rigortype/rigor/rigor-doctor
Claude Code and agent skill by rigortype/rigor
- community
Checking that the SKILL.md file is still in the repository.
Validate that a project's Rigor configuration, plugins, paths, and baseline are actually healthy. Use when diagnostics are suspicious or setup behavior is wrong; not for first-time onboarding or reducing ordinary diagnostics.
Install
npx vskill@latest install rigortype/rigor/rigor-doctorSKILL.md
Rigor Doctor
rigor skill describe reports what exists (presence checks). This skill goes a level deeper: rigor doctor runs Rigor's own setup validators (config audit, RBS environment, plugin loading, baseline drift, plugin gaps, install layout) and this skill interprets the result — the difference between "a .rigor.yml is present" and "it parses, loads its plugins, and analyses the right files." Reach for it when the diagnostics look wrong (suspiciously zero, or suspiciously many) or after editing the config.
First: load the version-current copy
This skill's exact commands, flags, and config keys drift between Rigor releases, so follow the copy that ships with the installed Rigor rather than any vendored or frozen copy of this file. Get the complete current procedure in one call:
If you already loaded this skill via rigor skill you have the current copy — just proceed (read any references/NN-*.md from the directory the header names). If rigor is not on PATH, this task needs it: run `rigor-next-steps` to install Rigor first, then come back.
When to use
- After editing
.rigor.yml/.rigor.dist.yml. - When
rigor checkreports suspiciously few or suspiciously many
diagnostics, or the config feels like it isn't taking effect.
- NOT for first-time setup (→
rigor-project-init) or working real
diagnostics down (→ rigor-baseline-reduce).
What it validates
rigor doctor runs the setup checks in one pass (--format json gives each finding's checks[].id and status) and exits non-zero when any check fails. It does not check whether the analysis sees the right files; that is a separate look at stats.target_files in rigor check --format json. What each check id means and how to act on it live in the version-current `references/01-checks.md` (loaded per the directive above).
Interpreting the result
- All clean (no
failorwarnfinding, and the file count matches
the project) → the setup is healthy; any diagnostics are about the code, not the configuration. Move on to rigor-baseline-reduce or rigor-protection-uplift.
- A `config_audit`, `rbs_environment`, or `plugins` failure → that is
the real problem; fixing it usually clears a whole cluster of confusing downstream diagnostics at once.
For deeper symptoms (hover shows untyped everywhere, completion empty, LSP silent) read the manual's troubleshooting chapter — offline and version-matched:
Next step
Re-run rigor skill describe for the recommended next move.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/rigor-doctor/SKILL.md
Popularity
- Repository stars
- 91
- Repository forks
- 1
- 7-day trend score
- 23
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/rigortype/rigor/rigor-doctor)