codex-pr
openbooklet.com/s/codex-propenbooklet.com/s/[email protected]GET /api/v1/skills/codex-prOpen or update a pull request for the current branch with an independently drafted and reviewed PR_AGENTDESC.md. Use whenever the user asks Codex to open or draft a pull request in a tbhb repository, or when a completed task should end in a pull request. Routes later CI work to codex-watch-pr and codex-fix-pr.
Query a Claude Code transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends. The tool reads the file line by line and reports every failure and repeated tool call by line number. Use this skill when the user asks for a retrospective on a past session, or hands over a transcript path with a question about it.
Query a Codex transcript without reading it into context, then write the retrospective to disk so it remains available after the session ends. The tool reads the file line by line and reports every failure and repeated tool call by line number. Use this skill when the user asks for a retrospective on a past session, or hands over a transcript path with a question about it.
Squash merge a pull request. The commit message comes from this workflow rather than from GitHub, whose own version concatenates every commit on the branch into text no linter ever reads. A briefing script prints the published description, every commit the squash collapses, and the diffstat, then leaves a SQUASH_AGENTMSG skeleton whose body the caller writes. Review, the commit-msg gates, and an operator confirmation all run before the merge. Use this whenever the user asks to merge or land a pull request, including one nobody here authored such as a dependency bump.
Review the squash commit message drafted in SQUASH_AGENTMSG against every commit it collapses, as an independent agent. Its distinct question is coverage. One message has to stand for a whole stack of commits, and this review asks what the collapse lost. Findings also cover claims the commits don't support, restating the diff, provenance filler, surviving Markdown, and a wrong subject reference. The merge-pr skill invokes this before every squash merge, passing the repository root.
Wait for a pull request's checks to settle in one long-running command, then report passed, skipped, and failed jobs with run links. Use whenever the user asks Codex to watch a pull request or wait for CI, and whenever another workflow needs the result before continuing.
Write or revise PR_AGENTDESC.md from the branch, its commits, and the repository template, then run the mechanical validator until it reports nothing. Use as a delegated writer from codex-pr, codex-fix-pr, or codex-merge-pr. Pass review findings or branch-drift notes in the task.
Reword one settled document so its prose lint passes, without changing meaning or any other file. The codex-fix-prose skill delegates this task with no inherited conversation context.
Clear the vale and cspell findings on a document whose content is already settled. A forked writer does the rounds and an independent reviewer reads the result, so the finding text never reaches this session. Takes the file plus the lint command that judges it. Use it when a draft is written but its prose gates are still red, or when a lint task has come back with findings more than once.
Settle the conflicts a stopped rebase left behind. Mechanical ones resolve without asking and the rest arrive with the evidence in front of you. Every path gets a classification first. An append-only sorted list becomes the verified union of both sides. A generated file takes one side whole and waits for its generator. Everything else is a real disagreement with what each side changed printed beside it. The rebase skill calls this at every stop. Use it directly whenever a rebase or cherry-pick stops on a conflict and the user asks to resolve it.
Review a drafted commit message in COMMIT_AGENTMSG against the staged diff, as an independent agent, for the things mechanical linting can't see: claims the diff doesn't support, counting, provenance filler, restating the diff, subject mood and bounds, plain-text form, and whether the staged change is one logical change. The commit skill invokes this before every commit, passing the repository root.
Review a drafted pull request description in PR_AGENTDESC.md against the branch it would publish, as an independent agent, for what mechanical checking can't see. Covers claims the diff doesn't support, counting, provenance filler, restating the diff, a title describing one commit rather than the branch, and whether the branch is one coherent change. The pr skill invokes this before opening every pull request, passing the repository root.
Reviews what a prose fix did to a document. The fix-prose skill invokes this by name.
Auto-indexed from tbhb/vale-ai-tells
Are you the author? Claim this skill to take ownership and manage it.
Related Skills
graceful-error-recovery
Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.
audience-aware-communication
Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.
Refactoring Expert
Expert in systematic code refactoring, code smell detection, and structural optimization. Use PROACTIVELY when encountering duplicated code, long methods, complex conditionals, or any code quality issues. Detects code smells and applies proven refactoring techniques without changing external behavior.
Research Expert
Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.
clarify-ambiguous-requests
Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.
structured-step-by-step-reasoning
Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.