skill-reviewer

skill-reviewer is a skill for Claude Code from Terryc21/skill-reviewer. It costs 71 tokens per session (2,110 once invoked), scanned A, original, Apache-2.0.

A review skill for Claude Code skills, which are instruction packages that teach an AI assistant how to perform a task. It assesses their quality and reports findings with file and line references.

In plain words
What is it for?
Use it to review a skill’s overall quality or focus on safety, discoverability, architecture, and related concerns, with severity-rated findings and an optional second opinion.
Why use it?
It helps catch unclear activation wording, missing tests, unsafe behavior, and output problems before a skill is published. The report ranks issues so authors can focus on the most important fixes first.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions subagents; mentions Claude Code.

Part of the skill-reviewer plugin — 1 skill shipped together

Good fit Use it to review a skill’s overall quality or focus on safety, discoverability, architecture, and related concerns, with severity-rated findings and an optional second opinion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terryc21/skill-reviewer/skill-reviewer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Terryc21/skill-reviewer --skill skill-reviewer
Clone the repo
git clone --depth 1 https://github.com/Terryc21/skill-reviewer

Made for: Claude Code.

Or install skill-reviewer, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/terryc21/skill-reviewer/skill-reviewer/github.svg)](https://agentmods.dev/skills/terryc21/skill-reviewer/skill-reviewer)
Your own site
<a href="https://agentmods.dev/skills/terryc21/skill-reviewer/skill-reviewer"><img src="https://agentmods.dev/badge/skills/terryc21/skill-reviewer/skill-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/terryc21/skill-reviewer/skill-reviewer"><img src="https://agentmods.dev/badge/skills/terryc21/skill-reviewer/skill-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,110 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.02110
Opus 5 $0.00036 $0.01055
Sonnet 5 $0.00014 $0.00422
Haiku 4.5 $0.00007 $0.00211

Measured 9d ago against content hash 63aeafdfaa8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skill-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/skill-reviewer/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Read the full file on GitHub · 127 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 127 lines · 0 tokens per session scan A 63aeafdfaa8a

Subscribe to this mod's changes

skill-reviewer is a skill published in the GitHub repository Terryc21/skill-reviewer (52 stars, last pushed 11d ago), licensed Apache-2.0. It adds 71 tokens to every session and 2,110 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

uplevel

Establish, automate, and enforce a project's engineering process — the gate that runs before every commit, the checks that replace it with automation, the environment and deploy discipline that keeps production safe, and the irreversible operations that need explicit sign-off. Use when the user asks to "uplevel this…

rlx/uplevel · 217 tokens

ring:migrating-to-lib-observability

Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…

LerianStudio/ring · 104 tokens

ring:mapping-streaming-events

Mapping the eventable points in a Lerian Go service where lib-streaming should emit past-tense, durable, tenant-scoped business events, producing a PM-validated event catalog and instrumentation-map.json for ring:instrumenting-streaming-events. Three-pass discovery (Survey, Slice, Mark) with a scope fence and delivery…

LerianStudio/ring · 95 tokens

ring:exploring-codebases

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…

LerianStudio/ring · 91 tokens

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:instrumenting-streaming-events

Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…

LerianStudio/ring · 102 tokens