Triaging the Issue Backlog
When To Use
Use this skill when auditing many issues at once: a backlog sweep, a bulk close pass, or a report on how much of the backlog can be retired.
For a single issue, use isaaclab-auditing-an-issue directly.
REQUIRED SUB-SKILL: Use isaaclab-auditing-an-issue for every individual issue. This skill only adds batch orchestration; it does not restate the per-issue checks.
Core Principle
Scale multiplies confident errors. A batch of drafted comments will read uniformly well whether or not the claims are true, so verification must be adversarial and the human review gate is not optional.
Workflow
Dump the backlog with metadata and split it into batches:
gh issue list --repo isaac-sim/IsaacLab --state open --limit 500 \
--json number,title,author,createdAt,updatedAt,labels,comments,assignees,url
Audit each issue per isaaclab-auditing-an-issue, recording a verdict, the evidence, and a confidence level.
Run an adversarial pass over every close recommendation. Instruct the reviewer to refute, and to return REFUTED or UNCERTAIN whenever it cannot independently confirm the evidence. Verify low-confidence recommendations as strictly as the rest — they refute at a far higher rate.
Sweep the drafted comments for claims that a per-issue audit misses across a batch: capability assertions, citations whose PR does not match, and dead links.
Review every comment with a maintainer, in batches, before anything is posted.
Post only what a maintainer explicitly approved.
Batch Controls
- Never infer approval. Approve on an explicit statement, not on a reply that merely discusses a batch. Record approvals so a resumed session cannot post something unreviewed.
- Keep one plan file listing every issue to be closed with its final comment, plus appendices for held issues and for issues pulled out during review with their next steps.
- Re-show anything edited after approval. Later passes rewrite earlier comments; approval does not survive a rewrite.
- Report what was excluded. State how many issues were refuted, held, or pulled out, not only how many are closeable.
Expect These Failure Modes
Measured over one full pass of the backlog; treat them as the default, not the exception.
| Failure mode |
What it looks like |
| Stale absence claims |
"Isaac Lab doesn't support X" when X moved to contrib/. |
| Mismatched citations |
A merged PR whose title fits the topic but whose diff never touches the behavior. |
| Capability drift |
Asserting a backend or release supports something it does not. |
| Answered-but-wrong |
A usage answer that was correct when written and is now outdated. |
| Blame framing |
"We never heard back" or "nothing on our side", which read badly in public. |
| Defensible but lossy |
A close whose reason is sound but which discards the only record of a live problem. |
Common Mistakes
- Treating a high-confidence label as a substitute for verification.
- Batching approval across issues that were edited at different times.
- Reporting a reduction figure without the refuted and held counts.
- Posting before a maintainer has read the specific comment being posted.
Validation
Before posting, confirm the batch is internally consistent: every comment ends with the intended marker, every cited PR is merged, and every URL resolves.
gh pr view PR_NUMBER --repo isaac-sim/IsaacLab --json state,mergedAt,title
curl -s -o /dev/null -w "%{http_code}" -L "URL"
If skills changed, run:
uv run --no-project python tools/skills/cli.py check
Maintenance
Keep the per-issue checks in isaaclab-auditing-an-issue and do not duplicate them here. Update the failure-mode table when a new class of error survives verification into a posted comment.
References
1---2name: isaaclab-triaging-issue-backlog3description: Triages many open GitHub issues at once into close/keep-open with drafted closing comments. Use when auditing the whole issue backlog, running a bulk close pass, or reporting how many issues can be retired.4audience: developer5status: experimental6owners:7 - isaaclab-maintainers8metadata:9 source: https://skillmd.com/skills/isaac-sim/isaaclab-triaging-issue-backlog10---1112# Triaging the Issue Backlog1314## When To Use1516Use this skill when auditing many issues at once: a backlog sweep, a bulk close pass, or a report on how much of the backlog can be retired.1718For a single issue, use `isaaclab-auditing-an-issue` directly.1920**REQUIRED SUB-SKILL:** Use `isaaclab-auditing-an-issue` for every individual issue. This skill only adds batch orchestration; it does not restate the per-issue checks.2122## Core Principle2324Scale multiplies confident errors. A batch of drafted comments will read uniformly well whether or not the claims are true, so verification must be adversarial and the human review gate is not optional.2526## Workflow27281. Dump the backlog with metadata and split it into batches:2930 ```bash31 gh issue list --repo isaac-sim/IsaacLab --state open --limit 500 \32 --json number,title,author,createdAt,updatedAt,labels,comments,assignees,url33 ```34352. Audit each issue per `isaaclab-auditing-an-issue`, recording a verdict, the evidence, and a confidence level.363. Run an adversarial pass over every close recommendation. Instruct the reviewer to **refute**, and to return REFUTED or UNCERTAIN whenever it cannot independently confirm the evidence. Verify low-confidence recommendations as strictly as the rest — they refute at a far higher rate.374. Sweep the drafted comments for claims that a per-issue audit misses across a batch: capability assertions, citations whose PR does not match, and dead links.385. Review every comment with a maintainer, in batches, before anything is posted.396. Post only what a maintainer explicitly approved.4041## Batch Controls4243- **Never infer approval.** Approve on an explicit statement, not on a reply that merely discusses a batch. Record approvals so a resumed session cannot post something unreviewed.44- **Keep one plan file** listing every issue to be closed with its final comment, plus appendices for held issues and for issues pulled out during review with their next steps.45- **Re-show anything edited after approval.** Later passes rewrite earlier comments; approval does not survive a rewrite.46- **Report what was excluded.** State how many issues were refuted, held, or pulled out, not only how many are closeable.4748## Expect These Failure Modes4950Measured over one full pass of the backlog; treat them as the default, not the exception.5152| Failure mode | What it looks like |53|---|---|54| Stale absence claims | "Isaac Lab doesn't support X" when X moved to `contrib/`. |55| Mismatched citations | A merged PR whose title fits the topic but whose diff never touches the behavior. |56| Capability drift | Asserting a backend or release supports something it does not. |57| Answered-but-wrong | A usage answer that was correct when written and is now outdated. |58| Blame framing | "We never heard back" or "nothing on our side", which read badly in public. |59| Defensible but lossy | A close whose reason is sound but which discards the only record of a live problem. |6061## Common Mistakes6263- Treating a high-confidence label as a substitute for verification.64- Batching approval across issues that were edited at different times.65- Reporting a reduction figure without the refuted and held counts.66- Posting before a maintainer has read the specific comment being posted.6768## Validation6970Before posting, confirm the batch is internally consistent: every comment ends with the intended marker, every cited PR is merged, and every URL resolves.7172```bash73gh pr view PR_NUMBER --repo isaac-sim/IsaacLab --json state,mergedAt,title74curl -s -o /dev/null -w "%{http_code}" -L "URL"75```7677If skills changed, run:7879```bash80uv run --no-project python tools/skills/cli.py check81```8283## Maintenance8485Keep the per-issue checks in `isaaclab-auditing-an-issue` and do not duplicate them here. Update the failure-mode table when a new class of error survives verification into a posted comment.8687## References8889- [Issue audit skill](../issue-audit/SKILL.md)90- [Contributing guide](../../../docs/source/refs/contributing.rst)