prm
Judge every CI run and matrix leg, merge human-authorized PRs when green, then close the issue and Mind task and clean the worktree.
Skill by PyAutoLabs
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/pyautolabs-prm
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, data, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/prm
What's inside
- Skill name
prm- Description
- Judge every CI run and matrix leg, merge human-authorized PRs when green, then close the issue and Mind task and clean the worktree. Use for /prm or merge-and-close requests; preserve library-first and data guards.
- License
- MIT
- Instructions
- 20 lines in SKILL.md · view on GitHub
Files (6)
- SKILL.md
- closeout.md
- freeze.md
- mcp.md
- prm.md
- reference.md
SKILL.md (first lines)
# /prm — PR, CI green, then merge, then close the task out Follow [`prm.md`](prm.md) exactly; gh + close-out mechanics in [`reference.md`](reference.md). Composition door — it owns no agent and re-derives nothing: merge gates from `/ship_*`, the CI verdict from GitHub Actions, the lifecycle from PyAutoMind, the render from `/intake`. Typing `/prm` authorizes the **whole** close-out, so it runs to the end without asking again — but still refuses on red, pending, conflicting, an unmerged upstream library PR or sibling branch, and asks once before deleting a worktree holding irreplaceable data products. The shipping session also runs it in-turn for a declared `notify` / witnessed `glance` task its approved plan authorized (`prm.md` "Tiered merge"). Read only the applicable step/environment from linked references, not all files. Reuse unchanged instructions already loaded; follow [CONTEXT.md](../CONTEXT.md) for bounded output and repository paths.
From PyAutoLabs/PyAutoBrain, MIT.
More from PyAutoLabs/PyAutoBrain
- 0.559score
batch
PyAutoLabs
Compose the next unattended batch via the Batch Agent — a BatchDecision planned against the slot's review-minute budget, with backpressure and lane rules.
SkillAFreshness: AClaude Code +9 - 0.557score
issue-cleanup
PyAutoLabs
Reconcile the PyAuto GitHub issue trackers — audit open issues against Mind completion records and merged PRs, bucket them, close only what a human confirms.
SkillAFreshness: AClaude Code +9 - 0.556score
profiling
PyAutoLabs
Plan PyAutoLens performance campaigns, ingest fresh profiling results, or triage profiling drift through the PyAutoBrain Profiling Agent without running…
SkillAFreshness: AClaude Code +9 - 0.556score
docs
PyAutoLabs
Start PyAutoLabs documentation, tutorial, notebook, example, or narrative-prose work through the Brain development workflow with the docs work type fixed.
SkillAFreshness: AClaude Code +9 - 0.556score
eyes
PyAutoLabs
Run the visualization review loop via the Eyes Agent — survey a figure surface, render via its gallery harness, review figures with the human, route critiques…
SkillAFreshness: AClaude Code +9 - 0.556score
feedback
PyAutoLabs
Draft user-reviewed feedback on using PyAutoLabs software and assistants (goals, successes, friction, evidence).
SkillAFreshness: AClaude Code +9 - 0.556score
health
PyAutoLabs
Use the single PyAuto health door for readiness assessment, validation sweeps, active-work status, release-run status, or worktree status through the Brain…
SkillAFreshness: AClaude Code +9 - 0.556score
intake
PyAutoLabs
Turn raw PyAutoLabs ideas, bug reports or loose requirements into classified, sized PyAutoMind prompt files via the Intake Agent; also files a human review of…
SkillAFreshness: AClaude Code +9 - 0.556score
board
PyAutoLabs
Read the PyAutoBrain agents/workflows directory, overnight exceptions and maintenance via Pages or `pyauto-brain board`; read-only.
SkillAFreshness: AClaude Code +9 - 0.556score
hygiene
PyAutoLabs
Audit and prioritise code-quality upkeep — slow tests/scripts/imports, CLI noise, dependency-cap drift, stale API docs, workspace doc blocks, git and…
SkillAFreshness: AClaude Code +9 - 0.556score
community
PyAutoLabs
Hear and answer the PyAuto community via the Community Agent — scan Discussions and all repos for threads awaiting a reply, triage, draft human-approved…
SkillAFreshness: AClaude Code +9 - 0.556score
cortex
PyAutoLabs
Check in on the science via the Cortex Agent — 'cortex pull' on the laptop (pull each project's runs) and 'cortex checkin' anywhere (stamp, re-render, push…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Oct 23, 2026 (6 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/PyAutoLabs/PyAutoBrain
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from PyAutoLabs
- 0.559score
batch
PyAutoLabs
Compose the next unattended batch via the Batch Agent — a BatchDecision planned against the slot's review-minute budget, with backpressure and lane rules.
SkillAFreshness: AClaude Code +9 - 0.557score
issue-cleanup
PyAutoLabs
Reconcile the PyAuto GitHub issue trackers — audit open issues against Mind completion records and merged PRs, bucket them, close only what a human confirms.
SkillAFreshness: AClaude Code +9 - 0.556score
docs
PyAutoLabs
Start PyAutoLabs documentation, tutorial, notebook, example, or narrative-prose work through the Brain development workflow with the docs work type fixed.
SkillAFreshness: AClaude Code +9 - 0.556score
cortex
PyAutoLabs
Check in on the science via the Cortex Agent — 'cortex pull' on the laptop (pull each project's runs) and 'cortex checkin' anywhere (stamp, re-render, push…
SkillAFreshness: AClaude Code +9 - 0.556score
community
PyAutoLabs
Hear and answer the PyAuto community via the Community Agent — scan Discussions and all repos for threads awaiting a reply, triage, draft human-approved…
SkillAFreshness: AClaude Code +9 - 0.556score
eyes
PyAutoLabs
Run the visualization review loop via the Eyes Agent — survey a figure surface, render via its gallery harness, review figures with the human, route critiques…
SkillAFreshness: AClaude Code +9
Cite this page
prm skill. Agent Mart. https://agentmart.dev/skills/pyautolabs-prm (last updated 2026-10-24)