Design
synnaxlabs/synnax
Process and hard rules for designing and planning complex new features, refactors, and re-architectures.
Find prior Rigor evaluations, measurements, comparisons, or decisions and report file:line evidence.
Install Rigor Prior Art
$ npx skills add rigortype/rigor --skill rigor-prior-art -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rigortype/rigor rigor-prior-art --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-prior-art .claude/skills/rigor-prior-art && 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-prior-art" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-prior-art into .claude/skills/rigor-prior-art/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-prior-art", 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-prior-artType 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-prior-art -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rigortype/rigor rigor-prior-art --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-prior-art .agents/skills/rigor-prior-art && 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-prior-art" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-prior-art into .agents/skills/rigor-prior-art/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-prior-art", 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-prior-art -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rigortype/rigor rigor-prior-art --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-prior-art .cursor/skills/rigor-prior-art && 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-prior-art" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-prior-art into .cursor/skills/rigor-prior-art/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-prior-art", 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-prior-art--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-prior-art -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rigortype/rigor rigor-prior-art --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-prior-art .gemini/skills/rigor-prior-art && 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-prior-art" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-prior-art into .gemini/skills/rigor-prior-art/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-prior-art", 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-prior-artInstalls 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-prior-art -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-prior-art .github/skills/rigor-prior-art && 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-prior-art" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-prior-art into .github/skills/rigor-prior-art/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-prior-art", 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-prior-art -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-prior-art --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-prior-art .opencode/skills/rigor-prior-art && 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-prior-art" agent skill from https://github.com/rigortype/rigor/tree/master/.claude/skills/rigor-prior-art into .opencode/skills/rigor-prior-art/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rigor-prior-art", 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.
Facts
- Skill name
rigor-prior-art- GitHub stars
- 106
- Token cost
- ~1.9k tokens
- SKILL.md length
- 964 words
- Files
- 2 (incl. references)
- Skills in repo
- 36
- Repo updated
- First seen
- Licence
- MPL-2.0
At a glance
Find prior Rigor evaluations, measurements, comparisons, or decisions and report file:line evidence.
- Works in 3 steps: First-party evaluation — Rigor ran /… → External material —… → Mere mention / bibliography URL — a…
- Tasks that involve Intellectual property
- SKILL.md covers When NOT to use this, Corpus map — where evidence…, Source taxonomy — classify… and Method, plus 2 more sections
- Calls git
What it does
Rigor Prior Art is an agent skill from rigortype/rigor. Find prior Rigor evaluations, measurements, comparisons, or decisions and report file:line evidence. Use before making a comparative or historical claim, or when asked what Rigor's corpus says; not for a fact in a file you already know.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/explore-prompt-template.md`).
It sits in Legal & Compliance, covering Intellectual property and Architecture decision records. The repository describes itself as: Inference-first static analysis for Ruby. The licence is MPL-2.0.
When your agent uses it
- Tasks that involve Intellectual property
- Tasks that involve Architecture decision records
Example prompts
- “/rigor-prior-art”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- First-party evaluation — Rigor ran / measured / compared something
- External material — docs/notes/deep-research/, quoted blog posts,
- Mere mention / bibliography URL — a name-drop or a citation-list
What it can do on your machine
Read from SKILL.md and the folder at commit 3264953. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
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.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Rigor Prior Art loads about 1.9k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 964 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.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated 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.
SKILL.md
The full file from rigortype/rigor at commit 3264953, republished under its MPL-2.0 licence (© rigortype). 964 words, ~1,881 tokens.
Download SKILL.mdSave it as
.claude/skills/rigor-prior-art/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- rigor-prior-art
- description
- Find prior Rigor evaluations, measurements, comparisons, or decisions and report file:line evidence. Use before making a comparative or historical claim, or when asked what Rigor's corpus says; not for a fact in a file you already know.
- metadata.internal
- true
rigor-prior-art — corpus archaeology with citation-grade output
The rigor repository accumulates evidence across 80+ ADRs, 100+ research notes, the CHANGELOG and its archives, a handbook, and a manual. Answering "what do we already know about X?" is a recurring task whose cost is dominated by two things this skill freezes: knowing where each kind of evidence lives, and the discipline that keeps citations accurate. The stakes are asymmetric — a published overclaim ("Steep misses X", "we measured Y") gets challenged by experts and costs credibility, so a finding you cannot pin to a file and line is not a finding.
When NOT to use this
A single fact in a file you already know → just Read/rg it directly.
This skill is for topic-level sweeps ("everything the corpus says about
X") and for claims that need verified citations before they leave the
repo (talks, comparisons, READMEs).
Corpus map — where evidence lives
| Location | What lives there | When to look |
|---|---|---|
docs/adr/README.md | Canonical ADR index: title + a short status (Accepted (WD1–WD4 landed; WD5 deferred)). Index only — no detail, by ADR-97. | First stop, to shortlist 2–5 ADRs and to see which are live. Never a source for what was decided. |
AGENTS.md ADR premises | A capped premise set (≤12) — topic and link, no status (ADR-97). | Which few ADRs bind every task. Never a source. |
docs/notes/README.md | Categorized note index: library surveys / coverage audits / regression sweeps / teeth / outside-research reviews / perf / meta. | Shortlisting notes by category. |
docs/adr/*.md | Full decisions: criteria, rejected alternatives, gate results. | The "why" behind a behaviour; what was rejected and why. |
docs/notes/*.md | What was observed, when, against which Rigor version. | Measurements, sweeps, adjudications. |
docs/CHANGELOG-*.md + CHANGELOG.md | Per-feature landing narratives with spec/corpus evidence. | Comparative evidence often lives ONLY here — e.g. the rbs_rails coverage comparison and the ~20-methods-per-column contrast are in the 0.1.x archive, indexed nowhere else. Always include every archive. |
docs/design/*.md | Design plans that preceded ADRs. | Pre-decision context, roadmaps. |
docs/handbook/, docs/manual/ | User-facing claims. | What Rigor promises publicly — the bar a new claim must clear. |
docs/notes/deep-research/ | External LLM deep-research reports stored for reference. | Community/competitor landscape only — never a first-party claim (register rules in its README). |
references/ submodules | Vendored upstream source (read-only). | Verifying a claim about another tool's code. |
git log -S"term" | When a claim or feature landed. | Dating evidence; finding the landing commit. |
Source taxonomy — classify every hit
- First-party evaluation — Rigor ran / measured / compared something (a note's sweep table, a CHANGELOG gate result, an ADR's corpus numbers). Only this class supports "Rigor's docs say…" / "we measured…".
- External material —
docs/notes/deep-research/, quoted blog posts,references/submodules. Report as "surveyed community knowledge", never as Rigor's own claim. Deep-research reports carry citation markers ([5]) that look authoritative but their references can be synthetic, and they are known to contain factual errors about Rigor itself (e.g. attributing the rigor-rs Rust port's internals — ruby-prism, bumpalo — to Rigor proper). - Mere mention / bibliography URL — a name-drop or a citation-list entry. Not evidence; exclude or mark as such.
Labelling the class is what lets the user decide what register a claim can carry downstream — do not collapse the three into one list.
Show full SKILL.md (459 more words)Show less
Method
- Indexes first, then the bodies. Skim
docs/adr/README.mdanddocs/notes/README.mdfor the topic. Both are indexes — title + short status, no detail (ADR-97) — so they shortlist 2–5 candidates but never answer outright. The substance is in the ADR bodies; open the shortlist, and expect the answer to come fromrgoverdocs/adr/*.md(step 2) rather than from any index. An index's status line is the one thing you can cite from it: whether the decision is live. - Expand terms before searching. Name variants (
rbs_rails/rbs-rails), English and Japanese vocabulary (型定義 / 生成 / メンテナンス / 陳腐化 …), tool aliases, and the adjacent tools a comparison would name (searching forrbs_railsshould also sweepTapioca,gem_rbs_collection,orthoses). - Sweep. For a broad multi-tool/multi-theme sweep, or when the main
conversation's context is worth protecting, fill in
references/explore-prompt-template.md
and hand it to one Explore subagent — the template encodes the location
list, adjudication criteria, and output format, so don't rewrite it from
scratch. For a narrow single-topic lookup, run the same sweep yourself
with
rgover the template's location list — a subagent round-trip adds minutes of latency that a focused inline sweep doesn't need. - Verify before citing. For every quote that will appear in your
report, re-read the raw bytes:
grep -n "<fragment>" <file> | cat -v. Subagent echoes can silently mangle proper nouns; a citation you did not verify against the file is a liability, not evidence. - Report per the output contract below.
Output contract
- Per finding:
file:line(repo-relative, clickable), a verbatim quote or tight paraphrase, its source class, and the tool/theme it bears on. - Organize by tool or theme, not by file — the user is answering a question, not auditing a directory.
- State what was NOT found. Absence is a result: "no side-by-side numeric Rigor-vs-Steep run exists in the corpus" prevents the exact overclaim the search was meant to protect against.
- Time-stamp caveat where it matters. Notes are non-normative snapshots ("what was true when written, against the Rigor version named inside") — when a finding names a file, flag, or method, note whether it still exists if the user is about to rely on it.
Pitfalls
- Archived CHANGELOGs are the evidence trove. Landing narratives hold
the densest per-feature comparative evidence, and an archived changelog
drops out of casual view (
docs/CHANGELOG-*.md). A sweep that skips them misses decisive material. - ADR supersedes note. An ADR's status line is updated in place; the note that spawned it is frozen. For "what is true now" prefer the ADR status; for "what was measured then" cite the note.
- rigor ≠ rigor-rs. The Rust port makes opposite design choices (vendored RBS, single binary). External material conflates them.
