pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks required tests and docs, then writes Description / Proofs / Fixes.
- Installs
- 104
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/plastic-labs/honcho --skill pre-pr- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads pre-pr automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Pre-PR checklist
Do this after the change works, before anyone opens the GitHub PR. Output is a filled template body — do not create the PR.
The template lives at .github/pull_request_template.md. Do not add extra sections.
1. Classify the diff
git diff main...HEAD --stat
Pick one primary kind: bug, feature, docs. Then decide layers:
| Surface touched | Required |
|---|---|
src/ (non-prompt) | unit tests under the matching tests/ tree |
| deriver / dialectic / dreamer / LLM path | unit + consider live-llm (tests/live_llm) |
| queue, config hierarchy, multi-turn, SDK contract | unified (uv run python -m tests.unified.run) |
/v3 HTTP or deriver queue behavior | /verify skill (runtime, not just pytest) |
public API, SDK exports, config.toml / settings, mintlify docs/ | documentation in the matching file |
Skip a layer only with a one-line reason (e.g. "docs-only", "comment-only"). "When appropriate" is not a skip.
Invoke /verify when the runtime surface moved. Do not restate that skill here.
Lint/type before claiming tests are green: uv run ruff check src/ → uv run basedpyright → the pytest command for the layer.
2. Proofs
Collect evidence that belongs in the PR, not in the commit:
- command + pass/fail for what you ran
- a log snippet, screenshot, or file path that shows the new behavior
- for bugs: the failing case before vs after, if you have it
If /verify ran, the proofs are that session's output. Do not invent green runs.
3. Write the body
Fill the description and proofs portion of the pull request description template.
If there is a related GitHub issue, link it with Fixes #<N>.
FAQ
What does the pre-pr skill do?
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks required tests and docs, then writes Description / Proofs / Fixes.
How do I install pre-pr?
Run npx skills add https://github.com/plastic-labs/honcho --skill pre-pr in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/pre-pr/ (personal) or .claude/skills/pre-pr/ (project).
Which AI agents can use pre-pr?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is pre-pr safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains pre-pr?
It is published by plastic-labs in plastic-labs/honcho. It has 104 recorded installs.
More from plastic-labs/honcho
honcho-integration
plastic-labs/honcho
Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.
honcho-cli
plastic-labs/honcho
Inspect and debug Honcho workspaces via the honcho CLI. Use when investigating peer representations, memory state, session context, or dialectic quality — any task that requires introspection of a Honcho deployment, including verifying that a recall/record memory loop is actually working.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.