Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Author a new Rigor plugin, choosing plugins/ for production support or examples/ for a contract walkthrough.
$ npx skills add rigortype/rigor --skill rigor-plugin-author -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rigortype/rigor rigor-plugin-author --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/rigortype/rigor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/rigor-plugin-author .claude/skills/rigor-plugin-author && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "rigor-plugin-author" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-plugin-author into .claude/skills/rigor-plugin-author/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-plugin-author", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-plugin-authorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add rigortype/rigor --skill rigor-plugin-author -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rigortype/rigor rigor-plugin-author --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rigortype/rigor.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/rigor-plugin-author .agents/skills/rigor-plugin-author && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rigor-plugin-author" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-plugin-author into .agents/skills/rigor-plugin-author/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-plugin-author", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rigortype/rigor --skill rigor-plugin-author -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rigortype/rigor rigor-plugin-author --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rigortype/rigor.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/rigor-plugin-author .cursor/skills/rigor-plugin-author && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "rigor-plugin-author" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-plugin-author into .cursor/skills/rigor-plugin-author/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-plugin-author", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/rigortype/rigor.git --path .claude/skills/rigor-plugin-author--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add rigortype/rigor --skill rigor-plugin-author -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rigortype/rigor rigor-plugin-author --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rigortype/rigor.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/rigor-plugin-author .gemini/skills/rigor-plugin-author && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "rigor-plugin-author" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-plugin-author into .gemini/skills/rigor-plugin-author/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-plugin-author", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install rigortype/rigor rigor-plugin-authorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add rigortype/rigor --skill rigor-plugin-author -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/rigortype/rigor.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/rigor-plugin-author .github/skills/rigor-plugin-author && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "rigor-plugin-author" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-plugin-author into .github/skills/rigor-plugin-author/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-plugin-author", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rigortype/rigor --skill rigor-plugin-author -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install rigortype/rigor rigor-plugin-author --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rigortype/rigor.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/rigor-plugin-author .opencode/skills/rigor-plugin-author && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "rigor-plugin-author" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-plugin-author into .opencode/skills/rigor-plugin-author/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-plugin-author", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
rigor-plugin-authorAuthor a new Rigor plugin, choosing plugins/ for production support or examples/ for a contract walkthrough.
Rigor Plugin Author is an agent skill from rigortype/rigor. Author a new Rigor plugin, choosing plugins/ for production support or examples/ for a contract walkthrough. Use when extending Rigor for a DSL, framework, or macro; not for editing an existing plugin or the analyzer engine.
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/01-requirements-and-templates.md`, `references/02-scaffold-walker-demo.md` and `references/03-test-and-ship.md`).
It sits in Development. The repository describes itself as: Inference-first static analysis for Ruby. The licence is MPL-2.0.
2 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit c7b6b60. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
makegitgemnixbundleFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Rigor Plugin Author loads about 3.3k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 1,450 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
(`Dotenv.load(path)` call), Q2=E (reads `.env` file), Q3=A (known finite set of variable names), Q4=B (error on missingAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from rigortype/rigor at commit c7b6b60, republished under its MPL-2.0 licence (© rigortype). 1,450 words, ~3,311 tokens.
.claude/skills/rigor-plugin-author/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.Decide placement first (Phase 0 below), then load the four reference files in order. All commands run through the Nix Flake (nix develop --command ...) per AGENTS.md.
Trigger this skill when the user requests a new plugin: "Create a Rigor plugin that catches Y", "Extend Rigor to understand our DSL Z", "Write a plugin similar to rigor-units but for currency", or Japanese equivalents.
Do NOT trigger for:
plugins/<id>/ or examples/<id>/ — these are ordinary edit tasks; modify the plugin in place and add a changelog.d/ fragment.lib/rigor/inference/ / lib/rigor/analysis/ / lib/rigor/plugin/ — that's core development.| Signal | Lands under |
|---|---|
| Real gem / framework (Rails, RSpec, dry-rb, Sorbet, Devise, Sidekiq, GraphQL, …) | plugins/<id>/ |
| User's in-house DSL on a real project | plugins/<id>/ |
Installed via Gemfile, activated in .rigor.yml against real source | plugins/<id>/ |
| Deliberately fictional / virtual domain (tiny Lisp, units-of-measure, fake route YAML) | examples/<id>/ |
| Authored to demonstrate one architectural surface of the contract | examples/<id>/ |
| Referenced by the handbook / ADRs as a teaching reference | examples/<id>/ |
Default to plugins/. The walkthroughs under examples/ are a curated set; adding to that tree requires a positive teaching reason.
Mechanical differences: production specs live at spec/integration/plugins/<id>_plugin_spec.rb; walkthrough specs at spec/integration/examples/<id>_plugin_spec.rb. Both auto-include spec/integration/support/plugin_helpers.rb. RuboCop excludes plugins/**/* and examples/**/* but lints the specs.
Phase 0's table assumes you are a Rigor maintainer authoring directly inside the monorepo. The placement table above applies to monorepo-internal authoring only — typical paths: a new bundled plugin Rigor team adds to support a real framework, or a new examples/ walkthrough teaching an architectural surface.
If you are not a Rigor maintainer (i.e. you don't have commit rights to rigortype/rigor), or you are authoring a plugin in response to an external author's proposal, the plugin's home is outside this monorepo per ADR-31 (project-wide contribution policy). Note: a new bundled plugin is treated as a sweeping change under ADR-31 WD1 and follows the issue-first path; small bug fixes to existing bundled plugins are minor PRs and welcome directly per ADR-31 WD1's minor-PR path:
| Situation | Path |
|---|---|
| Authoring a plugin you'll consume yourself | Third-party rigor-<gem> gem in your own repo depending on gem "rigortype" (ADR-31 WD4). For FFI bindings, also see rigor-ffi-plugin-author which adds an upstream coverage-assessment phase to talk users out of plugin work when core suffices. |
| Want the plugin officially bundled with Rigor | File an issue at the rigor repo with the ADR-31 WD2 fields: wrapped gem identity, evidence of community adoption (ADR-31 WD3 keeps the criterion deliberately vague), pointer to your working third-party plugin (as reference implementation), upstream-effort confirmation. The Rigor team re-implements from scratch; you are credited via Co-authored-by: on the implementation commit(s). |
| You ARE a Rigor maintainer and the plugin's authorship matches the bundled-plugins discipline | Proceed with Phase 0's table above (monorepo placement). |
Why there is no PR path for new bundled plugins. A new bundled plugin defines ecosystem identity (plugins/rigor-foo/ carries an implicit "this is the official rigor plugin for foo" signal), a project-governance concern beyond per-PR review. ADR-31 WD1 classifies new bundled plugins as sweeping changes that take the issue-first path; the Rigor team implements with Co-authored-by: attribution on the proposer. Bug fixes to existing bundled plugins are minor PRs and follow ADR-31 WD1's direct-PR path — they don't need this SKILL's full pipeline either, just clear-scope edits. This SKILL's procedural shape (Phases 1–10 below) supports both the monorepo path and the third-party-repo path identically — only the destination directory tree differs.
Load each reference when you reach its phase. The phases assume prior context, so backwards skipping is fine but forward skipping leaves gaps.
