By ppryde
PR comment review, categorisation, prioritisation and resolution. No heresy goes unaddressed.
A personal collection of Claude Code skills for serious engineering work — from PR review to architectural auditing. Built for real workflows, shared because they might help yours.
Three plugins, each with a distinct purpose:
| Plugin | Purpose |
|---|---|
| Puritan | Architectural doctrine enforcement — plan patterns, audit code, author rules |
| Tribunal | PR review workflow — fetch, triage, validate, action, and resolve GitHub PR comments |
| email-absolution | HTML email auditing and generation — doctrines, visitation, and absolution |
You can also install via Claude Code's plugin commands. From within a Claude Code session:
/plugin marketplace add ppryde/pip-skills
/plugin install puritan@ppryde/pip-skills
/plugin install tribunal@ppryde/pip-skills
/plugin install email-absolution@ppryde/pip-skills
Or from the terminal CLI:
# Install all plugins
claude plugin install puritan@ppryde/pip-skills
claude plugin install tribunal@ppryde/pip-skills
claude plugin install email-absolution@ppryde/pip-skills
After installing, the skills are available as slash commands:
/puritan:covenant — architecture planning and pattern selection
/puritan:inquisition — audit codebase against configured doctrines
/puritan:scriptorium — author new architecture doctrines
/tribunal:reckoning — triage and action GitHub PR review comments
/email-absolution:elder — email planning, Q&A, and config setup
/email-absolution:visitation — audit an email template against doctrine
/email-absolution:scribe — generate a template correct by construction
These skills are built around two ideas:
1. Architecture should be codified, not tribal knowledge. Architectural decisions that live only in people's heads — or in an ADR doc nobody reads — don't survive team turnover or code reviews. Puritan turns those decisions into auditable doctrine files that Claude can check your code against, commit by commit.
2. PR review is a workflow, not a scroll. Bot reviewers and human reviewers leave dozens of comments across multiple rounds. Tribunal treats this as a structured workflow: fetch everything, categorise by source and type, validate each comment against the actual current code, propose fixes, apply them with your approval, and resolve the threads.
All plugins operate in the voice of a deeply principled but self-aware Puritan inspector. Violations are heresies. Fixes are absolution. The codebase is the sanctum.
The persona is flavour, not a barrier to clarity — every verdict is technically precise and actionable. The Witchfinder is dramatic, not obscure.
settings.snippets.json at the repo root contains custom spinner verbs that replace Claude Code's default "Thinking…" messages with in-character Witchfinder flavour while the skills are running.
To use them, copy the file into your Claude Code settings directory:
cp settings.snippets.json ~/.claude/settings.snippets.json
If you already have a settings.snippets.json, merge the spinnerVerbs block into it manually.
The
mode: "replace"setting replaces all default spinner verbs with these. If you'd prefer to add them alongside the defaults, change it to"append".
Issues and PRs welcome. If you extend a doctrine or add a new one, the Scriptorium skill can help you author it to the required standard.
A personal collection of Claude Code skills for serious engineering work — from PR review to architectural auditing. Built for my own workflows, shared because they might help yours.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub ppryde/pip-skills --plugin tribunalRighteous HTML email construction. Doctrines, visitation, and absolution for the transactional email sanctum.
Architectural doctrine enforcement through composable lenses. Covenant, Inquisition, and Scriptorium.
Review pull requests with structured analysis and approve with confidence
PRのレビュー報告書を作成する。bugや脆弱性の調査だけでなく、exportされた対話コンテキスト・PR概要欄・実装されたコードの整合性を確認し、実装者の正気を疑う。
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.