agentleFS
processmissionprocessmission/oh-my-qemu/skills/qemu-agent-feedback/SKILL.md

qemu-agent-feedback

Skill60 starsChanged 13 days agoMITView on GitHub

Use when a completed QEMU skill session exposed a reusable oh-my-qemu workflow problem and the user wants a sanitized improvement proposal drafted or filed as a GitHub issue.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the proposal at summary level: no raw logs, source snippets, stack traces, private commands, or unreviewed artifacts.

    line 37
  2. Distinctive:

    Verify the proposed title and body disclose none of these values before presenting the draft.

    line 64
  3. Very specific:

    Write the title to .oh-my-qemu/<task-slug>/output/methodology-issue-title.txt and the body to …

    line 69
  4. Very specific:

    Run check-redaction.sh over the title and body before presenting the draft, and resolve every finding:

    line 74
  5. Very specific:

    After the user approves the exact title, body, and target repository, check gh auth status and confirm the issue is not a duplicate.

    line 83

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

QEMU Agent Feedback

Audit workflow

For a non-trivial task that writes to the workspace, use only the needed entries under .oh-my-qemu/<task-slug>/: audit.md (baseline, plan, decisions, evidence, verification, and gaps), commands.md (redacted commands, working directories, and results), logs/ (decisive build, test, and runtime output), scripts/ (probes, parsers, and harnesses), and output/ (generated deliverables, third-party dependencies, and non-QEMU binaries). Keep QEMU's own build tree at source-root builds/build-<target>/, never an unqualified build/. In a Git worktree, add .agents/, .oh-my-qemu/, and builds/ to the file from git rev-parse --git-path info/exclude before writing artifacts or configuring QEMU; preserve existing entries and avoid duplicates. Never stage or commit these paths; stage source only when the user explicitly requests that separate action. At handoff, reconcile git status --short with the baseline and report the task directory, build directory, source changes, pre-existing changes, and unresolved gaps.

QEMU upstream boundary

QEMU's official GitLab and mailing lists are upstream channels. A patch becomes an upstream contribution when it is sent to the maintainers selected through MAINTAINERS. Do not prepare or send agent-generated code, documentation, commit messages, or patches for upstream submission; see the checked-out tree's docs/devel/code-provenance.rst. Research, debugging, analysis, local experiments, verification, and workflow guidance remain allowed. Local branches, commits, patch files, pushes, and pull requests are not by themselves upstream contributions; perform those Git actions only when requested.

Privacy boundary

Keep the proposal at summary level: no raw logs, source snippets, stack traces, private commands, or unreviewed artifacts. Do not file anything unless the user explicitly asks for it or approves the exact title and body.

The default issue repository is processmission/oh-my-qemu; honor an explicit choice.

One issue per proposal

Draft one reusable workflow problem per issue; leave incidental fixes out. Search existing issues before drafting with gh issue list --repo processmission/oh-my-qemu --search "<keywords>" --state all, then report a match instead of filing a duplicate; update it only with user approval. If gh is unavailable, record the gap and produce the draft.

Sanitize

Sensitive valuePublic replacement
local paths, user names, home directories<local-path>
hostnames, machine IDs, hardware serials<host>
git author identity, email, Signed-off-by<author>
private repositories, branches, commits, or tree IDs<repo> / <git-ref>
private URLs, endpoints, credentials, or tokens<url> / <secret>
proprietary artifacts, SDKs, images, kernels, root filesystems<artifact>
build paths, source roots, task and audit directories<build-path>
unapproved customer, product, board, or SoC names<target>
raw logs, stack traces, commands, or codea behavior-level summary

Verify the proposed title and body disclose none of these values before presenting the draft; treat uncertainty as a privacy gap and ask the user.

Draft

Write the title to .oh-my-qemu/<task-slug>/output/methodology-issue-title.txt and the body to .oh-my-qemu/<task-slug>/output/methodology-issue.md using issue-template.md. State the affected skill, observed and expected behavior, and evidence gaps; never generalize a project-specific failure.

Run check-redaction.sh over the title and body before presenting the draft, and resolve every finding:

bash <skill-dir>/scripts/check-redaction.sh <title-file> <body-file>

File only with approval

After the user approves the exact title, body, and target repository, check gh auth status and confirm the issue is not a duplicate. Then run:

gh issue create --repo "<approved owner/repository>" \
  --title "<approved title>" \
  --body-file .oh-my-qemu/<task-slug>/output/methodology-issue.md

Record the approved repository, command, and issue URL in commands.md and audit.md. If gh is unavailable or fails, keep the sanitized drafts and report the gap.

Upstream references

  • docs/devel/code-provenance.rst
  • docs/devel/submitting-a-patch.rst
  • docs/devel/testing/main.rst

Paths can differ between QEMU versions; locate them in the checked-out tree.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.