What is skill-doctor?

An auditing tool for Agent Skills catalogues and installed skill folders. It checks metadata, documentation links, and declared skill dependencies, with an optional mode for narrow safe repairs.

Scanning a selected skill root, producing text or JSON findings, checking dependencies, and optionally creating missing agent configuration files or correcting a policy setting.

It reveals catalogue or installation problems that could prevent skills from being published or used correctly.

skill-doctor — Skill for Claude Code and Codex by PaulRBerg

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 PaulRBerg/agent-skills --skill skill-doctor

Clone the repo

git clone --depth 1 https://github.com/PaulRBerg/agent-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/paulrberg/agent-skills/skill-doctor/github.svg)](https://agentmods.dev/skills/paulrberg/agent-skills/skill-doctor)

Your own site

<a href="https://agentmods.dev/skills/paulrberg/agent-skills/skill-doctor"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/skill-doctor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/paulrberg/agent-skills/skill-doctor"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/skill-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,211 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.01211
Opus 5	$0.00015	$0.00606
Sonnet 5	$0.00006	$0.00242
Haiku 4.5	$0.00003	$0.00121

Measured yesterday against content hash 6c738bbe67a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skill-doctor 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 yesterday.

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-doctor/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Doctor

Use ai-skillet's canonical validator for the supported extended skill dialect to audit local catalogs and installed skill roots, then apply only narrow metadata repairs when requested.

Arguments

--root PATH: Scan this catalog or installed skill root. Repeatable. Default: current working directory.
--format text|json: Select report format. Default: text.
--fix-safe: Create missing agents/openai.yaml files or update mismatched policy.allow_implicit_invocation.
--dependencies-only: Report only malformed or unresolved skill-dependencies declarations. Do not combine with --fix-safe.

Workflow

Require ai-skillet 0.1.0 or newer on PATH, then run:
```
ai-skillet doctor
```
Append each parsed invocation option and its value as separate arguments, preserving quoted values. For example, --root '/path with spaces' --format json adds two options; use the argument-free form for the defaults.
Use JSON when another command or agent will consume the result:
```
ai-skillet doctor --root . --format json
```
Run safe fixes only after reading the findings:
```
ai-skillet doctor --root . --fix-safe
```
Re-run without --fix-safe after any manual edits.

For a dependency-only catalog gate, run:

ai-skillet doctor --root . --dependencies-only

Findings

Treat error findings as catalog defects that should block publishing or syncing.
Treat warning findings as review-required catalog hygiene issues.
JSON output uses schema version 1 with structured roots, counts, findings, and safe-fix records. Each finding carries its code, severity, path, line when known, fixability, and message.
Frontmatter validation accepts the portable Agent Skills fields, Claude Code extensions, and repository extensions as one supported union. It reports unknown top-level fields; invalid field, item, and metadata-value types; invalid enumerated values; and agent or background used without context: fork.
Explicit disable-model-invocation: false and user-invocable: true produce redundant-default warnings. Omit those fields to preserve the same effective defaults.
Prompt-hygiene warnings are advisory and never auto-fix: stale model pins, oversized unconditional Markdown references, conflicting requirement/prohibition language, and missing completion evidence.
Coordination-exemption errors are report-only: coordination: exempt must be paired with the catalog's canonical coordination-exempt sentence in ordinary Markdown prose. Inline code, fenced or indented code, blockquotes, and headed Example or Examples sections do not count as declarations. Neither side is repaired by --fix-safe.
Dependency errors reject non-array, empty, non-string, duplicate, malformed, incorrectly ordered, self-referential, or unresolved local declarations. External ORG/REPO#SKILL identifiers are shape-checked without network access.
Metadata, OpenAI policy, coordination, resource, README, prompt-hygiene, and CLI-version checks remain available outside --dependencies-only.
Use path and line from JSON output for precise follow-up edits.

Read the full file on GitHub · 109 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 42 B

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.

yesterday Changed · +3 lines 6c738bbe67a2
11d ago First seen · 106 lines · 29 tokens per session scan A 844276addc0e

Subscribe to this mod's changes

skill-doctor is a skill published in the GitHub repository PaulRBerg/agent-skills (70 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,211 once invoked, about $0.0001 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.

Building agents agent-skills ai-agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens