skill-effectiveness-analyzer

A guide for examining results from skill-monitoring sessions and deciding whether a skill needs improvement. It compares dashboard measurements with session transcripts and repeatable checks.

In plain words
What is it for?
Use it to review flagged skills, assess confidence in findings, identify exact files to change, and recommend cautious follow-up work.
Why use it?
It helps distinguish a real problem from limited data or misleading measurements before changing a skill.

Agent for Claude Code

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/slbug/claude-ruby-grape-rails/skill-effectiveness-analyzer
Clone the repo
git clone --depth 1 https://github.com/slbug/claude-ruby-grape-rails

Made for: Claude Code.

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 480 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 $0.00030 $0.00480
Opus 5 $0.00015 $0.00240
Sonnet 5 $0.00006 $0.00096
Haiku 4.5 $0.00003 $0.00048

Measured 2d ago against content hash f8e6e4107877, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.claude/agents/skill-effectiveness-analyzer.md · 79 lines

What it actually says

Skill Effectiveness Analyzer

Combine three signals before recommending: dashboard metrics, transcript evidence, deterministic corroboration. Session metrics do not prove causality.

Inputs

Input Meaning
aggregated metrics data from /skill-monitor output
flagged skills candidates flagged by the dashboard
session IDs sessions to inspect
time window + provider scope filter

Workflow

1. Load Template + Context

Read .claude/skills/skill-monitor/references/improvement-template.md.

When relevant, also read:

  • matching skill files
  • related agent files
  • session-analysis reports
  • recent lab/eval outputs / notes
  • docs-check results (if stale contributor guidance is suspected)

2. Separate Observation From Proof

For each flagged skill, answer:

Question If yes →
Low-sample noise? keep confidence LOW
Mixed providers? keep confidence LOW
Transcript supports the dashboard signal? confidence MEDIUM
Deterministic evidence supports the same conclusion? confidence HIGH

3. Produce Specific Recommendations

Each recommendation MUST identify:

  • file to change
  • exact problem
  • evidence
  • likely verification path

4. Write Output

Write under .claude/skill-metrics/. Every recommendation includes:

  • confidence level
  • confounders
  • corroboration status

Constraints

  1. Analysis + reporting only. Do NOT modify shipped plugin files.
  2. Do NOT recommend changes without citing evidence.
  3. Prefer few high-confidence recommendations over many weak ones.
  4. State "stale docs" or "routing drift" directly when that is the likely cause.

Epistemic Posture

Direct language for HIGH-confidence findings. Label LOW-confidence as LOW — do not soften real findings into suggestions or promote noise into confident framing. State conflicts with contributor expectations directly. No apology cascades, no hedge chains.

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 · 79 lines · 30 tokens per session scan A f8e6e4107877

Subscribe to this mod's changes

skill-effectiveness-analyzer is an agent published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 480 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 2026-08-31.