SkillFoxx

skill-reviewer plugin

A skill that reads other skills file by file and returns finding cards with line citations and severity.

  • 57 ★ on the repository
  • Last commit
  • Apache-2.0
Plugin

Minimal access

Why this level

  • The skill reads the reviewed skill's files and writes a report, using no external services.
All reasons and checks

terryc21/skill-reviewerAuthor:Terryc21

Install

Works in

In your terminal, with SkillFoxx CLI

npx skillfoxx add plugins/skill-reviewer

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • The skill reads the reviewed skill's files and writes a report, using no external services.

This is third-party code. Review the repository files before installing.

What it does

skill-reviewer reviews Claude Code skills you write yourself. It reads every file, cites specific lines and lists strengths and weaknesses separately without hedging. The output is a Markdown report of about 1500 words for a plugin: a short summary, five to ten strengths to keep and a stack of finding cards sorted by severity. Each card has a reason, a fix, a line citation, an effort estimate and a quick-win tag. A final section names patterns that recur across cards. `/skill-reviewer review <path>` runs a full review, `summary` gives a five-minute check, `lenses` and `detect` list the available lenses and detect the skill type, and `--version` prints the version.

Who it is for. Authors of Claude Code skills and plugins who want a candid review before publishing rather than polite approval.

Good fit when

  • Before publishing you want a review citing specific lines of a finished skill.
  • You want a quick five-minute check: `/skill-reviewer summary`.
  • You want a second opinion on a skill: an optional challenger pass is available.
  • After many edits you need to find recurring weaknesses.

Not a fit when

  • You want feedback on a product or idea rather than skill files.
  • You need an automatic CI check without a model.
  • The skill is for another agent: the tool targets Claude Code's format.

Example request

/skill-reviewer review ~/.claude/skills/my-skill

Limitations

The project is at version 0.3.0: the author has shipped five releases and reviews the skill with itself after every meaningful edit. Assessment comes from a model reading files, so check its conclusions rather than accepting them. A full review takes two to five minutes. After a manual install the skill registers as a skill rather than a plugin and is called with the `/skill skill-reviewer` prefix. Enter the two plugin install commands one at a time: pasted together, the second becomes arguments to the first. There is no autocomplete for subcommands.

How to disable. Uninstall the plugin with Claude Code or delete `~/.claude/skills/skill-reviewer` if you installed manually.

FAQ

How do I install it?

Enter `/plugin marketplace add Terryc21/skill-reviewer`, wait for the success message, then `/plugin install skill-reviewer@skill-reviewer`. Enter them one at a time.

How do I verify the install?

`/skill-reviewer --version` prints three lines: version, install path and the lens list.

How do I install it manually?

Run `mkdir -p ~/.claude/skills` and `git clone https://github.com/Terryc21/skill-reviewer ~/.claude/skills/skill-reviewer`. Call it as `/skill skill-reviewer <subcommand>`.

What is in the report?

A summary, strengths, finding cards with reason, fix, citation, effort and quick-win tag, and a patterns section.

Is there a sample report?

Yes, the repository includes a review of a real skill, `unforget`, at `skills/skill-reviewer/examples/sample-report-unforget.md`.

Discussion

No questions or reviews yet.

Plugins

A code review skill with four independent probes, evidence-backed findings and a merge gate derived from JSON

SkillExtended access479

A Codex skill for reviewing AI-written code: explains blocks, names files and lines, checks goals against evidence.

SkillExtended access133

A code review skill across many languages and frameworks: architecture, performance, security, anti-patterns and common bugs

SkillMinimal access2.3K13
Needs a VPN

A Claude Code skill that delegates tasks to OpenAI's Codex CLI for code analysis, review and edits

SkillBroad access1.5K

Catalog of 46 versioned skills for code review, releases, CI and landing pages, installed as the lstack plugin or through npx.

PluginExtended access145

Skill and agent manager with a lock file: installs one set into Claude Code, Codex, Cursor and others and keeps your edits.

CLIExtended access181

README in short

The plugin builds on Claude Code's skills architecture. The README explains subcommands, a first-review example and when to choose a full report or a summary.

README badge

Original SKILL.md

---
name: skill-reviewer
version: 0.3.0
description: Use when reviewing a Claude Code skill, auditing skill quality before publish, or asking "is this skill any good?". Produces structured reports with file:line citations, severity-rated findings cards, and an optional second-opinion pass. Lens variants: full (default), safety, discoverability, architecture, parseability, tests, quick.
license: Apache-2.0
---

# skill-reviewer

> Installed as a Claude Code plugin in v0.1. Invoke as `/skill-reviewer <subcommand>`. The plugin registers `/skill-reviewer` as a single skill activation; Claude parses the argument string as a subcommand. There is no per-subcommand autocomplete or native slash command for each row in the table below — they are subcommand strings the skill recognizes, not registered commands.

> Candid, no-bullshit reviews of Claude Code skills. Honest about strengths and weaknesses both.

## Why this skill exists

Skill authors get polite-by-default feedback. Reviewers want to be helpful, so they hedge: "consider adding tests," "you might think about discoverability." That kind of feedback ships skills with quiet flaws — silent test gaps, unparseable output formats, trigger phrases that never fire.

skill-reviewer was extracted from a real review session where a skill author wanted blunt critique with file:line citations and ranked actions. The pattern worked. This skill bottles it.

Three things distinguish a skill-reviewer report from generic feedback:

1. **File:line citations for every claim.** No "this could be clearer" without saying where and why.
2. **Equal weight to strengths and weaknesses.** Reviews that only list problems tell authors what to change but not what to preserve.
3. **Severity rubric with effort estimates.** Quick wins are tagged so authors can pick low-cost-high-leverage fixes first.

---

## Subcommand surface

| Subcommand | Purpose | Full spec |
|---|---|---|
| `/skill-reviewer review <path>` | Full review of one skill | `reference/protocol.md` |
| `/skill-reviewer review <path> --lens=<name>` | Focused review under a lens | `reference/lenses.md` |
| `/skill-reviewer review <path> --second-opinion` | Full review + reconciliation pass | `reference/second-opinion.md` |
| `/skill-reviewer summary <path>` | TL;DR + top 5 strengths + top 5 weaknesses only | `reference/lenses.md` (`quick` lens) |
| `/skill-reviewer lenses` | List available lenses with descriptions | `reference/lenses.md` |
| `/skill-reviewer detect <path>` | Classification only; print shape + recommended review depth | `reference/detection.md` |
| `/skill-reviewer --version` | Print version, install path, supported lens names | `reference/output-format.md` § `--version` output |

**Flags** (apply to `review` only unless noted):

Report a problem