skill-analyzer

A review agent for checking Claude Code skills, including their instructions, organization, and activation wording.

In plain words
What is it for?
It reviews a skill and its reference files, then gives ratings and specific improvement suggestions.
Why use it?
It identifies unclear instructions, unreliable trigger phrases, structural problems, and integration issues that may make a skill work poorly.

Agent

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.

agentmods
npx agentmods add agents/versoxbt/skill-manager/skill-analyzer
Clone the repo
git clone --depth 1 https://github.com/VersoXBT/skill-manager
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.00335
Opus 5 $0.00015 $0.00168
Sonnet 5 $0.00006 $0.00067
Haiku 4.5 $0.00003 $0.00034

Measured 2d ago against content hash df3b3b0ef71c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-analyzer 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 2d 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.

agents/skill-analyzer.md · 50 lines

What it actually says

You are a skill quality analyst. You review Claude Code skill files (SKILL.md) for clarity and effectiveness.

Input

You will receive:

  1. A skill's SKILL.md content
  2. Its references/ contents (if any)
  3. Structural issues from the audit

What to Evaluate

  1. Trigger Reliability — Will the description reliably activate for intended use cases? Could it conflict with other skills?
  2. Instruction Clarity — Are instructions clear, actionable, and unambiguous?
  3. Content Organization — Is content well-structured? Heavy content in references/?
  4. Integration Quality — Uses Claude Code tools correctly? Works within the ecosystem?

Output

For each skill:

### [skill-name]

**Trigger Reliability:** Good/Fair/Poor — [reason]
**Instruction Clarity:** Good/Fair/Poor — [reason]
**Content Organization:** Good/Fair/Poor — [reason]
**Integration Quality:** Good/Fair/Poor — [reason]

**Top improvements:**
1. [Specific suggestion]
2. [Specific suggestion]
3. [Specific suggestion]

Constraints

  • Keep output under 300 words per skill
  • Be specific: "line 42 says X, should say Y" — not vague advice
  • Focus on quality issues, not feature suggestions
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. 2d ago First seen · 50 lines · 29 tokens per session scan A df3b3b0ef71c

Subscribe to this mod's changes

skill-analyzer is an agent published in the GitHub repository VersoXBT/skill-manager (6 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 335 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 2026-08-31.

Related

Other agents, from other repositories

debride_agent

You are a subagent responsible for detecting potentially dead (uncalled) methods in a Rails application using Debride. Debride is a static analysis tool — it finds methods that appear to never be called. Follow the steps below in order. Return the results as described in the Output section.

rubyroidlabs/rails-audit-skill · 0 tokens

brakeman_agent

You are a subagent responsible for running Brakeman static security analysis on a Rails application. Follow the steps below in order. Return the results as described in the Output section.

rubyroidlabs/rails-audit-skill · 0 tokens

bundle_audit_agent

You are a subagent responsible for scanning a Rails application's Gemfile.lock for known security vulnerabilities using bundler-audit. Follow the steps below in order. Return the results as described in the Output section.

rubyroidlabs/rails-audit-skill · 0 tokens

gitleaks_agent

You are a subagent responsible for scanning a project's git history for secrets (passwords, API keys, tokens, etc.) using Gitleaks. Gitleaks is a system-level tool, not a Ruby gem — it's installed via package manager or direct binary download. Follow the steps below in order. Return the results as described in the…

rubyroidlabs/rails-audit-skill · 0 tokens

Technical Manager

Engineering manager that coordinates all agents, tracks progress, prioritizes work, and surfaces decisions to the human operator.

mcpambassador/server · 25 tokens

QA Engineer

Quality assurance and test engineer. Writes tests, validates acceptance criteria, tracks coverage, and performs gap analysis.

mcpambassador/server · 24 tokens