evaluating-skills

evaluating-skills is a skill for Claude Code from slowdini/slow-powers. It costs 28 tokens per session (6,958 once invoked), scanned A, original, MIT.

A skill for testing whether an agent skill changes behavior in a useful way.

In plain words
What is it for?
Designing evaluations, writing assertions, and measuring an old skill against a revised version or no skill.
Why use it?
It replaces opinions about a skill with structured test cases, comparisons, and graded results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; positional $N argument; mentions Claude Code.

Part of the slow-powers plugin — 9 skills, 2 hooks shipped together

Good fit Designing evaluations, writing assertions, and measuring an old skill against a revised version or no skill.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/slowdini/slow-powers/evaluating-skills
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 slowdini/slow-powers --skill evaluating-skills
Clone the repo
git clone --depth 1 https://github.com/slowdini/slow-powers

Made for: Claude Code.

Or install slow-powers, the plugin that ships this one along with the rest of its 9 skills, 2 hooks.

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 evaluating-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/slowdini/slow-powers/evaluating-skills.svg)](https://agentmods.dev/skills/slowdini/slow-powers/evaluating-skills)
Your own site
<a href="https://agentmods.dev/skills/slowdini/slow-powers/evaluating-skills"><img src="https://agentmods.dev/badge/skills/slowdini/slow-powers/evaluating-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,958 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.
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 $0.00028 $0.06958
Opus 5 $0.00014 $0.03479
Sonnet 5 $0.00006 $0.01392
Haiku 4.5 $0.00003 $0.00696

Measured 7d ago against content hash 6c3d4b5e176d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

evaluating-skills 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 7d 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/evaluating-skills/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluating skills

Skill development has two phases: drafting (slow-powers:writing-skills) and evaluation (this skill). This skill owns the craft of evaluation — deciding whether a change needs measuring, designing test cases, devising pressure-testing scenarios, writing assertions, and reading results. The mechanics of actually running an eval — building the workspace, staging skills, dispatching subagents, grading, aggregating — are owned by a dedicated tool, eval-magic, which ships as a dependency-less prebuilt binary you invoke as eval-magic. See Running the eval for the hand-off.

Overview

An eval is a structured measurement of whether a skill actually shifts behavior. Each test case is a realistic prompt; each run dispatches a fresh general-purpose subagent twice — once with the skill loaded, once without (or once with the prior version, once with the revised version) — and grades the outputs against assertions. Pass-rate deltas tell you whether the skill is worth shipping or the change is worth landing.

Evals are harness-agnostic: run records use a portable JSON schema so an eval authored on one harness (Claude Code, Codex, OpenCode) can be executed and graded on any other. The runner documents the schema and the per-harness specifics; this skill stays at the level of what makes a good eval.

Two comparison modes

  • Mode A — new skill. Compares with_skill vs without_skill. Use when validating that a brand-new skill beats baseline behavior with no skill loaded. Best understood as a bundle of removal tests — one case per behavior the skill teaches (see Decompose the skill into behaviors first).
  • Mode B — revision (the common case). Compares old_skill vs new_skill. Use when testing a language change to an existing skill — snapshot the old SKILL.md, then run both variants against the same prompts. A negative or zero delta is a signal to revert: the new language did not improve behavior.

Read the full file on GitHub · 278 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. 7d ago First seen · 278 lines · 28 tokens per session scan A 6c3d4b5e176d

Subscribe to this mod's changes

evaluating-skills is a skill published in the GitHub repository slowdini/slow-powers (2 stars, last pushed 24d ago), licensed MIT. It adds 28 tokens to every session and 6,958 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 skills, from other repositories

ospec-change

Create or advance a lightweight OSpec change using the classic fast workflow.

clawplays/ospec · 18 tokens

trellis-channel

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

mindfold-ai/Trellis · 32 tokens

krypton-execution

Use when executing an approved Krypton plan, GOAL.md, or implementation plan that already defines intent, ownership, contract, cutover, task boundaries, and acceptance evidence. Use for main-agent execution with explorer, plan-reviewer, reviewer, maintainer, or verifier gates.

jturntdev/krypton · 61 tokens

krypton-planning

Use when a user has a feature request, bugfix, refactor, migration, architecture change, or product goal and needs an implementation plan before coding. Use especially when wrong ownership, duplicate paths, stale contracts, weak evidence, or unclear cutover would make plausible agent work dangerous.

jturntdev/krypton · 62 tokens

spec-brainstorm

Conversational design workshop for substantial work. Interviews the human one question at a time, explores 2-3 approaches with trade-offs, and presents the design section by section for approval before writing only design.md, then stops. Combines requirements discovery with codebase research and architecture design.…

martinffx/atelier · 95 tokens

atelier-orchestrator

Skill routing and workflow orchestration. Selects Inline Plan or Spec-backed Plan, routes to the correct workflow skill, and manages transitions between phases. Use when starting any conversation or task to determine which planning mode and skill apply.

martinffx/atelier · 52 tokens