<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>pdlc on tomrochette.com</title>
    <link>https://tomrochette.com/tags/pdlc/</link>
    <description>Recent content in pdlc on tomrochette.com</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <managingEditor>tom@tomrochette.com (Tom Rochette)</managingEditor>
    <webMaster>tom@tomrochette.com (Tom Rochette)</webMaster>
    <copyright>© 2026 Tom Rochette</copyright>
    <lastBuildDate>Sun, 04 Oct 2026 07:44:33 -0400</lastBuildDate><atom:link href="https://tomrochette.com/tags/pdlc/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>What I&#39;ve built and what I need: August 2026</title>
      <link>https://tomrochette.com/what-ive-built-and-what-i-need/2026-08/</link>
      <pubDate>Sun, 04 Oct 2026 00:00:00 +0000</pubDate>
      <author>tom@tomrochette.com (Tom Rochette)</author>
      <guid>https://tomrochette.com/what-ive-built-and-what-i-need/2026-08/</guid>
      <category>what-ive-built-and-what-i-need</category><category>personal-update</category><category>llm</category><category>ai-agents</category><category>automation</category><category>sdlc</category><category>pdlc</category><category>workflows</category><category>fully-ai-generated</category><category>llm=deepseek-v4.1-flash</category>
      <description>&lt;p&gt;The headline this month was &lt;strong&gt;the product-side counterpart to the SDLC: a full PDLC skill set that carries an idea from discovery through measurement&lt;/strong&gt;.&#xA;August also realigned the verification skills around non-overlapping roles, added several new pipeline phases, and completed the ISO/IEC 25010 audit set.&#xA;The month came to 61 commits, over 500 files changed, and 30 new skills.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;What I Have Been Working On&#xA;    &lt;div id=&#34;what-i-have-been-working-on&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#what-i-have-been-working-on&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;&lt;strong&gt;Shipped the &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/pdlc/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;PDLC&lt;/a&gt; pipeline.&lt;/strong&gt;&#xA;This was last month&amp;rsquo;s open need, and it is now a self-contained product development lifecycle that wraps the engineering one.&#xA;It covers discovery, validation, strategy, definition, launch, and measurement, with a proceed, pivot, or kill gate at every phase.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/pdlc/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;PDLC&lt;/a&gt; is the only slash command; the 31 phase and cross-cutting sub-skills live under &lt;code&gt;skills/pdlc/skills/&lt;/code&gt; and the orchestrator loads them on demand.&#xA;Artifacts live under &lt;code&gt;.pdlc/&lt;/code&gt;, mirroring the &lt;code&gt;.sdlc/&lt;/code&gt; conventions: a shared reference file, a &lt;code&gt;PDLC_DIR&lt;/code&gt; fallback, a state file, and a revision mode.&#xA;Definition is the seam where the product work hands the settled what and why to SDLC.&#xA;Two supporting skills came with it, &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/create-roadmap/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;create-roadmap&lt;/a&gt; and &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/review-roadmap/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;review-roadmap&lt;/a&gt;, and &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/identify-feature-opportunities/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;identify-feature-opportunities&lt;/a&gt; generates and ranks new ideas from the code surface.&lt;/p&gt;&#xA;&lt;p&gt;&lt;strong&gt;Realigned the verification skills.&lt;/strong&gt;&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/validate-pr/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;validate-pr&lt;/a&gt;, &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/verify-pr/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;verify-pr&lt;/a&gt;, and &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/review-pr/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;review-pr&lt;/a&gt; had overlapping mandates, so I split them into three questions: validate-pr asks whether the change builds the right product, verify-pr asks whether the product is built right using runtime proof, and review-pr judges code craft from static reading alone.&#xA;The new &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/review-requested-prs/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;review-requested-prs&lt;/a&gt; orchestrator runs the three across the PRs waiting on me and skips any step already done for the current commit using SHA markers.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/analyze-test-coverage/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;analyze-test-coverage&lt;/a&gt; became its own skill for reporting introduced tests, change coverage, and uncovered code, and &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/review-pr-full/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;review-pr-full&lt;/a&gt; chains the whole review into one pass.&lt;/p&gt;&#xA;&lt;p&gt;&lt;strong&gt;Added SDLC phases and artifacts.&lt;/strong&gt;&#xA;A new &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/validate-assumptions/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;validate-assumptions&lt;/a&gt;/&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/review-assumption-validation/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;review-assumption-validation&lt;/a&gt; phase collects the assumptions made during design, runs the cheapest experiment that could invalidate each risky one, and blocks implementation when an assumption fails.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/create-lifecycle/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;create-lifecycle&lt;/a&gt;/&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/review-lifecycle/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;review-lifecycle&lt;/a&gt; document how a resource&amp;rsquo;s states, transitions, and retention change over time, and &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/create-domain-model/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;create-domain-model&lt;/a&gt;/&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/review-domain-model/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;review-domain-model&lt;/a&gt; became standalone so a domain can be understood before solutioning.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/create-project/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;create-project&lt;/a&gt;/&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/review-project/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;review-project&lt;/a&gt; fill the context files for a new repository, and &lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/create-question/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;create-question&lt;/a&gt;/&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/review-question/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;review-question&lt;/a&gt; record open questions with what they block.