From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from ms.lwn.net (ms.lwn.net [45.79.88.28]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 625BF30D3EB; Mon, 12 Oct 2026 22:47:21 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.79.88.28 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791845242; cv=none; b=HCGs88U5vFxaOeRs2/RVEa59SUMM2D/79byCOV06/CdgSPNzQhl1FwnwY6tUbxTUnddBm2kM2khwftDr5lP3opUJuaduzCScKkvo4JfnDN4jGI5vmvU5x+bK4yCUPclpV6ycKFHRH+1ZkbzfJOKeUOBSSREf5qAt5x0gGL33LTg= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791845242; c=relaxed/simple; bh=lO3hYstUc7DzsSd9NZZIoY9nl1kfdGbzMtG5Ks7VECU=; h=From:To:Cc:Subject:In-Reply-To:References:Date:Message-ID: MIME-Version:Content-Type; b=MaCgmICoecVf8/4x3ScFzTARumh1chiW4mk9PPA0uAGfTkONIRdPHZgI3dqT6JNvUipQnqhFPDLAL0VhA2Qgw11BXTYHdIheH+MOBhpKY8Nm3FEGiteqXOXn2jYA1V5pJc5Zk8aKe4R7igja7uRrHPhxf5XUZIkHbAjt6TNGrk8= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=lwn.net; spf=pass smtp.mailfrom=lwn.net; dkim=pass (2048-bit key) header.d=lwn.net header.i=@lwn.net header.b=gA4n+9iy; arc=none smtp.client-ip=45.79.88.28 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=lwn.net Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=lwn.net Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=lwn.net header.i=@lwn.net header.b="gA4n+9iy" DKIM-Filter: OpenDKIM Filter v2.11.0 ms.lwn.net 2A81D408F6 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=lwn.net; s=20201203; t=1791845235; bh=L5mVvdQ7SkcC0vgiumo1qpu0fc0kTH3GV33hr4acS+4=; h=From:To:Cc:Subject:In-Reply-To:References:Date:From; b=gA4n+9iyyKJZ2fnZ6ppvWQIE4dReKGeDhFWqVP5fc+jNjukORsCXVqBuYOOZCOemX alOdpbYBKT4SHBTuO4piW53z8ND2J6zpAWB2SA4Bw3o4k8EKhuacCKmCO3UeCqwyi+ C+Tlfyms9DLZF215UNzHn4X/NXIaGrQhjPU7cZj439cvFKdT2pu1TgvaCk2zBk2/Kf NIOd6jixwRV0hgGYVv0gOVmg1eYWAf2f0b5Y8vgPgEHkuLvtTALclxu53uccvka3CE P1kzZFde95yUhR9tSJRgvByqt24krpYEQX/tvgdrZuYBjqb6ICVjC95veHW1zyBclY +3x6SF48m9w1A== Received: from localhost (unknown [IPv6:2601:280:4600:814::1fe]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange ECDHE (prime256v1) server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by ms.lwn.net (Postfix) with ESMTPSA id 2A81D408F6; Mon, 12 Oct 2026 22:47:15 +0000 (UTC) From: Jonathan Corbet To: Sasha Levin , workflows@vger.kernel.org, ksummit@lists.linux.dev Cc: linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, Shuah Khan , Randy Dunlap , Mark Brown , Theodore Ts'o , Laurent Pinchart , Greg Kroah-Hartman , Leon Romanovsky , Konstantin Ryabitsev , Thorsten Leemhuis , "Michael S . Tsirkin" , Sasha Levin Subject: Re: [PATCH v2 0/5] agents: add skills for Fixes tags, stable tags, similar bugs, and commit messages In-Reply-To: <20261012213452.1863248-1-sashal@kernel.org> References: <20261012213452.1863248-1-sashal@kernel.org> Date: Mon, 12 Oct 2026 16:47:14 -0600 Message-ID: <87zewiy1sd.fsf@trenco.lwn.net> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain Sasha Levin writes: > At the Maintainers Summit, Ted asked whether the stable trees have a way > to deal with incorrect Fixes tags. Hannes estimated that 15-20% of them > are wrong, often because the author ran git blame and took the first > commit that touched the line [1]. We use LLM workflows to find the > commit that actually introduced a bug, and others asked us to share > them. > > This series adds them as agent skills under agents/skills/, together > with a skill for writing commit messages: Time to argue for a more fuchsia shade of mauve without actually getting into the substance of what you're doing...:) I wonder about the top-level agents/ directory. If we regard this material as documentation, perhaps the "skills" should go there too? As readable text, they might just help to improve human skills as well, assuming we think we still need those. Under Documentation, they could be built into the rendered docs and made more widely available. Otherwise, if this is primarily a development tool, perhaps under tools/ makes sense? I lack strong opinions here, but figured I would ask the question. jon