| Module | Read | Covers | Output of this module |
|---|---|---|---|
| 1 | references/01-requirements-and-templates.md | Phases 1–2. Five-question scope check (trigger surface / look at / prove / diagnostic / config). Picks ADR-16 macro-substrate tier (A/B/C, declarative) or a node_rule template from six worked examples. | Five Q&A answers + one template name from the table. |
| 2 | references/02-scaffold-walker-demo.md | Phases 3–5. Directory tree, gemspec, plugin class skeleton, per-template node_rule patterns (engine owns the walk; node_file_context / NodeContext for two-pass / lexical context), calling the target library directly instead of reimplementing it (ADR-39: Plugin::Inflector, Base.suggest, the plugins_isolation: strategy), IoBoundary + cache producer rule (ADR-60 WD3 record-and-validate: read inside the block, declare watch: for directory globs; producer_value / producer_error for the lazy-load + error surface), demo project with tmp/-anchored cache + per-demo .gitignore. | Working plugin directory + runnable demo/ whose rigor check diagnostic stream matches expectations. |
| 3 | references/03-test-and-ship.md | Phases 6–10. RSpec integration helpers, README sections, changelog fragment, local gate and CI expectations, commit subject convention. | Passing integration spec + README + changelog fragment + make verify-changed + green CI on the Draft PR + one commit. |
| 4 | references/04-appendix.md | Side material. Common pitfalls (top 10), real-Rails alignment for rigor-rails-* plugins, post-ADR-9 services.fact_store cross-plugin pattern, reading list, closing checklist. | Reference-only — no fixed output. Consult per the surface the plugin touches. |
Map the Phase 1 answers to one of these:
ADR-16 substrate (declarative, no walker):
Tier A → plugins/rigor-sinatra/ (block-as-method)
Tier B → plugins/rigor-devise/ (trait registry)
Tier C → plugins/rigor-dry-struct/ (heredoc template)
Node-rule templates (engine owns the walk, ADR-37):
Q1=A/B Q2=A Q3=A Q5=C → examples/rigor-deprecations/ (~80 lines; config-driven)
Q1=A Q2=A Q3=E Q5=A/B → examples/rigor-lisp-eval/ (literal AST recursion)
Q1=D Q2=B Q3=C Q5=A → examples/rigor-units/ (local-variable flow)
Q1=C/E Q2=C Q3=A Q5=A/B → plugins/rigor-statesman/ (two-pass collect → validate)
Q1=B Q2=A/B Q3=B Q5=C → examples/rigor-pattern/ (asks Scope#type_of)
Q1=A/B/C Q2=E Q3=A/D Q5=C/D → examples/rigor-routes/ (IoBoundary + cache)If the requirement fits neither substrate nor template, stop and ask the user — the current plugin contract may not yet expose what they need. Check the per-library survey before inventing a workaround.
The plugin is shippable when all of these hold:
bundle exec exe/rigor check against the plugin's demo/ prints the diagnostic stream documented in the plugin's README.md § "What the plugin recognises" — verbatim, no drift.spec/integration/plugins/<id>_plugin_spec.rb (or examples/) covers every diagnostic shape the plugin emits, passing in CI.make verify-changed passes locally and CI is green on the Draft PR: rspec 0 failures, rubocop 0 offenses on the spec file (the plugin source itself is excluded from rubocop), rigor check lib baseline unchanged.git status is clean (tmp/-anchored cache + per-demo .gitignore keep build artefacts out of the index).changelog.d/added/<branch-slug>.md fragment carries one sentence naming the plugin; Rigor::VERSION is not bumped (the user drives release cuts per docs/agents/contribution-flow.md § "Release Cadence").docs/agents/contribution-flow.md style (Add rigor-<id> plugin (<facet>) or Add rigor-<id> walkthrough (<facet>)).Publishing to RubyGems is out of scope for this skill. A bundled plugin ships inside the single rigortype gem (per ADR-31's single-bundled-gem distribution model — there are no per-plugin gemspecs and no git subtree split); it reaches users when a maintainer cuts the next rigortype release (.claude/skills/rigor-release-prep/SKILL.md). A third-party plugin (ADR-31 WD4) instead lives in the author's own repo with its own gemspec depending on gem "rigortype".
Concrete trace through a fictional request — "Create a Rigor plugin for the dotenv gem" — to anchor expectations:
dotenv is a real gem → plugins/rigor-dotenv/. (Not a fictional teaching domain.)Dotenv.load(path) call), Q2=E (reads .env file), Q3=A (known finite set of variable names), Q4=B (error on missing var), Q5=D (external file path config).rigor-routes template row (Q1=A/B/C, Q2=E, Q3=A/D, Q5=C/D). Copy the rigor-routes directory layout.plugins/rigor-dotenv/{lib,demo}/, add the cache-producer + IoBoundary pattern verbatim from Module 2, demo with tmp/-anchored cache.spec/integration/plugins/dotenv_plugin_spec.rb, README, changelog fragment, run make verify-changed, single commit, Draft PR.If the request shifts mid-flow (e.g. user later says "and also error when the value is empty"), restart from Phase 1 Q3 — the requirements gathering is the gate that prevents accidental scope creep.
Rigor::Plugin.unregister! in before + after. See references/04-appendix.md § Common pitfalls #2.watch:, so a new file the prior run never read reads as fresh. Add watch: -> { [[@search_paths, "**/*.rb"]] }. See references/02-scaffold-walker-demo.md Phase 4.5.source_family: was passed to the Diagnostic constructor. Don't — the runner overwrites it. See pitfall #7.Prism::CallNode#name == "foo" always false — node.name returns a Symbol. Use == :foo. See pitfall #4.lib/ not on load path in tests — spec needs $LOAD_PATH.unshift(...) before require "rigor-<id>". See pitfall #10.git status shows leaked .rigor/cache/ — demo .rigor.yml didn't set cache.path: tmp/.rigor/cache or missing per-demo /tmp/-only .gitignore. See pitfall #1.© rigortype, MPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files (references) in .claude/skills/rigor-plugin-author of rigortype/rigor.
Open the folder on GitHubat commit c7b6b60
Rigor Plugin Author next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Rigor Plugin Author this skillrigortype/rigor | 106 | — | ~3.3k | Automated safety check: Notes | MPL-2.0 | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 24 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Greplooponyx-dot-app/onyx | 32k | 4 repos | ~3.3k | Automated safety check: Pass | MIT |
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
akash-network/node
Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.
rigortype/rigor
Measure Rigor's baseline drift across the tagged history of a real OSS Ruby project.
rigortype/rigor
Adjudicate a rigor unused report safely before proposing dead-code removal.
rigortype/rigor
Reduce an existing .rigor-baseline.yml rule by rule by triaging sites, fixing or intentionally suppressing them, and regenerating the baseline.
rigortype/rigor
Validate that a project's Rigor configuration, plugins, paths, and baseline are actually healthy.
rigortype/rigor
Author a Rigor plugin in an adopting project or standalone rigor- gem for a DSL, framework, or metaprogramming pattern.
rigortype/rigor
Audit an existing Rigor plugin against the current authoring contract and produce a prioritized upgrade path.
Categories
Author a new Rigor plugin, choosing plugins/ for production support or examples/ for a contract walkthrough. Rigor Plugin Author is an agent skill from rigortype/rigor. Author a new Rigor plugin, choosing plugins/ for production support or examples/ for a contract walkthrough.
Rigor Plugin Author fits situations like: extending Rigor for a DSL; not for editing an existing plugin; the analyzer engine.
Run `npx skills add rigortype/rigor --skill rigor-plugin-author -a claude-code`. Or copy the skill folder (.claude/skills/rigor-plugin-author in rigortype/rigor) into .claude/skills/rigor-plugin-author in your project. Claude Code loads it when a task matches its description.
Run `npx skills add rigortype/rigor --skill rigor-plugin-author -a codex`. Or copy the skill folder (.claude/skills/rigor-plugin-author in rigortype/rigor) into .agents/skills/rigor-plugin-author in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rigortype/rigor --skill rigor-plugin-author -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rigor-plugin-author, .gemini/skills/rigor-plugin-author, .github/skills/rigor-plugin-author and .opencode/skills/rigor-plugin-author in your project.
Going by SKILL.md and its folder, Rigor Plugin Author needs the command-line tools its instructions call (make, git, gem, nix and bundle).
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Rigor Plugin Author is published under the MPL-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.8k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Rigor Plugin Author: Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars) and Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
rigortype (a GitHub organization) maintains it in rigortype/rigor, which has 106 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on October 2, 2026.
Source: rigortype/rigor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.