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/create-cli-design/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;create-cli-design&lt;/a&gt; settles a feature&amp;rsquo;s command surface as a companion artifact to requirements.&#xA;Generated artifacts carry a &lt;code&gt;session_link&lt;/code&gt; so a reviewer can reopen the session that produced them, &lt;code&gt;create-*&lt;/code&gt; auto-dispatches its &lt;code&gt;review-*&lt;/code&gt; in a subagent, and outcome files list the artifacts a phase produced.&#xA;A single HTML slide deck now presents the whole SDLC family.&lt;/p&gt;&#xA;&lt;p&gt;&lt;strong&gt;Completed the ISO/IEC 25010 audit set.&lt;/strong&gt;&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/audit-sdlc/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;audit-sdlc&lt;/a&gt; is now the coordinator for the &lt;a href=&#34;https://en.wikipedia.org/wiki/ISO/IEC_25010&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=en.wikipedia.org&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;ISO/IEC 25010&lt;/a&gt; quality model, with a mapping table from each characteristic to a skill.&#xA;One skill now covers each remaining characteristic: functional suitability, performance efficiency, compatibility, usability, reliability, maintainability, and portability, alongside the existing security and observability audits.&lt;/p&gt;&#xA;&lt;p&gt;&lt;strong&gt;Shipped general-purpose skills.&lt;/strong&gt;&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/devils-advocate/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;devils-advocate&lt;/a&gt; argues the strongest case against an idea, plan, or decision before you commit.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/gh-stack/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;gh-stack&lt;/a&gt; manages stacked pull requests.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/post-slack-message/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;post-slack-message&lt;/a&gt; posts or threads a Slack message.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/stakeholder-announcement/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;stakeholder-announcement&lt;/a&gt; drafts and posts infrastructure updates to stakeholder channels.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/agents-section-daily-refresh/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;agents-section-daily-refresh&lt;/a&gt; runs the daily curation of the agent-maintained section of this blog.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/sync-articles/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;sync-articles&lt;/a&gt; brings a batch of articles into conformance with the writing rules.&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/handle-pr-author-feedback/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;handle-pr-author-feedback&lt;/a&gt; (renamed from &lt;code&gt;handle-pr-feedback&lt;/code&gt;) verifies that an author&amp;rsquo;s new commits answer your review comments.&lt;/p&gt;&#xA;&lt;p&gt;&lt;strong&gt;Gated GitHub writes and reworked tooling.&lt;/strong&gt;&#xA;A &lt;code&gt;should-post-to-github&lt;/code&gt; script now gates every GitHub content write, and the PR skills default to not posting, so a comment or merge only happens when &lt;code&gt;--post&lt;/code&gt; is passed.&#xA;SDLC worktrees moved to &lt;code&gt;/tmp/sdlc/&amp;lt;owner&amp;gt;/&amp;lt;repo&amp;gt;/&amp;lt;issue&amp;gt;&lt;/code&gt;, and &lt;code&gt;~/.sdlc/**&lt;/code&gt; and &lt;code&gt;/tmp/sdlc/**&lt;/code&gt; are pre-approved in the agent CLI so unattended runs are not stopped by a prompt.&#xA;Script references moved to &lt;code&gt;~/.agents/scripts/&lt;/code&gt;, the audit and find skills switched from grep to ripgrep, and &lt;code&gt;CLAUDE.md&lt;/code&gt; and &lt;code&gt;.claude&lt;/code&gt; were replaced by &lt;code&gt;AGENTS.md&lt;/code&gt; and &lt;code&gt;.agents&lt;/code&gt; across the library.&lt;/p&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tightened conventions.&lt;/strong&gt;&#xA;&lt;a href=&#34;https://github.com/tomzx/agents/blob/main/skills/create-article/SKILL.md&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;create-article&lt;/a&gt; now requires naming the referent rather than leaving a vague it, and the 2-5 link cap on its See also sections was removed.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;What I Currently Need&#xA;    &lt;div id=&#34;what-i-currently-need&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#what-i-currently-need&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;I did not write this entry at the time, so I have no record of what I needed in August and am stating that plainly rather than reconstructing a list I cannot trust.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;See also&#xA;    &lt;div id=&#34;see-also&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#see-also&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/what-ive-built-and-what-i-need/2026-07/&#34; &gt;What I&amp;rsquo;ve built and what I need: July 2026&lt;/a&gt; - the previous entry in this series; August delivers the PDLC pipeline it asked for.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/the-self-evolving-repository/&#34; &gt;The Self-Evolving Repository&lt;/a&gt; - the end-to-end automation vision that the SDLC and PDLC pipelines now serve.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/loops-as-files/&#34; &gt;Loops as Files&lt;/a&gt; - the scheduling layer that runs skills unattended, which the daily refresh and PR skills rely on.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/iterating-on-agent-skills/&#34; &gt;Iterating on Agent Skills&lt;/a&gt; - how the skill library changes over time, of which this month&amp;rsquo;s 30 additions are one step.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;../../a-pull-request-is-a-claim-not-evidence/index.md&#34; &gt;A Pull Request Is a Claim, Not Evidence&lt;/a&gt; - the reasoning behind splitting verification into a right-product check and a built-right check.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;References&#xA;    &lt;div id=&#34;references&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#references&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://github.com/tomzx/agents&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;agents&lt;/a&gt; - the skill library where the PDLC pipeline, the verification realignment, and the audit set landed.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://en.wikipedia.org/wiki/ISO/IEC_25010&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=en.wikipedia.org&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;ISO/IEC 25010&lt;/a&gt; - the quality model the audit skills now map one to one.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://github.com/TomzxCode/ghx&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;ghx&lt;/a&gt; - the GitHub CLI used across the review and feedback skills.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;</description>
      
    </item>
    
  </channel>
</rss>
