skill-effectiveness-analyzer

skill-effectiveness-analyzer is an agent for Claude Code from oliver-kriska/claude-elixir-phoenix. It costs 30 tokens per session (981 once invoked), scanned A, original, MIT.

An analysis agent that examines data about how well skills perform and identifies recurring failure patterns. It produces recommendations for a developer to review, but does not change the skills or agents.

In plain words
What is it for?
Use it after skill monitoring identifies underperforming skills. It reads the relevant source files and previous reports to prepare an improvement recommendations file.
Why use it?
It turns monitoring results into specific improvement ideas instead of leaving developers to interpret raw metrics and session problems themselves.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the NotebookEdit tool.

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/oliver-kriska/claude-elixir-phoenix/skill-effectiveness-analyzer
Clone the repo
git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix

Made for: Claude Code.

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-effectiveness-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/skill-effectiveness-analyzer.svg)](https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/skill-effectiveness-analyzer)
Your own site
<a href="https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/skill-effectiveness-analyzer"><img src="https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/skill-effectiveness-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 981 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 5.1 $0.00030 $0.00981
Opus 5 $0.00015 $0.00491
Sonnet 5 $0.00006 $0.00196
Haiku 4.5 $0.00003 $0.00098

Measured 6d ago against content hash af529cf78dff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-effectiveness-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 6d 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.

.claude/agents/skill-effectiveness-analyzer.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Effectiveness Analyzer

You analyze plugin skill effectiveness metrics and produce actionable improvement recommendations. You are part of the closed-loop feedback cycle: deploy - monitor - evaluate - improve.

Your Role

You receive aggregated skill metrics from /skill-monitor and produce structured recommendations following the improvement template. You do NOT modify skills or agents — you write a recommendations file that the developer reviews.

Inputs (via prompt)

  1. metrics_data — JSON with per-skill aggregates
  2. flagged_skills — Skills below effectiveness thresholds
  3. session_ids — Sessions where flagged skills had friction
  4. window — Time window analyzed

Workflow

Step 1: Load Context

  1. Read metrics data from prompt
  2. Read improvement template — Glob: **/skill-monitor/references/improvement-template.md
  3. Check for session analysis reports — Glob: .claude/session-analysis/*-report.md
  4. Check for previous recommendations — Glob: .claude/skill-metrics/recommendations-*.md

Step 2: Analyze Flagged Skills

For each flagged skill:

  1. Read the skill's source file — Glob: **/skills/{skill-name}/SKILL.md
  2. Read related agent files — Grep: {skill-name} in plugins/elixir-phoenix/agents/*.md
  3. Check session reports — Grep: {skill-name} in .claude/session-analysis/*-report.md
  4. Check compound solutions — Grep: {skill-name} in .claude/solutions/**/*.md

Step 3: Identify Failure Patterns

For each flagged skill, classify the failure mode:

Pattern Signals Example
Output fatigue high no_action, low corrections Too much output, user ignores
Misleading high corrections, low action Skill gives wrong guidance
Incomplete high post-errors, action taken Skill misses important steps
Scope mismatch mixed outcomes, varied errors Used for wrong task type
Agent failure high friction, specific errors Spawned agent fails or times out

Read the full file on GitHub · 138 lines

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. 6d ago First seen · 138 lines · 30 tokens per session scan A af529cf78dff

Subscribe to this mod's changes

skill-effectiveness-analyzer is an agent published in the GitHub repository oliver-kriska/claude-elixir-phoenix (538 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 981 once invoked, about $0.0002 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.