- "Evaluated" ≠ "mentioned". A tool appearing in a comparison table someone imported is not Rigor having evaluated it — that is what the taxonomy is for.
© 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
Files
SKILL.md and 1 other file (references) in .claude/skills/rigor-prior-art of rigortype/rigor.
- SKILL.md
- references/explore-prompt-template.md
Open the folder on GitHubat commit 3264953
Compare with similar skills
Rigor Prior Art 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 Prior Art this skillrigortype/rigor | 106 | — | ~1.9k | Automated safety check: Pass | MPL-2.0 | |
| Designsynnaxlabs/synnax | 128 | — | ~4.5k | Automated safety check: Pass | Custom licence | |
| Prior Art Scoutn1m21n/Infinite | 271 | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Adr Brief Drafterrohasnagpal/legal-ai-skills | 178 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Paper to Chinese Patent DrafterYuan1z0825/nature-skills | 47k | 1 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill | 107 | 1 repos | ~959 | Automated safety check: Pass | None |
Similar skills
Prior Art Scout
n1m21n/Infinite
Find publicly documented solutions (peer repos, GitHub, forums) to bugs, platform quirks, dependency gotchas or architectural patterns, respecting the copyleft discussions-only rule.
Adr Brief Drafter
rohasnagpal/legal-ai-skills
Drafts the brief a party submits to a mediator or conciliator ahead of a session — position, facts, interests, chronology, evidence, negotiation history, and settlement obstacles — adapted to…
Paper to Chinese Patent Drafter
Yuan1z0825/nature-skills
Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.
Paper To Cn Patent
snipp-zha/Paper-to-patent-Skill
Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.
Patent Examine
gfodor/legal-skills
Iteratively examine and revise a draft U.S. An agent skill from gfodor/legal-skills.
More from rigortype/rigor
All 36 skills in this repoRigor Regression Sweep
rigortype/rigor
Measure Rigor's baseline drift across the tagged history of a real OSS Ruby project.
Rigor Unused Adjudicate
rigortype/rigor
Adjudicate a rigor unused report safely before proposing dead-code removal.
Rigor Baseline Reduce
rigortype/rigor
Reduce an existing .rigor-baseline.yml rule by rule by triaging sites, fixing or intentionally suppressing them, and regenerating the baseline.
Rigor Doctor
rigortype/rigor
Validate that a project's Rigor configuration, plugins, paths, and baseline are actually healthy.
Rigor Plugin Author
rigortype/rigor
Author a new Rigor plugin, choosing plugins/ for production support or examples/ for a contract walkthrough.
Rigor Plugin Author
rigortype/rigor
Author a Rigor plugin in an adopting project or standalone rigor- gem for a DSL, framework, or metaprogramming pattern.
Related
Categories
Questions about Rigor Prior Art
What does Rigor Prior Art do?
Find prior Rigor evaluations, measurements, comparisons, or decisions and report file:line evidence. Rigor Prior Art is an agent skill from rigortype/rigor. Find prior Rigor evaluations, measurements, comparisons, or decisions and report file:line evidence.
When should I use Rigor Prior Art?
Rigor Prior Art fits situations like: tasks that involve Intellectual property; tasks that involve Architecture decision records.
How do I install Rigor Prior Art in Claude Code?
Run `npx skills add rigortype/rigor --skill rigor-prior-art -a claude-code`. Or copy the skill folder (.claude/skills/rigor-prior-art in rigortype/rigor) into .claude/skills/rigor-prior-art in your project. Claude Code loads it when a task matches its description.
How do I install Rigor Prior Art in Codex?
Run `npx skills add rigortype/rigor --skill rigor-prior-art -a codex`. Or copy the skill folder (.claude/skills/rigor-prior-art in rigortype/rigor) into .agents/skills/rigor-prior-art in your project. Codex loads it when a task matches its description.
Can I use Rigor Prior Art in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rigortype/rigor --skill rigor-prior-art -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-prior-art, .gemini/skills/rigor-prior-art, .github/skills/rigor-prior-art and .opencode/skills/rigor-prior-art in your project.
What does Rigor Prior Art need to run?
Going by SKILL.md and its folder, Rigor Prior Art needs the command-line tools its instructions call (git).
Does Rigor Prior Art access the network?
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.
Is Rigor Prior Art safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Rigor Prior Art use?
Rigor Prior Art is published under the MPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Rigor Prior Art use?
About 1.9k tokens (SKILL.md is roughly 7.5k 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 560 tokens, read only when the agent opens those files.
What are the alternatives to Rigor Prior Art?
Skills that share tags, products or a category with Rigor Prior Art: Design (synnaxlabs/synnax, 128 stars), Prior Art Scout (n1m21n/Infinite, 271 stars), Adr Brief Drafter (rohasnagpal/legal-ai-skills, 178 stars) and Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Rigor Prior Art?
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 10, 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.