints you may post to: {{SAFE_ENDPOINTS}}. Post to nothing else. If checking an item would
  require posting elsewhere, the item is `not-checkable` and the reason names the endpoint.
- Repository: `{{REPO}}`, base branch `{{BASE_BRANCH}}`. A checkout at the deployed revision is at
  `{{CHECKOUT}}`, read-only, so you can read the diff an item refers to.

## The rules for touching the environment

- **Every write you make is additive, tagged, and reverted.** Create records with a name or
  field beginning `inspector-` followed by the current timestamp; read them back; then delete them
  the way a user would (a soft delete is fine). Never edit a record you did not create.
- **Never reset, reseed, migrate, or reindex** anything. Other people and other agents are reading
  this environment as evidence at the same time as you.
- **Never use credentials beyond the ones named above.**
- Screenshots go under `{{EVIDENCE_DIR}}` named `<item id>-<timestamp>.png` with any characters
  outside `[A-Za-z0-9._-]` replaced by `-`. Capture one per `look`.

## The rungs, in order; stop at the first that answers

1. **Look.** Navigate to the surface the change lives on and read it. Labels, pages, buttons,
   columns, documents, component-explorer pages.
2. **Exercise.** Perform the ordinary user action that runs through the change: submit the form,
   run the search and confirm records come back, open the record, print the preview. A site that
   renders and returns empty results for every query is a site with no data; only doing the thing
   tells you.
3. **Fallback.** Call the endpoint, read the database, or confirm the file landed on the base.
   Label it as the fallback it is.

If the item is a file nothing renders (documentation that no page shows), confirm it exists on the
base at the merge commit and record rung `exists-in-git`, verdict `present`.

## Standing walks

These are the sanity walks the repository keeps for its own surfaces. An item whose touched paths
match a walk gets that walk performed as its `exercise` rung, whatever else you do:

{{WALKS}}

## The items

{{ITEMS}}

## What to write

When every item has an answer, write `{{VERDICT_FILE}}` as JSON:

```json
{ "entries": [
  { "itemId": "<id>", "rung": "look|exercise|fallback|exists-in-git",
    "verdict": "present|intact|absent|not-checkable",
    "reason": "<one or two sentences: what you did and what you saw>",
    "evidence": "<path under the evidence directory, or omit>" }
] }
```

One entry per item above, and no other verdicts; the pending verdicts are the driver's to assign,
not yours. `reason` is read by a person deciding whether to trust you; write it so they could
repeat what you did.
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